Integrated optics design for vision and thermal imaging fusion

Abstract

Imaging systems and methods are disclosed for generating composite images by fusing two images generated by light beams having different spectral distributions. An imaging system generates images of a single scene on two image sensors having different spectral responses through different but partially overlapping optical paths and uses the resulting image signals to generate a composite image that captures features imaged based on visible light and thermal radiation.

Description

[0001] INTEGRATED OPTICS DESIGN FOR VISION AND THERMAL IMAGING FUSION

[0002] [1] This application claims the priority benefit of U.S. Provisional Patent Application No. 63 / 626713, entitled INTEGRATED OPTICS DESIGN FOR VISION AND THERMAL IMAGING FUSION, filed on January 30, 2024, the content of which is incorporated herein by reference in its entirety.

[0003] BRIEF DESCRIPTION OF THE FIGURES

[0004] [2] FIG. 1 is an example environment in which a vehicle including one or more components of an autonomous system can be implemented.

[0005] [3] FIG. 2 is a diagram of one or more example systems of a vehicle including an autonomous system.

[0006] [4] FIG. 3 is a diagram of components of one or more example devices and / or one or more example systems of FIGS. 1 and 2.

[0007] [5] FIG. 4A is a diagram of certain components of an example autonomous system.

[0008] [6] FIG. 4B is a diagram of certain components of an example autonomous system.

[0009] [7] FIG. 4C is a diagram of certain components of an example autonomous system.

[0010] [8] FIG. 4D is a diagram of certain components of an example autonomous system.

[0011] [9] FIG. 5 schematically illustrates a vehicle equipped with a Light Detection and Ranging (lidar) system and an imaging system. The inset shows an image captured by the imaging system of the vehicle.

[0012]

[0010] FIG. 6 is a block diagram illustrating an example imaging system having a visible (VIS) image sensor for capturing a visible image and an infrared image sensor for capturing a thermal image.

[0013]

[0011] FIG. 7 is a block diagram illustrating an example optical subsystem and arrangement of optical components therein that can be used by the imaging system shown in FIG. 6 to capture visible and infrared images of a scene via a single entrance aperture.

[0012] FIG. 8 is a diagram illustrating images generated using the VIS and infrared image sensors of the imaging system shown in FIG. 6 and an image generated by fusing the VIS and thermal images.

[0014] DETAILED DESCRIPTION

[0015]

[0013] In the following description numerous specific details are set forth in order to provide a thorough understanding of the present disclosure for the purposes of explanation. It will be apparent, however, that the embodiments described by the present disclosure can be practiced without these specific details. In some instances, well-known structures and devices are illustrated in block diagram form in order to avoid unnecessarily obscuring aspects of the present disclosure.

[0016]

[0014] Specific arrangements or orderings of schematic elements, such as those representing systems, devices, modules, instruction blocks, data elements, and / or the like are illustrated in the drawings for ease of description. However, it will be understood by those skilled in the art that the specific ordering or arrangement of the schematic elements in the drawings is not meant to imply that a particular order or sequence of processing, or separation of processes, is required unless explicitly described as such. Further, the inclusion of a schematic element in a drawing is not meant to imply that such element is required in all embodiments or that the features represented by such element may not be included in or combined with other elements in some embodiments unless explicitly described as such.

[0017]

[0015] Further, where connecting elements such as solid or dashed lines or arrows are used in the drawings to illustrate a connection, relationship, or association between or among two or more other schematic elements, the absence of any such connecting elements is not meant to imply that no connection, relationship, or association can exist. In other words, some connections, relationships, or associations between elements are not illustrated in the drawings so as not to obscure the disclosure. In addition, for ease of illustration, a single connecting element can be used to represent multiple connections, relationships or associations between elements. For example, where a connecting element represents communication of signals, data, or instructions (e.g., “software instructions”), it should be understood by those skilled in the art that such element can represent one or multiple signal paths (e.g., a bus), as may be needed, to affect the communication.

[0018]

[0016] Although the terms first, second, third, and / or the like are used to describe various elements, these elements should not be limited by these terms. The terms first, second, third, and / or the like are used only to distinguish one element from another. For example, a first contact could be termed a second contact and, similarly, a second contact could be termed a first contact without departing from the scope of the described embodiments. The first contact and the second contact are both contacts, but they are not the same contact.

[0019]

[0017] The terminology used in the description of the various described embodiments herein is included for the purpose of describing particular embodiments only and is not intended to be limiting. As used in the description of the various described embodiments and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well and can be used interchangeably with “one or more” or “at least one,” unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises,” and / or “comprising,” when used in this description specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0020]

[0018] As used herein, the terms “communication” and “communicate” refer to at least one of the reception, receipt, transmission, transfer, provision, and / or the like of information (or information represented by, for example, data, signals, messages, instructions, commands, and / or the like). For one unit (e.g., a device, a system, a component of a device or system, combinations thereof, and / or the like) to be in communication with another unit means that the one unit is able to directly or indirectly receive information from and / or send (e.g., transmit) information to the other unit. This may refer to a direct or indirect connection that is wired and / or wireless in nature. Additionally, two units may be in communication with each other even though the information transmitted may be modified, processed, relayed, and / or routed between the first and second unit. For example, a first unit may be in communication with a second unit even though the first unit passively receives information and does not actively transmit information to the second unit. As another example, a first unit may be in communication with a second unit if at least one intermediary unit (e.g., a third unit located between the first unit and the second unit) processes information received from the first unit and transmits the processed information to the second unit. In some embodiments, a message may refer to a network packet (e.g., a data packet and / or the like) that includes data.

[0021]

[0019] As used herein, the term “if” is, optionally, construed to mean “when”, “upon”, “in response to determining,” “in response to detecting,” and / or the like, depending on the context. Similarly, the phrase “if it is determined” or “if [a stated condition or event] is detected” is, optionally, construed to mean “upon determining,” “in response to determining,” “upon detecting [the stated condition or event],” “in response to detecting [the stated condition or event],” and / or the like, depending on the context. Also, as used herein, the terms “has”, “have”, “having”, or the like are intended to be open-ended terms. Further, the phrase “based on” is intended to mean “based at least partially on” unless explicitly stated otherwise.

[0022]

[0020] Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the various described embodiments. However, it will be apparent to one of ordinary skill in the art that the various described embodiments can be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

[0023] General Overview

[0024]

[0021] In some aspects and / or embodiments, systems, methods, and computer program products described herein include and / or implement improvements to the design, manufacture, operation, and / or management of an autonomous vehicle or fleet of such vehicles, components or elements of an autonomous vehicle or fleet of such vehicles, support systems for an autonomous vehicle or fleet of such vehicles, or ancillary systems related to an autonomous vehicle or fleet of such vehicles.

[0025]

[0022] By virtue of the implementation of systems, methods, and computer program products described herein, techniques for improving autonomous vehicles or fleets of such vehicles are realized (including improvement to the design, manufacture, operation, and / or management of an autonomous vehicle or fleet of such vehicles, components or elements of an autonomous vehicle or fleet of such vehicles, support systems for an autonomous vehicle or fleet of such vehicles, or ancillary systems related to an autonomous vehicle or fleet of such vehicles).

[0026]

[0023] Referring now to FIG. 1 , illustrated is example environment 100 in which vehicles that include autonomous systems, as well as vehicles that do not, are operated. As illustrated, environment 100 includes vehicles 102a-102n, objects 104a-104n, routes 106a-106n, area 108, vehicle-to-infrastructure (V2I) device 110, network 112, remote autonomous vehicle (AV) system 114, fleet management system 116, and V2I system 118. Vehicles 102a-102n, vehicle-to-infrastructure (V2I) device 110, network 112, autonomous vehicle (AV) system 114, fleet management system 116, and V2I system 118 interconnect (e.g., establish a connection to communicate and / or the like) via wired connections, wireless connections, or a combination of wired or wireless connections. In some embodiments, objects 104a-104n interconnect with at least one of vehicles 102a- 102n, vehicle-to-infrastructure (V2I) device 110, network 112, autonomous vehicle (AV) system 114, fleet management system 116, and V2I system 118 via wired connections, wireless connections, or a combination of wired or wireless connections.

[0027]

[0024] Vehicles 102a-102n (referred to individually as vehicle 102 and collectively as vehicles 102) include at least one device configured to transport goods and / or people. In some embodiments, vehicles 102 are configured to be in communication with V2I device 110, remote AV system 114, fleet management system 116, and / or V2I system 118 via network 112. In some embodiments, vehicles 102 include cars, buses, trucks, trains, and / or the like. In some embodiments, vehicles 102 are the same as, or similar to, vehicles 200, described herein (see FIG. 2). In some embodiments, a vehicle 200 of a set of vehicles 200 is associated with an autonomous fleet manager. In some embodiments, vehicles 102 travel along respective routes 106a-106n (referred to individually as route 106 and collectively as routes 106), as described herein. In some embodiments, one or more vehicles 102 include an autonomous system (e.g., an autonomous system that is the same as or similar to autonomous system 202).

[0028]

[0025] Objects 104a-104n (referred to individually as object 104 and collectively as objects 104) include, for example, at least one vehicle, at least one pedestrian, at least one cyclist, at least one structure (e.g., a building, a sign, a fire hydrant, etc.), and / or the like. Each object 104 is stationary (e.g., located at a fixed location for a period of time) or mobile (e.g., having a velocity and associated with at least one trajectory). In some embodiments, objects 104 are associated with corresponding locations in area 108.

[0029]

[0026] Routes 106a-106n (referred to individually as route 106 and collectively as routes 106) are each associated with (e.g., prescribe) a sequence of actions (also known as a trajectory) connecting states along which an AV can navigate. Each route 106 starts at an initial state (e.g., a state that corresponds to a first spatiotemporal location, velocity, and / or the like) and ends at a final goal state (e.g., a state that corresponds to a second spatiotemporal location that is different from the first spatiotemporal location) or goal region (e.g. a subspace of acceptable states (e.g., terminal states)). In some embodiments, the first state includes a location at which an individual or individuals are to be picked-up by the AV and the second state or region includes a location or locations at which the individual or individuals picked-up by the AV are to be dropped-off. In some embodiments, routes 106 include a plurality of acceptable state sequences (e.g., a plurality of spatiotemporal location sequences), the plurality of state sequences associated with (e.g., defining) a plurality of trajectories. In an example, routes 106 include only high level actions or imprecise state locations, such as a series of connected roads dictating turning directions at roadway intersections. Additionally, or alternatively, routes 106 may include more precise actions or states such as, for example, specific target lanes or precise locations within the lane areas and targeted speed at those positions. In an example, routes 106 include a plurality of precise state sequences along the at least one high level action sequence with a limited lookahead horizon to reach intermediate goals, where the combination of successive iterations of limited horizon state sequences cumulatively correspond to a plurality of trajectories that collectively form the high level route to terminate at the final goal state or region.

[0030]

[0027] Area 108 includes a physical area (e.g. , a geographic region) within which vehicles 102 can navigate. In an example, area 108 includes at least one state (e.g., a country, a province, an individual state of a plurality of states included in a country, etc.), at least one portion of a state, at least one city, at least one portion of a city, etc. In some embodiments, area 108 includes at least one named thoroughfare (referred to herein as a “road”) such as a highway, an interstate highway, a parkway, a city street, etc. Additionally, or alternatively, in some examples area 108 includes at least one unnamed road such as a driveway, a section of a parking lot, a section of a vacant and / or undeveloped lot, a dirt path, etc. In some embodiments, a road includes at least one lane (e.g., a portion of the road that can be traversed by vehicles 102). In an example, a road includes at least one lane associated with (e.g., identified based on) at least one lane marking.

[0031]

[0028] Vehicle-to-lnfrastructure (V2I) device 110 (sometimes referred to as a Vehicle-to- Infrastructure or Vehicle-to-Everything (V2X) device) includes at least one device configured to be in communication with vehicles 102 and / or V2I infrastructure system 118. In some embodiments, V2I device 110 is configured to be in communication with vehicles 102, remote AV system 114, fleet management system 116, and / or V2I system 118 via network 112. In some embodiments, V2I device 110 includes a radio frequency identification (RFID) device, signage, cameras (e.g., two-dimensional (2D) and / or three- dimensional (3D) cameras), lane markers, streetlights, parking meters, etc. In some embodiments, V2I device 110 is configured to communicate directly with vehicles 102. Additionally, or alternatively, in some embodiments V2I device 110 is configured to communicate with vehicles 102, remote AV system 114, and / or fleet management system 116 via V2I system 118. In some embodiments, V2I device 110 is configured to communicate with V2I system 118 via network 112.

[0032]

[0029] Network 112 includes one or more wired and / or wireless networks. In an example, network 112 includes a cellular network (e.g., a long term evolution (LTE) network, a third generation (3G) network, a fourth generation (4G) network, a fifth generation (5G) network, a code division multiple access (CDMA) network, etc.), a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a telephone network (e.g., the public switched telephone network (PSTN), a private network, an ad hoc network, an intranet, the Internet, a fiber opticbased network, a cloud computing network, etc., a combination of some or all of these networks, and / or the like.

[0033]

[0030] Remote AV system 114 includes at least one device configured to be in communication with vehicles 102, V2I device 110, network 112, fleet management system 116, and / or V2I system 118 via network 112. In an example, remote AV system 114 includes a server, a group of servers, and / or other like devices. In some embodiments, remote AV system 114 is co-located with the fleet management system 116. In some embodiments, remote AV system 114 is involved in the installation of some or all of the components of a vehicle, including an autonomous system, an autonomous vehicle compute, software implemented by an autonomous vehicle compute, and / or the like. In some embodiments, remote AV system 114 maintains (e.g., updates and / or replaces) such components and / or software during the lifetime of the vehicle.

[0034]

[0031] Fleet management system 116 includes at least one device configured to be in communication with vehicles 102, V2I device 110, remote AV system 114, and / or V21 infrastructure system 118. In an example, fleet management system 116 includes a server, a group of servers, and / or other like devices. In some embodiments, fleet management system 116 is associated with a ridesharing company (e.g., an organization that controls operation of multiple vehicles (e.g., vehicles that include autonomous systems and / or vehicles that do not include autonomous systems) and / or the like).

[0035]

[0032] In some embodiments, V2I system 118 includes at least one device configured to be in communication with vehicles 102, V2I device 110, remote AV system 114, and / or fleet management system 116 via network 112. In some examples, V2I system 118 is configured to be in communication with V2I device 110 via a connection different from network 112. In some embodiments, V2I system 118 includes a server, a group of servers, and / or other like devices. In some embodiments, V2I system 118 is associated with a municipality or a private institution (e.g., a private institution that maintains V2I device 110 and / or the like).

[0033] The number and arrangement of elements illustrated in FIG. 1 are provided as an example. There can be additional elements, fewer elements, different elements, and / or differently arranged elements, than those illustrated in FIG. 1. Additionally, or alternatively, at least one element of environment 100 can perform one or more functions described as being performed by at least one different element of FIG. 1. Additionally, or alternatively, at least one set of elements of environment 100 can perform one or more functions described as being performed by at least one different set of elements of environment 100.

[0036]

[0034] Referring now to FIG. 2, vehicle 200 (which may be the same as, or similar to vehicles 102 of FIG. 1 ) includes or is associated with autonomous system 202, powertrain control system 204, steering control system 206, and brake system 208. In some embodiments, vehicle 200 is the same as or similar to vehicle 102 (see FIG. 1 ). In some embodiments, autonomous system 202 is configured to confer vehicle 200 autonomous driving capability (e.g., implement at least one driving automation or maneuver-based function, feature, device, and / or the like that enable vehicle 200 to be partially or fully operated without human intervention including, without limitation, fully autonomous vehicles (e.g., vehicles that forego reliance on human intervention such as Level 5 ADS- operated vehicles), highly autonomous vehicles (e.g., vehicles that forego reliance on human intervention in certain situations such as Level 4 ADS-operated vehicles), conditional autonomous vehicles (e.g., vehicles that forego reliance on human intervention in limited situations such as Level 3 ADS-operated vehicles) and / or the like . In one embodiment, autonomous system 202 includes operational or tactical functionality required to operate vehicle 200 in on-road traffic and perform part or all of Dynamic Driving Task (DDT) on a sustained basis. In another embodiment, autonomous system 202 includes an Advanced Driver Assistance System (ADAS) that includes driver support features. Autonomous system 202 supports various levels of driving automation, ranging from no driving automation (e.g., Level 0) to full driving automation (e.g., Level 5). For a detailed description of fully autonomous vehicles and highly autonomous vehicles, reference may be made to SAE International's standard J3016: Taxonomy and Definitions for Terms Related to On-Road Motor Vehicle Automated Driving Systems, which is incorporated by reference in its entirety. In some embodiments, vehicle 200 is associated with an autonomous fleet manager and / or a ridesharing company.

[0037]

[0035] Autonomous system 202 includes a sensor suite that includes one or more devices such as cameras 202a, LiDAR sensors 202b, radar sensors 202c, and microphones 202d. In some embodiments, autonomous system 202 can include more or fewer devices and / or different devices (e.g., ultrasonic sensors, inertial sensors, GPS receivers (discussed below), odometry sensors that generate data associated with an indication of a distance that vehicle 200 has traveled, and / or the like). In some embodiments, autonomous system 202 uses the one or more devices included in autonomous system 202 to generate data associated with environment 100, described herein. The data generated by the one or more devices of autonomous system 202 can be used by one or more systems described herein to observe the environment (e.g., environment 100) in which vehicle 200 is located. In some embodiments, autonomous system 202 includes communication device 202e, autonomous vehicle compute 202f, drive-by-wire (DBW) system 202h, and safety controller 202g.

[0038]

[0036] Cameras 202a include at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and / or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG. 3). Cameras 202a include at least one camera (e.g., a digital camera using a light sensor such as charge-coupled device CCD), a thermal camera, an infrared (IR) camera, an event camera, and / or the like) to capture images including physical objects (e.g., cars, buses, curbs, people, and / or the like). In some embodiments, camera 202a generates camera data as output. In some examples, camera 202a generates camera data that includes image data associated with an image. In this example, the image data may specify at least one parameter (e.g., image characteristics such as exposure, brightness, etc., an image timestamp, and / or the like) corresponding to the image. In such an example, the image may be in a format (e.g., RAW, JPEG, PNG, and / or the like). In some embodiments, camera 202a includes a plurality of independent cameras configured on (e.g., positioned on) a vehicle to capture images for the purpose of stereopsis (stereo vision). In some examples, camera 202a includes a plurality of cameras that generate image data and transmit the image data to autonomous vehicle compute 202f and / or a fleet management system (e g., a fleet management system that is the same as or similar to fleet management system 116 of FIG. 1 ). In such an example, autonomous vehicle compute 202f determines depth to one or more objects in a field of view of at least two cameras of the plurality of cameras based on the image data from the at least two cameras. In some embodiments, cameras 202a is configured to capture images of objects within a distance from cameras 202a (e.g., up to 100 meters, up to a kilometer, and / or the like). Accordingly, cameras 202a include features such as sensors and lenses that are optimized for perceiving objects that are at one or more distances from cameras 202a.

[0039]

[0037] In an embodiment, camera 202a includes at least one camera configured to capture one or more images associated with one or more traffic lights, street signs and / or other physical objects that provide visual navigation information. In some embodiments, camera 202a generates traffic light data associated with one or more images. In some examples, camera 202a generates TLD (Traffic Light Detection) data associated with one or more images that include a format (e.g., RAW, JPEG, PNG, and / or the like). In some embodiments, camera 202a that generates TLD data differs from other systems described herein incorporating cameras in that camera 202a can include one or more cameras with a wide field of view (e.g., a wide-angle lens, a fish-eye lens, a lens having a viewing angle of approximately 120 degrees or more, and / or the like) to generate images about as many physical objects as possible.

[0040]

[0038] In some embodiments, camera 202a may generate two or more images captured using light having different spectral distributions to enable detection of physical objects that can appear brighter in one of the images. In some embodiments, camera 202a may comprise at least two image sensors having different spectral responses and configured to generate two images of the same portion of a scene using different spectral portions of the light received from the scene. In some such embodiments, the camera 202a may combine or fuse two images (e.g., digital images) received from the two image sensors to generate a composite image. In some examples, a portion of the captured scene that appear with different brightnesses on the images formed on the two different image sensors may appear with modified (e.g., enhanced) brightness according to the image within which it appear with higher brightness. In some embodiments, the camera 202a may comprise one or more features described below with respect to imaging system 600 and example optical subsystem 702 in FIGS 6 and 7. In some embodiments, the camera 202a may comprise the imaging system 600 and example optical subsystem 702 in FIGS 6 and 7.

[0041]

[0039] Light Detection and Ranging (LiDAR) sensors 202b include at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and / or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG. 3). LiDAR sensors 202b include a system configured to transmit light from a light emitter (e.g., a laser transmitter). Light emitted by LiDAR sensors 202b include light (e.g., infrared light and / or the like) that is outside of the visible spectrum. In some embodiments, during operation, light emitted by LiDAR sensors 202b encounters a physical object (e.g., a vehicle) and is reflected back to LiDAR sensors 202b. In some embodiments, the light emitted by LiDAR sensors 202b does not penetrate the physical objects that the light encounters. LiDAR sensors 202b also include at least one light detector which detects the light that was emitted from the light emitter after the light encounters a physical object. In some embodiments, at least one data processing system associated with LiDAR sensors 202b generates an image (e.g., a point cloud, a combined point cloud, and / or the like) representing the objects included in a field of view of LiDAR sensors 202b. In some examples, the at least one data processing system associated with LiDAR sensor 202b generates an image that represents the boundaries of a physical object, the surfaces (e.g., the topology of the surfaces) of the physical object, and / or the like. In such an example, the image is used to determine the boundaries of physical objects in the field of view of LiDAR sensors 202b.

[0042]

[0040] Radio Detection and Ranging (radar) sensors 202c include at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and / or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG. 3). Radar sensors 202c include a system configured to transmit radio waves (either pulsed or continuously). The radio waves transmitted by radar sensors 202c include radio waves that are within a predetermined spectrum In some embodiments, during operation, radio waves transmitted by radar sensors 202c encounter a physical object and are reflected back to radar sensors 202c. In some embodiments, the radio waves transmitted by radar sensors 202c are not reflected by some objects. In some embodiments, at least one data processing system associated with radar sensors 202c generates signals representing the objects included in a field of view of radar sensors 202c. For example, the at least one data processing system associated with radar sensor 202c generates an image that represents the boundaries of a physical object, the surfaces (e.g., the topology of the surfaces) of the physical object, and / or the like. In some examples, the image is used to determine the boundaries of physical objects in the field of view of radar sensors 202c.

[0043]

[0041] Microphones 202d includes at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and / or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG. 3). Microphones 202d include one or more microphones (e.g., array microphones, external microphones, and / or the like) that capture audio signals and generate data associated with (e.g., representing) the audio signals. In some examples, microphones 202d include transducer devices and / or like devices. In some embodiments, one or more systems described herein can receive the data generated by microphones 202d and determine a position of an object relative to vehicle 200 (e.g., a distance and / or the like) based on the audio signals associated with the data.

[0044]

[0042] Communication device 202e includes at least one device configured to be in communication with cameras 202a, LiDAR sensors 202b, radar sensors 202c, microphones 202d, autonomous vehicle compute 202f, safety controller 202g, and / or DBW (Drive-By-Wire) system 202h. For example, communication device 202e may include a device that is the same as or similar to communication interface 314 of FIG. 3. In some embodiments, communication device 202e includes a vehicle-to-vehicle (V2V) communication device (e.g., a device that enables wireless communication of data between vehicles).

[0045]

[0043] Autonomous vehicle compute 202f include at least one device configured to be in communication with cameras 202a, LiDAR sensors 202b, radar sensors 202c, microphones 202d, communication device 202e, safety controller 202g, and / or DBW system 202h. In some examples, autonomous vehicle compute 202f includes a device such as a client device, a mobile device (e.g., a cellular telephone, a tablet, and / or the like), a server (e.g., a computing device including one or more central processing units, graphical processing units, and / or the like), and / or the like. In some embodiments, autonomous vehicle compute 202f is the same as or similar to autonomous vehicle compute 400, described herein. Additionally, or alternatively, in some embodiments autonomous vehicle compute 202f is configured to be in communication with an autonomous vehicle system (e.g., an autonomous vehicle system that is the same as or similar to remote AV system 114 of FIG. 1 ), a fleet management system (e.g., a fleet management system that is the same as or similar to fleet management system 116 of FIG. 1 ), a V2I device (e.g., a V2I device that is the same as or similar to V2I device 110 of FIG. 1 ), and / or a V2I system (e.g., a V2I system that is the same as or similar to V2I system 118 of FIG. 1 ).

[0046]

[0044] Safety controller 202g includes at least one device configured to be in communication with cameras 202a, LiDAR sensors 202b, radar sensors 202c, microphones 202d, communication device 202e, autonomous vehicle computer 202f, and / or DBW system 202h. In some examples, safety controller 202g includes one or more controllers (electrical controllers, electromechanical controllers, and / or the like) that are configured to generate and / or transmit control signals to operate one or more devices of vehicle 200 (e.g., powertrain control system 204, steering control system 206, brake system 208, and / or the like). In some embodiments, safety controller 202g is configured to generate control signals that take precedence over (e.g., overrides) control signals generated and / or transmitted by autonomous vehicle compute 202f.

[0047]

[0045] DBW system 202h includes at least one device configured to be in communication with communication device 202e and / or autonomous vehicle compute 202f. In some examples, DBW system 202h includes one or more controllers (e.g., electrical controllers, electromechanical controllers, and / or the like) that are configured to generate and / or transmit control signals to operate one or more devices of vehicle 200 (e.g., powertrain control system 204, steering control system 206, brake system 208, and / or the like). Additionally, or alternatively, the one or more controllers of DBW system 202h are configured to generate and / or transmit control signals to operate at least one different device (e.g., a turn signal, headlights, door locks, windshield wipers, and / or the like) of vehicle 200.

[0046] Powertrain control system 204 includes at least one device configured to be in communication with DBW system 202h. In some examples, powertrain control system 204 includes at least one controller, actuator, and / or the like. In some embodiments, powertrain control system 204 receives control signals from DBW system 202h and powertrain control system 204 causes vehicle 200 to make longitudinal vehicle motion, such as start moving forward, stop moving forward, start moving backward, stop moving backward, accelerate in a direction, decelerate in a direction or to make lateral vehicle motion such as performing a left turn, performing a right turn, and / or the like. In an example, powertrain control system 204 causes the energy (e.g., fuel, electricity, and / or the like) provided to a motor of the vehicle to increase, remain the same, or decrease, thereby causing at least one wheel of vehicle 200 to rotate or not rotate.

[0048]

[0047] Steering control system 206 includes at least one device configured to rotate one or more wheels of vehicle 200. In some examples, steering control system 206 includes at least one controller, actuator, and / or the like. In some embodiments, steering control system 206 causes the front two wheels and / or the rear two wheels of vehicle 200 to rotate to the left or right to cause vehicle 200 to turn to the left or right. In other words, steering control system 206 causes activities necessary for the regulation of the y-axis component of vehicle motion.

[0049]

[0048] Brake system 208 includes at least one device configured to actuate one or more brakes to cause vehicle 200 to reduce speed and / or remain stationary. In some examples, brake system 208 includes at least one controller and / or actuator that is configured to cause one or more calipers associated with one or more wheels of vehicle 200 to close on a corresponding rotor of vehicle 200. Additionally, or alternatively, in some examples brake system 208 includes an automatic emergency braking (AEB) system, a regenerative braking system, and / or the like.

[0050]

[0049] In some embodiments, vehicle 200 includes at least one platform sensor (not explicitly illustrated) that measures or infers properties of a state or a condition of vehicle 200. In some examples, vehicle 200 includes platform sensors such as a global positioning system (GPS) receiver, an inertial measurement unit (IMU), a wheel speed sensor, a wheel brake pressure sensor, a wheel torque sensor, an engine torque sensor, a steering angle sensor, and / or the like. Although brake system 208 is illustrated to be located in the near side of vehicle 200 in FIG. 2, brake system 208 may be located anywhere in vehicle 200.

[0051]

[0050] Referring now to FIG. 3, illustrated is a schematic diagram of a device 300. As illustrated, device 300 includes processor 304, memory 306, storage component 308, input interface 310, output interface 312, communication interface 314, and bus 302. In some embodiments, device 300 corresponds to at least one device of vehicles 102 (e.g., at least one device of a system of vehicles 102), at least one device of the remote AV system 114, at least one device of the fleet management system 116, at least one device of the vehicle-to-infrastructure system 118, and / or one or more devices of network 112 (e.g., one or more devices of a system of network 112). In some embodiments, one or more devices of vehicles 102 (e.g., one or more devices of a system of vehicles 102), at least one device of the remote AV system 114, at least one device of the fleet management system 116, at least one device of the vehicle-to-infrastructure system 118, and / or one or more devices of network 112 (e.g., one or more devices of a system of network 112) include at least one device 300 and / or at least one component of device 300. As shown in FIG. 3, device 300 includes bus 302, processor 304, memory 306, storage component 308, input interface 310, output interface 312, and communication interface 314.

[0052]

[0051] Bus 302 includes a component that permits communication among the components of device 300. In some cases, the processor 304 includes a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), and / or the like), a microphone, a digital signal processor (DSP), and / or any processing component (e.g., a field-programmable gate array (FPGA), an application specific integrated circuit (ASIC), and / or the like) that can be programmed to perform at least one function. Memory 306 includes random access memory (RAM), readonly memory (ROM), and / or another type of dynamic and / or static storage device (e.g., flash memory, magnetic memory, optical memory, and / or the like) that stores data and / or instructions for use by processor 304.

[0053]

[0052] Storage component 308 stores data and / or software related to the operation and use of device 300. In some examples, storage component 308 includes a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optic disk, a solid state disk, and / or the like), a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a cartridge, a magnetic tape, a CD-ROM, RAM, PROM, EPROM, FLASH-EPROM, NV-RAM, and / or another type of computer readable medium, along with a corresponding drive.

[0054]

[0053] Input interface 310 includes a component that permits device 300 to receive information, such as via user input (e.g., a touchscreen display, a keyboard, a keypad, a mouse, a button, a switch, a microphone, a camera, and / or the like). Additionally or alternatively, in some embodiments input interface 310 includes a sensor that senses information (e.g., a global positioning system (GPS) receiver, an accelerometer, a gyroscope, an actuator, and / or the like). Output interface 312 includes a component that provides output information from device 300 (e.g., a display, a speaker, one or more lightemitting diodes (LEDs), and / or the like).

[0055]

[0054] In some embodiments, communication interface 314 includes a transceiver-like component (e.g., a transceiver, a separate receiver and transmitter, and / or the like) that permits device 300 to communicate with other devices via a wired connection, a wireless connection, or a combination of wired and wireless connections. In some examples, communication interface 314 permits device 300 to receive information from another device and / or provide information to another device. In some examples, communication interface 314 includes an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi® interface, a cellular network interface, and / or the like.

[0056]

[0055] In some embodiments, device 300 performs one or more processes described herein. Device 300 performs these processes based on processor 304 executing software instructions stored by a computer-readable medium, such as memory 305 and / or storage component 308. A computer-readable medium (e.g., a non-transitory computer readable medium) is defined herein as a non-transitory memory device. A non-transitory memory device includes memory space located inside a single physical storage device or memory space spread across multiple physical storage devices.

[0057]

[0056] In some embodiments, software instructions are read into memory 306 and / or storage component 308 from another computer-readable medium or from another device via communication interface 314. When executed, software instructions stored in memory 306 and / or storage component 308 cause processor 304 to perform one or more processes described herein. Additionally or alternatively, hardwired circuitry is used in place of or in combination with software instructions to perform one or more processes described herein. Thus, embodiments described herein are not limited to any specific combination of hardware circuitry and software unless explicitly stated otherwise.

[0058]

[0057] Memory 306 and / or storage component 308 includes data storage or at least one data structure (e.g., a database and / or the like). Device 300 is capable of receiving information from, storing information in, communicating information to, or searching information stored in the data storage or the at least one data structure in memory 306 or storage component 308. In some examples, the information includes network data, input data, output data, or any combination thereof.

[0059]

[0058] In some embodiments, device 300 is configured to execute software instructions that are either stored in memory 306 and / or in the memory of another device (e.g., another device that is the same as or similar to device 300). As used herein, the term “module” refers to at least one instruction stored in memory 306 and / or in the memory of another device that, when executed by processor 304 and / or by a processor of another device (e.g., another device that is the same as or similar to device 300) cause device 300 (e.g., at least one component of device 300) to perform one or more processes described herein. In some embodiments, a module is implemented in software, firmware, hardware, and / or the like.

[0060]

[0059] The number and arrangement of components illustrated in FIG. 3 are provided as an example. In some embodiments, device 300 can include additional components, fewer components, different components, or differently arranged components than those illustrated in FIG. 3. Additionally or alternatively, a set of components (e.g., one or more components) of device 300 can perform one or more functions described as being performed by another component or another set of components of device 300.

[0061]

[0060] Referring now to FIG. 4, illustrated is an example block diagram of an autonomous vehicle compute 400 (sometimes referred to as an “AV stack”). As illustrated, autonomous vehicle compute 400 includes perception system 402 (sometimes referred to as a perception module), planning system 404 (sometimes referred to as a planning module), localization system 406 (sometimes referred to as a localization module), control system 408 (sometimes referred to as a control module), and database 410. In some embodiments, perception system 402, planning system 404, localization system 406, control system 408, and database 410 are included and / or implemented in an autonomous navigation system of a vehicle (e.g., autonomous vehicle compute 202f of vehicle 200). Additionally, or alternatively, in some embodiments perception system 402, planning system 404, localization system 406, control system 408, and database 410 are included in one or more standalone systems (e.g., one or more systems that are the same as or similar to autonomous vehicle compute 400 and / or the like). In some examples, perception system 402, planning system 404, localization system 406, control system 408, and database 410 are included in one or more standalone systems that are located in a vehicle and / or at least one remote system as described herein. In some embodiments, any and / or all of the systems included in autonomous vehicle compute 400 are implemented in software (e.g., in software instructions stored in memory), computer hardware (e.g., by microprocessors, microcontrollers, application-specific integrated circuits (ASICs), Field Programmable Gate Arrays (FPGAs), and / or the like), or combinations of computer software and computer hardware. It will also be understood that, in some embodiments, autonomous vehicle compute 400 is configured to be in communication with a remote system (e.g., an autonomous vehicle system that is the same as or similar to remote AV system 114, a fleet management system 116 that is the same as or similar to fleet management system 116, a V2I system that is the same as or similar to V2I system 118, and / or the like).

[0062]

[0061] In some embodiments, perception system 402 receives data associated with at least one physical object (e.g., data that is used by perception system 402 to detect the at least one physical object) in an environment and classifies the at least one physical object. In some examples, perception system 402 receives image data captured by at least one camera (e.g., cameras 202a), the image associated with (e.g., representing) one or more physical objects within a field of view of the at least one camera. In such an example, perception system 402 classifies at least one physical object based on one or more groupings of physical objects (e.g., bicycles, vehicles, traffic signs, pedestrians, and / or the like). In some embodiments, perception system 402 transmits data associated with the classification of the physical objects to planning system 404 based on perception system 402 classifying the physical objects.

[0062] In some embodiments, planning system 404 receives data associated with a destination and generates data associated with at least one route (e.g., routes 106) along which a vehicle (e.g., vehicles 102) can travel along toward a destination. In some embodiments, planning system 404 periodically or continuously receives data from perception system 402 (e.g., data associated with the classification of physical objects, described above) and planning system 404 updates the at least one trajectory or generates at least one different trajectory based on the data generated by perception system 402. In other words, planning system 404 may perform tactical function-related tasks that are required to operate vehicle 102 in on-road traffic. Tactical efforts involve maneuvering the vehicle in traffic during a trip, including but not limited to deciding whether and when to overtake another vehicle, change lanes, or selecting an appropriate speed, acceleration, deacceleration, etc. In some embodiments, planning system 404 receives data associated with an updated position of a vehicle (e.g., vehicles 102) from localization system 406 and planning system 404 updates the at least one trajectory or generates at least one different trajectory based on the data generated by localization system 406.

[0063]

[0063] In some embodiments, localization system 406 receives data associated with (e.g., representing) a location of a vehicle (e.g., vehicles 102) in an area. In some examples, localization system 406 receives LiDAR data associated with at least one point cloud generated by at least one LiDAR sensor (e.g., LiDAR sensors 202b). In certain examples, localization system 406 receives data associated with at least one point cloud from multiple LiDAR sensors and localization system 406 generates a combined point cloud based on each of the point clouds. In these examples, localization system 406 compares the at least one point cloud or the combined point cloud to two-dimensional (2D) and / or a three-dimensional (3D) map of the area stored in database 410. Localization system 406 then determines the position of the vehicle in the area based on localization system 406 comparing the at least one point cloud or the combined point cloud to the map. In some embodiments, the map includes a combined point cloud of the area generated prior to navigation of the vehicle. In some embodiments, maps include, without limitation, high- precision maps of the roadway geometric properties, maps describing road network connectivity properties, maps describing roadway physical properties (such as traffic speed, traffic volume, the number of vehicular and cyclist traffic lanes, lane width, lane traffic directions, or lane marker types and locations, or combinations thereof), and maps describing the spatial locations of road features such as crosswalks, traffic signs or other travel signals of various types. In some embodiments, the map is generated in real-time based on the data received by the perception system.

[0064]

[0064] In another example, localization system 406 receives Global Navigation Satellite System (GNSS) data generated by a global positioning system (GPS) receiver. In some examples, localization system 406 receives GNSS data associated with the location of the vehicle in the area and localization system 406 determines a latitude and longitude of the vehicle in the area. In such an example, localization system 406 determines the position of the vehicle in the area based on the latitude and longitude of the vehicle. In some embodiments, localization system 406 generates data associated with the position of the vehicle. In some examples, localization system 406 generates data associated with the position of the vehicle based on localization system 406 determining the position of the vehicle. In such an example, the data associated with the position of the vehicle includes data associated with one or more semantic properties corresponding to the position of the vehicle.

[0065]

[0065] In some embodiments, control system 408 receives data associated with at least one trajectory from planning system 404 and control system 408 controls operation of the vehicle. In some examples, control system 408 receives data associated with at least one trajectory from planning system 404 and control system 408 controls operation of the vehicle by generating and transmitting control signals to cause a powertrain control system (e.g., DBW system 202h, powertrain control system 204, and / or the like), a steering control system (e.g., steering control system 206), and / or a brake system (e.g., brake system 208) to operate. For example, control system 408 is configured to perform operational functions such as a lateral vehicle motion control or a longitudinal vehicle motion control. The lateral vehicle motion control causes activities necessary for the regulation of the y-axis component of vehicle motion. The longitudinal vehicle motion control causes activities necessary for the regulation of the x-axis component of vehicle motion. In an example, where a trajectory includes a left turn, control system 408 transmits a control signal to cause steering control system 206 to adjust a steering angle of vehicle 200, thereby causing vehicle 200 to turn left. Additionally, or alternatively, control system 408 generates and transmits control signals to cause other devices (e.g., headlights, turn signal, door locks, windshield wipers, and / or the like) of vehicle 200 to change states.

[0066]

[0066] In some embodiments, perception system 402, planning system 404, localization system 406, and / or control system 408 implement at least one machine learning model (e.g., at least one multilayer perceptron (MLP), at least one convolutional neural network (CNN), at least one recurrent neural network (RNN), at least one autoencoder, at least one transformer, and / or the like). In some examples, perception system 402, planning system 404, localization system 406, and / or control system 408 implement at least one machine learning model alone or in combination with one or more of the above-noted systems. In some examples, perception system 402, planning system 404, localization system 406, and / or control system 408 implement at least one machine learning model as part of a pipeline (e.g., a pipeline for identifying one or more objects located in an environment and / or the like). An example of an implementation of a machine learning model is included below with respect to FIGS. 4B-4D.

[0067]

[0067] Database 410 stores data that is transmitted to, received from, and / or updated by perception system 402, planning system 404, localization system 406 and / or control system 408. In some examples, database 410 includes a storage component (e.g., a storage component that is the same as or similar to storage component 308 of FIG. 3) that stores data and / or software related to the operation and uses at least one system of autonomous vehicle compute 400. In some embodiments, database 410 stores data associated with 2D and / or 3D maps of at least one area. In some examples, database 410 stores data associated with 2D and / or 3D maps of a portion of a city, multiple portions of multiple cities, multiple cities, a county, a state, a State (e.g., a country), and / or the like). In such an example, a vehicle (e.g., a vehicle that is the same as or similar to vehicles 102 and / or vehicle 200) can drive along one or more drivable regions (e.g., single-lane roads, multi-lane roads, highways, back roads, off road trails, and / or the like) and cause at least one LiDAR sensor (e.g., a LiDAR sensor that is the same as or similar to LiDAR sensors 202b) to generate data associated with an image representing the objects included in a field of view of the at least one LiDAR sensor.

[0068] In some embodiments, database 410 can be implemented across a plurality of devices. In some examples, database 410 is included in a vehicle (e.g., a vehicle that is the same as or similar to vehicles 102 and / or vehicle 200), an autonomous vehicle system (e.g., an autonomous vehicle system that is the same as or similar to remote AV system 114, a fleet management system (e.g., a fleet management system that is the same as or similar to fleet management system 116 of FIG. 1 , a V2I system (e.g., a V2I system that is the same as or similar to V2I system 118 of FIG. 1 ) and / or the like.

[0068]

[0069] Referring now to FIG. 4B, illustrated is a diagram of an implementation of a machine learning model. More specifically, illustrated is a diagram of an implementation of a convolutional neural network (CNN) 420. For purposes of illustration, the following description of CNN 420 will be with respect to an implementation of CNN 420 by perception system 402. However, it will be understood that in some examples CNN 420 (e.g., one or more components of CNN 420) is implemented by other systems different from, or in addition to, perception system 402 such as planning system 404, localization system 406, and / or control system 408. While CNN 420 includes certain features as described herein, these features are provided for the purpose of illustration and are not intended to limit the present disclosure.

[0069]

[0070] CNN 420 includes a plurality of convolution layers including first convolution layer 422, second convolution layer 424, and convolution layer 426. In some embodiments, CNN 420 includes sub-sampling layer 428 (sometimes referred to as a pooling layer). In some embodiments, sub-sampling layer 428 and / or other subsampling layers have a dimension (i.e., an amount of nodes) that is less than a dimension of an upstream system. By virtue of sub-sampling layer 428 having a dimension that is less than a dimension of an upstream layer, CNN 420 consolidates the amount of data associated with the initial input and / or the output of an upstream layer to thereby decrease the amount of computations necessary for CNN 420 to perform downstream convolution operations. Additionally, or alternatively, by virtue of sub-sampling layer 428 being associated with (e.g., configured to perform) at least one subsampling function (as described below with respect to FIGS. 4C and 4D), CNN 420 consolidates the amount of data associated with the initial input. In some cases, the initial input may include one or both thermal and visible images (e.g., digital images) generated by the imaging system 600 and example optical subsystem 702 described below with respect to FIGS 6 and 7. In some cases, the initial input may include a composite image generated by the imaging system 600 and example optical subsystem 702 described below with respect to FIGS 6 and 7.

[0070]

[0071] Perception system 402 performs convolution operations based on perception system 402 providing respective inputs and / or outputs associated with each of first convolution layer 422, second convolution layer 424, and convolution layer 426 to generate respective outputs. In some examples, perception system 402 implements CNN 420 based on perception system 402 providing data as input to first convolution layer 422, second convolution layer 424, and convolution layer 426. In such an example, perception system 402 provides the data as input to first convolution layer 422, second convolution layer 424, and convolution layer 426 based on perception system 402 receiving data from one or more different systems (e.g., one or more systems of a vehicle that is the same as or similar to vehicle 102), a remote AV system that is the same as or similar to remote AV system 114, a fleet management system that is the same as or similar to fleet management system 116, a V2I system that is the same as or similar to V2I system 118, and / or the like). A detailed description of convolution operations is included below with respect to FIG. 4C.

[0071]

[0072] In some embodiments, perception system 402 provides data associated with an input (referred to as an initial input) to first convolution layer 422 and perception system 402 generates data associated with an output using first convolution layer 422. In some embodiments, perception system 402 provides an output generated by a convolution layer as input to a different convolution layer. For example, perception system 402 provides the output of first convolution layer 422 as input to sub-sampling layer 428, second convolution layer 424, and / or convolution layer 426. In such an example, first convolution layer 422 is referred to as an upstream layer and sub-sampling layer 428, second convolution layer 424, and / or convolution layer 426 are referred to as downstream layers. Similarly, in some embodiments perception system 402 provides the output of sub-sampling layer 428 to second convolution layer 424 and / or convolution layer 426 and, in this example, sub-sampling layer 428 would be referred to as an upstream layer and second convolution layer 424 and / or convolution layer 426 would be referred to as downstream layers.

[0073] In some embodiments, perception system 402 processes the data associated with the input provided to CNN 420 before perception system 402 provides the input to CNN 420. For example, perception system 402 processes the data associated with the input provided to CNN 420 based on perception system 402 normalizing sensor data (e.g., image data, LiDAR data, radar data, and / or the like).

[0072]

[0074] In some embodiments, CNN 420 generates an output based on perception system 402 performing convolution operations associated with each convolution layer. In some examples, CNN 420 generates an output based on perception system 402 performing convolution operations associated with each convolution layer and an initial input. In some embodiments, perception system 402 generates the output and provides the output as fully connected layer 430. In some examples, perception system 402 provides the output of convolution layer 426 as fully connected layer 430, where fully connected layer 430 includes data associated with a plurality of feature values referred to as F1 , F2 . . . FN. In this example, the output of convolution layer 426 includes data associated with a plurality of output feature values that represent a prediction.

[0073]

[0075] In some embodiments, perception system 402 identifies a prediction from among a plurality of predictions based on perception system 402 identifying a feature value that is associated with the highest likelihood of being the correct prediction from among the plurality of predictions. For example, where fully connected layer 430 includes feature values F1 , F2, . . . FN, and F1 is the greatest feature value, perception system 402 identifies the prediction associated with F1 as being the correct prediction from among the plurality of predictions. In some embodiments, perception system 402 trains CNN 420 to generate the prediction. In some examples, perception system 402 trains CNN 420 to generate the prediction based on perception system 402 providing training data associated with the prediction to CNN 420.

[0074]

[0076] Referring now to FIGS. 4C and 4D, illustrated is a diagram of example operation of CNN 440 by perception system 402. In some embodiments, CNN 440 (e.g., one or more components of CNN 440) is the same as, or similar to, CNN 420 (e.g., one or more components of CNN 420) (see FIG. 4B).

[0075]

[0077] At step 450, perception system 402 provides data associated with an image as input to CNN 440 (step 450). For example, as illustrated, perception system 402 provides the data associated with the image to CNN 440, where the image is a greyscale image represented as values stored in a two-dimensional (2D) array. In some embodiments, the data associated with the image may include data associated with a color image, the color image represented as values stored in a three-dimensional (3D) array. Additionally, or alternatively, the data associated with the image may include data associated with an infrared image, a radar image, and / or the like.

[0076]

[0078] At step 455, CNN 440 performs a first convolution function. For example, CNN 440 performs the first convolution function based on CNN 440 providing the values representing the image as input to one or more neurons (not explicitly illustrated) included in first convolution layer 442. In this example, the values representing the image can correspond to values representing a region of the image (sometimes referred to as a receptive field). In some embodiments, each neuron is associated with a filter (not explicitly illustrated). A filter (sometimes referred to as a kernel) is representable as an array of values that corresponds in size to the values provided as input to the neuron. In one example, a filter may be configured to identify edges (e.g., horizontal lines, vertical lines, straight lines, and / or the like). In successive convolution layers, the filters associated with neurons may be configured to identify successively more complex patterns (e.g., arcs, objects, and / or the like).

[0077]

[0079] In some embodiments, the image provided as input to CNN 440 or another CNN may include one or both thermal and visible images (e.g., digital images) generated by the imaging system 600 and example optical subsystem 702 described below with respect to FIGS 6 and 7. In some embodiments, the image provided as input to CNN 440 or another CNN may include a composite image generated by the imaging system 600 and example optical subsystem 702 described below with respect to FIGS 6 and 7.

[0078]

[0080] In some embodiments, CNN 440 performs the first convolution function based on CNN 440 multiplying the values provided as input to each of the one or more neurons included in first convolution layer 442 with the values of the filter that corresponds to each of the one or more neurons. For example, CNN 440 can multiply the values provided as input to each of the one or more neurons included in first convolution layer 442 with the values of the filter that corresponds to each of the one or more neurons to generate a single value or an array of values as an output. In some embodiments, the collective output of the neurons of first convolution layer 442 is referred to as a convolved output. In some embodiments, where each neuron has the same filter, the convolved output is referred to as a feature map.

[0079]

[0081] In some embodiments, CNN 440 provides the outputs of each neuron of first convolutional layer 442 to neurons of a downstream layer. For purposes of clarity, an upstream layer can be a layer that transmits data to a different layer (referred to as a downstream layer). For example, CNN 440 can provide the outputs of each neuron of first convolutional layer 442 to corresponding neurons of a subsampling layer. In an example, CNN 440 provides the outputs of each neuron of first convolutional layer 442 to corresponding neurons of first subsampling layer 444. In some embodiments, CNN 440 adds a bias value to the aggregates of all the values provided to each neuron of the downstream layer. For example, CNN 440 adds a bias value to the aggregates of all the values provided to each neuron of first subsampling layer 444. In such an example, CNN 440 determines a final value to provide to each neuron of first subsampling layer 444 based on the aggregates of all the values provided to each neuron and an activation function associated with each neuron of first subsampling layer 444.

[0080]

[0082] At step 460, CNN 440 performs a first subsampling function. For example, CNN 440 can perform a first subsampling function based on CNN 440 providing the values output by first convolution layer 442 to corresponding neurons of first subsampling layer 444. In some embodiments, CNN 440 performs the first subsampling function based on an aggregation function. In an example, CNN 440 performs the first subsampling function based on CNN 440 determining the maximum input among the values provided to a given neuron (referred to as a max pooling function). In another example, CNN 440 performs the first subsampling function based on CNN 440 determining the average input among the values provided to a given neuron (referred to as an average pooling function). In some embodiments, CNN 440 generates an output based on CNN 440 providing the values to each neuron of first subsampling layer 444, the output sometimes referred to as a subsampled convolved output.

[0081]

[0083] At step 465, CNN 440 performs a second convolution function. In some embodiments, CNN 440 performs the second convolution function in a manner similar to how CNN 440 performed the first convolution function, described above. In some embodiments, CNN 440 performs the second convolution function based on CNN 440 providing the values output by first subsampling layer 444 as input to one or more neurons (not explicitly illustrated) included in second convolution layer 446. In some embodiments, each neuron of second convolution layer 446 is associated with a filter, as described above. The filter(s) associated with second convolution layer 446 may be configured to identify more complex patterns than the filter associated with first convolution layer 442, as described above.

[0082]

[0084] In some embodiments, CNN 440 performs the second convolution function based on CNN 440 multiplying the values provided as input to each of the one or more neurons included in second convolution layer 446 with the values of the filter that corresponds to each of the one or more neurons. For example, CNN 440 can multiply the values provided as input to each of the one or more neurons included in second convolution layer 446 with the values of the filter that corresponds to each of the one or more neurons to generate a single value or an array of values as an output.

[0083]

[0085] In some embodiments, CNN 440 provides the outputs of each neuron of second convolutional layer 446 to neurons of a downstream layer. For example, CNN 440 can provide the outputs of each neuron of first convolutional layer 442 to corresponding neurons of a subsampling layer. In an example, CNN 440 provides the outputs of each neuron of first convolutional layer 442 to corresponding neurons of second subsampling layer 448. In some embodiments, CNN 440 adds a bias value to the aggregates of all the values provided to each neuron of the downstream layer. For example, CNN 440 adds a bias value to the aggregates of all the values provided to each neuron of second subsampling layer 448. In such an example, CNN 440 determines a final value to provide to each neuron of second subsampling layer 448 based on the aggregates of all the values provided to each neuron and an activation function associated with each neuron of second subsampling layer 448.

[0084]

[0086] At step 470, CNN 440 performs a second subsampling function. For example, CNN 440 can perform a second subsampling function based on CNN 440 providing the values output by second convolution layer 446 to corresponding neurons of second subsampling layer 448. In some embodiments, CNN 440 performs the second subsampling function based on CNN 440 using an aggregation function. In an example, CNN 440 performs the first subsampling function based on CNN 440 determining the maximum input or an average input among the values provided to a given neuron, as described above. In some embodiments, CNN 440 generates an output based on CNN 440 providing the values to each neuron of second subsampling layer 448.

[0085]

[0087] At step 475, CNN 440 provides the output of each neuron of second subsampling layer 448 to fully connected layers 449. For example, CNN 440 provides the output of each neuron of second subsampling layer 448 to fully connected layers 449 to cause fully connected layers 449 to generate an output. In some embodiments, fully connected layers 449 are configured to generate an output associated with a prediction (sometimes referred to as a classification). The prediction may include an indication that an object included in the image provided as input to CNN 440 includes an object, a set of objects, and / or the like. In some embodiments, perception system 402 performs one or more operations and / or provides the data associated with the prediction to a different system, described herein.

[0086]

[0088] In the foregoing description, aspects and embodiments of the present disclosure have been described with reference to numerous specific details that can vary from implementation to implementation. Accordingly, the description and drawings are to be regarded in an illustrative rather than a restrictive sense. The sole and exclusive indicator of the scope of the invention, and what is intended by the applicants to be the scope of the invention, is the literal and equivalent scope of the set of claims that issue from this application, in the specific form in which such claims issue, including any subsequent correction. Any definitions expressly set forth herein for terms contained in such claims shall govern the meaning of such terms as used in the claims. In addition, when we use the term “further comprising,” in the foregoing description or following claims, what follows this phrase can be an additional step or entity, or a sub-step / sub-entity of a previously- recited step or entity.

[0087]

[0089] Further details regarding particular improvements contemplated are provided in the sections below directed to multispectral imaging. It should be understood that statements made with respect to the imaging systems described below should be understood to refer to the embodiments disclosed below, and not necessarily to all embodiments of the present disclosure. For example, statements indicating that certain features are necessary or essential, in the context of the imaging systems described below, to the extent such statements exist, should be understood to refer to the necessity or essentiality of such features with respect to the embodiments of these imaging systems. Such statements do not indicate that such features are necessary or essential for all embodiments of the present disclosure. Similarly, term definitions in the sections below should be understood to define terms in the context of the corresponding imaging systems and such definitions may not apply to the remainder of this disclosure.

[0088]

[0090] The improvements discussed with respect to the imaging systems described below may represent computer-implementable improvements implemented within the systems described herein with respect to FIGS. 1-4. For example, the improvements discussed with respect to the imaging systems described below may be implemented in whole or in part by a device 300 of FIG. 3, such as by execution on the processor 304 of FIG. 3 of computer code stored within memory 306 of FIG. 3, which code implements the improvement of the corresponding imaging systems described below. In one embodiment, the device 300 is located within a vehicle, such as the vehicle 200 of FIG. 2. In another embodiment, the device 300 is located externally to a vehicle, such as in a remote AV system 114, fleet management system 116, orvehicle-to-infrastructure system 118 of FIG. 1. Additionally or alternatively, the improvements discussed within ?? may represent improvement components for elements of FIG. 1 , including improvement components of a vehicle 102, a remote AV system 114, fleet management system 116, or vehicle-to-infrastructure system 118 of FIG. 1. Accordingly, the improvements discussed in sections below may be bodily incorporated into one or more of the above- mentioned elements of FIG. 1 to improvement such elements. As one example, improvements to LiDAR sensors may be used to modify LiDAR sensor 202b of FIG. 2. Further details regarding an example implementation of the LiDAR sensor 202b of FIG. 2 are provided in U.S. Patent Application No. 17 / 931 ,051 , entitled “SYSTEMS AND METHODS FOR TIME-OF-FLIGHT (TOF) LIDAR SIGNAL-TO-NOISE IMPROVEMENT” and filed September 9, 2022 (Att’y docket no: MOTN.057A), the entirety of which is hereby incorporated by reference herein.

[0089]

[0091] The imaging systems, and methods described below could be incorporated into such various type of autonomous vehicles and self-driving cars for examples those disclosed in U.S. Patent Application Publication Nos 17 / 444,966, entitled “END-TO-END SYSTEM TRAINING USING FUSED IMAGES” and filed August 12, 2021 , and 17 / 443,433, entitled “VEHICLE LOCATION USING COMBINED INPUTS OF REDUNDANT LOCALIZATION PIPELINES” and filed July 26, 2021 , the entire contents of which are incorporated by reference herein and made a part of this specification.

[0090] Vision System with Integrated Visible and Thermal Imaging

[0091]

[0092] In various imaging systems two or more images captured by different image sensors, or at two different times by a single image sensor may be combined or fused to generate a fused or composite image. In some cases, the process of combining image information (e.g., relevant information from) two or more images into a single composite image may be referred to as image fusion.

[0092]

[0093] In some cases, a fused image generated by fusing two or more input images can be more informative and accurate than the input images individually. In various imaging applications, e.g., remote sensing, medical imaging, military applications, and computer vision, image fusion may be used to enhance image quality, improve decision-making, reduce data volume, among other improvements. For example, integrating complementary information from different images in a fused image may provide more detail, more clarity, and more comprehensive information, each one of which may aid in better analysis and interpretation. In some cases, image fusion may include fusing two input images captured by two different image sensors having different spectral responses or sensitivities (e.g., a thermal image sensor and a visible image sensor). Advantageously, a composite or fused image formed by fusing images captured by two image sensors having different spectral sensitivities (herein referred to as spectrally complementary input images) may include features that may be unclear or absent in one of the input images captured by one of these image sensors.

[0093]

[0094] One of the challenges of image fusion can be image registration and / or aligning the input images (e.g., images captured by different images sensors and / or at different times) to accurately preserve the geometrical features of the captured image scene in the resulting composite image. In some cases, aligning the input images can be difficult due to differences in perspective, resolution, and field of view of the imaging systems used to capture the input images. In some cases, inaccurate alignment and / or misalignment between features of different input images in a resulting fused image may lead to low resolution, inaccuracies, and other defects and deficiencies of the fused image.

[0094]

[0095] In some cases, when two input images are captured by two separate imaging systems (e.g., two cameras), the misalignment between the input images can be due to relative movements and / or vibrations between the two imaging systems. For example, when the two cameras are mounted on a moving platform (e.g., a vehicle such as a car) mechanical vibrations of the moving platform may cause misalignment between the images captured by these cameras. In some cases, the two cameras may include a vision camera configured to capture images based on light having wavelength within visible wavelength range (e.g., from 380 to 780 nanometers) and a thermal camera configured to capture images based on electromagnetic radiation having wavelength within longwave infrared (LWIR) wavelength range (e.g., from 8 to 15 micrometers) or, in some cases, mid-wave infrared (MWIR) wavelength range (e.g., from 2.5 to 8 micrometers).

[0095]

[0096] In some implementations, the two imaging systems (e.g., a vision camera and a thermal camera) can be mounted (e.g., separately mounted) on a vehicle to allow detection of humans and animals to prevent fatal accidents particularly in low light conditions (e.g., at night). In some cases, alignment error between images captured by the two imaging systems (e.g., a vision camera and a thermal camera), e.g., due to manufacturing tolerances, thermal movement, mechanical vibrations (when the cameras are mounted a vehicle) can be as large as 3 degrees; such a large misalignment may negatively affect the accuracy of the image fusion process and thereby the accuracy of the resulting fused image.

[0096]

[0097] In some of the imaging systems disclosed herein (described below), the magnitude of misalignment between two images captured by two different imaging devices, such as a vision camera and a thermal camera mounted on a vehicle, may be significantly reduced (e.g., to less than 0.5 degrees), by integrating (e.g., optically integrating) the two imaging devices. In some cases, optically integrating the two imaging systems may include redirecting light or electromagnetic radiation received from the environment through a single entrance aperture to two different image sensors (e.g., a VIS image sensor and a thermal image sensor) via two partially overlapping optical paths extended between the single entrance aperture and two images sensors having different spectral response (e.g., within VIS and thermal wavelength ranges). In some, embodiments the overlapping portion of the two optical paths may provide high transmission for light (or radiation) within both VIS and thermal wavelength ranges (e.g., including LWIR and MWIR), and the two non-overlapping portions may each provide high transmission for light (or radiation) within one of the VIS and thermal wavelength ranges.

[0097]

[0098] Some of the imaging systems disclosed herein (described below), may include imaging systems configured to be mounted on vehicle to image an environment surrounding the vehicle, e.g., to environment to generate images, information, control signals or commands usable for safely driving the vehicle.

[0098]

[0099] In some embodiments, imaging systems disclosed below may allow generate accurate composite images formed by spectrally complementary images captures by different image sensors having different spectral responses. In some cases, the disclosed imaging systems may be mounted on a vehicle and can be configured to generate composite images formed by fusing accurately aligned visible light and thermal images. A visible light image (herein referred to as visible image) can be an image formed by light having wavelengths within the visible wavelength range and a thermal image can be an image formed by thermal radiation light or electromagnetic radiation having wavelengths within MWIR or LWIR wavelength range. In some cases, such composite (or fused) image may allow identifying obstacles and moving subjects in the environment surrounding the vehicle, e.g., in a low light condition (e.g., at night or in a tunnel). In some cases, the composite image formed by fusing a thermal and a visible image may include information and features missing from one of the thermal and visible images. For example, certain features, e.g., traffic signs, road markings, or features comprising multiple colors may not be identified due to lack contrast and / or visibility. Similarly, on a visible image captured in a low-light condition certain other features, e.g., humans, animals, colors may not be easily identifiable.

[0099]

[0100] In some embodiments, the disclosed imaging systems may include an integrated optical design that can provide partially overlapping optical paths comprising a common field of view (FOV) and entrance aperture (or window) for forming visible and thermal images of the same scene on two image sensors having different spectral responses. In some cases, the shared portion of the two optical path lengths may be configured to allow formation of images having substantially the same perspective and the same elements / features of the scene on the two image sensors.

[0100]

[0101] The disclosed methods and systems can significantly reduce and potentially eliminate misalignment between images captured by visible and thermal imagers and enable generation of highly accurate composite images using integrated visible and thermal imagers. In some examples, the imaging system can form first and second images of a scene on first and second sensors, respectively. The first and the second images can be formed via a first optical path and a second optical path, different from the first optical path, respectively. In some cases, the first and second optical paths are at least partially overlapping.

[0101]

[0102] In some cases, the first optical path can be configured to selectively transmit light having wavelengths within a first wavelength range (e.g., VIS wavelength range) and the second optical path can be configured to selectively transmit light having a wavelength within a second wavelength range (e.g., LWIR and / or MIR wavelength range). In some cases, the first optical path can be configured to provide greater optical transmission for light having wavelengths within the first wavelength range compared to light having wavelengths within the second wavelength range. In some such cases, the second optical path can be configured to provide greater optical transmission for light having wavelengths within the second wavelength range compared to light having wavelengths within the first wavelength range.

[0102]

[0103] In some examples, the non-overlapping portions of the first and second optical paths can be generated by a dichroic beam splitter that transmits light having wavelength within a first wavelength range (e.g., visible wavelength range) and redirects (e.g., rotates by 90 degrees) light having a wavelength within a second wavelength range (e.g., LWIR or MWIR wavelength range). Additionally, or alternatively, one or more optical components or surfaces in the first optical path can be configured to reject light having wavelengths within the second wavelength range (e.g., LWIR or MWIR wavelength range) and one or more optical components or surfaces in the second optical path can be configured to reject light having wavelengths within the first wavelength range.

[0104] In some cases, the first and second images can be substantially identical images of the same scene having the same magnification but with different spectral distributions. For example, the first image can have a spectral distribution with a peak wavelength in the visible wavelength range and the second image can have a spectral distribution with a peak wavelength in the near infrared wavelength range.

[0103]

[0105] In some implementations, the first image sensor can have high sensitivity (or a peak sensitivity) in the visible (VIS) wavelength range and the second image sensor has high sensitivity (or a peak sensitivity) in LWIR (or MWIR) wavelength range. An image sensor having high sensitivity (or a peak sensitivity) in the visible (VIS) wavelength range can be referred to as VIS image sensor and an image sensor having high sensitivity (or a peak sensitivity) in the in LWIR (or MWIR) wavelength range can be commonly referred to as LWIR (or MWIR) image sensor. In some cases, the first and the second wavelength ranges can be non-overlapping (i.e. , mutually exclusive) or partially overlapping. In some examples, the first image sensor can be sensitive to light from 380 to 780 nanometers and the second image sensor can be sensitive to light from 2.5 to 4 micrometers, from 4 micrometers to 7.5 micrometers, from 7.5 to 10 micrometers, from 10 to 15 micrometers, from 8 to 12 micrometers, from 8 to 15 micrometers, or any ranges formed by these values or larger or smaller ranges. In some examples, a difference between a peak response wavelength of the first image sensor and the second image sensor can be from 5 to 7.5 micrometers, from 7.5 to 8.5 micrometers, from 8.5 to 9.5 micrometers, from 9.5 to 10.5 micrometers, from 10.5 to 11.5 micrometers or any ranges formed by these values or larger or smaller values. In some cases, where the two image sensors (e.g., the VIS and LWIR sensors) have different spectral sensitivities, the first and the second images can be substantially identical images of the same scene having the same magnification and spectral distribution. In some embodiments, the first image sensor may include silicon, gallium arsenide (GaAs), indium gallium arsenide (InGaAs), perovskites (e.g., CsPbBrs), graphene, or other materials.

[0104]

[0106] In some embodiments, the second image sensor may include a bolometer, a thermocouple, a thermopile, a pyroelectric, microbolomter detector, or a detector comprising quantum wells and / or superlattices.

[0107] In some embodiments, the second image sensor may include Mercury Cadmium Telluride (HgCdTe or MCT), Indium Gallium Arsenide (InGaAs), Lead Sulfide (PbS) and Lead Selenide (PbSe, indium antimonide (InSb), or other materials (e.g., heterostructures and compound semiconductors).

[0105]

[0108] In some such cases, the first and second optical paths through which the first and the second images are formed can provide similar or substantially identical spectral transmissions. For example, both paths can provide the same amount of optical transmission for light having wavelengths in the LWIR (and / or MWIR) wavelength range and light having wavelength within the VIS wavelength range. In some cases, e.g., when the two image sensors have different spectral sensitivities, the two different optical paths can be generated by a beam splitter that does not discriminate between LWIR (or MWIR) and VIS wavelengths (e.g., a beam splitter having the same splitting ratio for light having wavelengths within LWIR (MWIR) wavelength range and light having wavelengths within VIS wavelength range).

[0106]

[0109] In some embodiments, the imaging system may fuse the first and second image sensors to generate a fused or composite image comprising features captured by the VIS image sensor and the LWIR (or MWIR) images sensor. In some cases, the imaging system may process (e.g., modify) a digital image of a scene generated using the first and / or second image sensors, before fusing the VIS and thermal images (e.g., LWIR or MWIR images).

[0107] Imaging and Sensing Systems of a Vehicle

[0108]

[0110] FIG. 5 schematically illustrates a vehicle 500 equipped with an imaging system 502. In some cases, in addition to the imaging system 502 may include a Light Detection and Ranging (lidar) system 504. In some case one or both the imaging system 502 and the lidar system 504 may be configured to detect and image objects (both luminous and non-luminous objects), and other vehicles in an environment surrounding the vehicle 500. In some cases, the vehicle 500, can be an autonomous or semi-autonomous vehicle (e.g., a vehicle having a driving automation level from 1 -6 as defined by The Society of Automotive Engineers or SAE). The imaging system 502 can include at least one digital camera configured to generate images of a portion of the surrounding environment. In some cases, the images generated by the imaging system 502 of the vehicle 500 can include fused or composite digital images generated by processing two or more digital images or digital image signals received from two or more image sensors (e.g., sensors having different spectral responses). In some cases, the vehicle 500 may include a light source configured to illuminate a scene to enhance the images of the scene generated by the imaging system 502.

[0109]

[0111] In some cases, the lidar system 504 may generate and steer optical probe beams and receive reflections of the optical beams to detect objects in the environment. In various implementations, the lidar system 504 can be a scanning lidar system, or a mechanical lidar system. A scanning lidar system scans one or more optical probe beams over a wide field of view of a detector while the mechanical lidar system emits a single optical probe beam (e.g., a low divergence optical beam) to illuminate a narrow field of view of a detector and scans (e.g., rotates) the detector and the optical probe beam.

[0110]

[0112] In some embodiments, the imaging system 502 (e.g., a digital camera) may generate images (e.g., digital images) using the image signals (digital image signals) received from one or more image sensors. The imaging system 502 can include one or more optical components that receive light from the environment and form images on two or more image sensors. The optical components can form optical trains positioned along optical paths from the environment to the image sensors. In some cases, a first optical train that directs light from the environment to the first image sensor through a first optical path can provide substantially the same optical transformation as a second optical train that directs light from the environment to the second image sensor through a second optical path. In some cases, the first and second optical trains can have different spectral transmissions but be otherwise identical (e.g., have the same image formation properties). In some cases, the first and second optical trains can have different spectral transmissions and can be configured to form two images of the same portion of a scene on two different image sensors having different spectral responses, where the two images are magnified by substantially the same amount, are captured through the same field of view, and include the same perspective of the scene.

[0111]

[0113] In some cases, both optical paths can receive light from the same scene via a common entrance aperture or optical input port. In some examples, at least a portion of the first optical path can overlap with the second optical path. As a result, a first image projected on the first image sensor by the first optical train can be substantially identical to a second image projected on the second image sensor by the second optical train (e.g., having the same magnification).

[0112]

[0114] One or more image signals generated by the imaging system 502 can be used by a control and processing system to generate an image (e.g., a digital image) of a portion of a scene or surrounding environment. In some implementations, the control and processing system can generate a digital image (e.g., a modified digital image) using at least a first image signal received from the first image sensor and a second image received from the second image sensor. In some examples, the control and processing system generates a first image using the first image signal, generates a second image using the second image signal, makes a comparison between the first and the second images, and generates a third digital image based on the comparison. In some cases, generating the third image can include modifying the first digital image based on the second digital image (e.g., modifying a portion of the first digital image based on the respective portion of the second digital image). In some cases, the control and processing can synchronize the first and second image sensors and / or process the first and second image signals in a synchronous manner, such that the first and the second digital images correspond to images of the same scene captured at the same time. In some implementations, the control and processing can synchronize the imaging system 502 with the lidar system 504. In some such implementations, the first and / or the second image signals are generated in a time interval during which the lidar system 504 is emitting optical probe beams. In some cases, the first and / or the second image signals, or two subsequent images signals received from the first and the second image sensors, are generated in a time interval during which the lidar system 504 does not emit any optical probe beams.

[0113]

[0115] With continued reference to FIG. 5, the control and processing system of the imaging system 502 can generate an image 530 (a digital image) of a scene in the environment. In some cases, image 530 can be generated using an image signal received from an image sensor of the imaging system 502 (e.g., a VIS image sensor or a LWIR image sensor). In the example shown, the scene captured by the imaging system 502 includes an incoming vehicle 510, and the light sources and sensors carried by the vehicle 510, and human subject 506. Accordingly, image 530 includes a depiction 511 of the incoming vehicle 510, and a depiction 507 of the human subject 506.

[0114]

[0116] In some examples, the incoming vehicle 510 can include a second lidar system 514 that emit light beams for range finding. As such, image 530 includes a depiction 515 of the lidar system 514 and depiction 513 of the light source 512. In some cases, one, two, or all of the lidar system 514, light source 512 can emit light having wavelength within a wavelength range (e.g., LWIR wavelength range) that at least partially overlap with a spectral response of the image sensor using which the image 530 is generated.

[0115]

[0117] In some cases, the imaging system 502 can include a VIS image sensor with a sensitivity in the VIS range. In some such cases, in a low light environment, e.g., at night and in the absence of a sufficiently bright external light source, a non-lum inous object, a human, or an animal may not be sufficiently in an image captured by the VIS image sensor. Herein, non-luminous objects may include objects that do not emit electromagnetic radiation having wavelengths within visible wavelength range or within sensitivity range of the VIS image sensor.

[0116]

[0118] Advantageously, in certain aspects, an imaging system may include at least one image sensor, in addition to the VIS image sensor, having a spectral response in the LWIR range. In some embodiments, the imaging system may use image signals received from the LWIR image sensor to improve the visibility of the non-luminous physical objects, human subjects, or animals, and the like in a composite digital image generated by fusing the images captured by the VIS and LWIR image sensors.

[0117] Imaging systems with Image Sensors having Different Spectral Responses

[0118]

[0119] FIG. 6 is a block diagram illustrating an example imaging system 600 having a visible (VIS) image sensor 611 for capturing a visible image and a long wave infrared (LWIR) image sensors 612 for capturing a LWIR or thermal image. In some cases, a thermal image can be a LWIR or MWIR image.

[0119]

[0120] In some cases, the imaging system 600 can generate a composite or fused digital image including depictions of certain non-luminous elements in the scene that generate electromagnetic radiation having wavelengths in thermal or long-wave infrared wavelength range. In some cases, the imaging system 600 includes an optical subsystem 602, at least two image sensors 611 , 612, and a control and processing system 622. In some cases, the optical subsystem 622 can be an integrated optical system comprising two partially overlapping optical paths from a single entrance aperture to two different image sensors. The imaging system 600 receives light from the scene forms a first image on the first image sensor 611 and a second image on the second image sensor 612. In response to formation of the first and second images, the first and the second image sensors 611 , 612, can generate first and second image signals 614, 616, and transmit the first and second image signals 614, 616 to the control and processing system 622. In some embodiments, the imaging system 600 may transmit the first and second image signals 614, 616, to another system.

[0120]

[0121] In some cases, the first image signal 614 includes a first digital image associated with the first image of a scene formed on the first image sensor 611 , and the second image signals 616 includes a second digital image associated with the second image of the same scene formed on the second image sensor 612. In some cases, the first image can have a spectral intensity distribution different from that of the second image but be other otherwise identical to the second image (e.g., have substantially the same magnification, the same features of the scene, the same perspective of the scene).

[0121]

[0122] In some examples, the first and second image signals 614, 616, include electrical signals carrying information (e.g., digital information) usable for generating the first and the second digital images, respectively.

[0122]

[0123] The control and processing system 622 can use the first and the second image signals 614, 616 to generate a third image signal 226. In some cases, the third image signal 226 may include a composite or fused digital image. In some cases, the control and processing system 622 may transmit the composite or fused digital image to a navigation system or a display of vehicle 500 (or the autonomous vehicle compute 202f of the vehicle 200). In some embodiments, the third image signal 626 may include an electrical signal carrying information (e.g., digital information) usable for generating the composite digital image. In some cases, generating the composite digital image may include enhancing or adjusting the brightness of certain features that may not be sufficiently visible on the first or the second image. In some cases, generating the composite digital image may include enhancing or adjusting the brightness and / or contrast of image of a region of the scene that has different brightnesses and / or contrasts on the first image (or the corresponding first digital image) and on the second image (or the corresponding second digital image) based at least in part on one of the first or second images (e.g., the image on which the image region appears with more brightness and / or contrast). In some embodiments, the third image signal 626 include the composite digital image.

[0123]

[0124] In some implementations, the control and processing system 622 can transmit the third image signal 626 to a display system that uses the third image signal 626 to generate an image viewable via a user interface. Additionally, or alternatively, the control and processing system 622 can transmit the third image signal 626 to a navigation system that uses at least the third image signal for navigation in an environment. In some examples, the navigation system uses the third signal in combination with signals received from a lidar system (e.g., the lidar 504) for navigation in the environment. The lidar system 504, the imaging system 502, and the navigation system can be mounted on a single vehicle 500 (e.g., an AV) and navigation in the environment can include detecting objects and obstacles in the environment and determining their position and velocity with respect to the vehicle.

[0124]

[0125] In some embodiments, the first image sensor 611 can have a first spectral response and the second image sensor can have a second spectral response different from the first spectral response. In some examples, a second peak sensitivity wavelength of the second spectral response can be larger than a first peak sensitivity wavelength of the first spectral response by at least 1 micrometer, at least 2 micrometers, at least 3 micrometers, at least 4 micrometers, at least 5 micrometers, at least 6 micrometers, at least 8 micrometers, or larger values. In some cases, peak sensitivity wavelength of a spectral response can be a wavelength at which the spectral response is larger than the spectral responses at other wavelengths within a response bandwidth of the corresponding image sensor (e.g., an operational bandwidth of the image sensor). In some cases, peak sensitivity wavelength of a spectral response can be an average or mean wavelength associated with a spectral response and calculated based on wavelengths at which the sensitivity is larger than a threshold value.

[0126] In some examples, the first image sensor 611 can have a peak responsivity in the visible wavelength range. In some examples, the first image sensors 611 can have first response bandwidth including wavelengths from 400 nm to 700 nm, from 380 nm to 780 nm, from 400 nm to 1100 nm, or any ranges formed by these values or larger or smaller values.

[0125]

[0127] In some examples, the first image sensor 611 can have a peak responsivity in the mid infrared or long-wave infrared wavelength range. In some examples, the second image sensor 612 can have a second response bandwidth including wavelengths from 7.5 micrometers to 12 micrometers, from 8 micrometers to 12 micrometers, from 9 micrometers to 13 micrometers, from 12 micrometers to 15 micrometers or any ranges formed by these values or larger or smaller values.

[0126]

[0128] In some embodiments, the first image sensor 611 may include a complementary metal-oxide-sem iconductor (CMOS) sensor (e.g., a silicon based sensor) or a sensor including HIV compound semiconductor (e.g., Gallium Arsenide, GaAs, or Indium Gallium Arsenide, InGaAs, Indium Phosphide, InP, or a combination thereof). In some embodiments, the second image sensor 612 may include a microbolometer or an antimony-based photodetector (e.g., an antimony-based photodetector based on type-ll superlattice), or another photodetector configured to generate an electric signal in response to receiving light having wavelengths in MWIR or LWIR wavelength range.

[0127]

[0129] In some embodiments, the first and second image sensors 611 , 612 can be zoom- capable imagers capable of generating a zoomed image that can be smaller or larger compared to an image projected on the corresponding sensor. In some examples, the first and second image sensors 611 , 612 can allow digital zooming on a digital image.

[0128]

[0130] In some embodiments, an overlap between a response or sensitivity bandwidth of the first image sensor 611 and the second image sensor 612 can be less than 30%, less than 20%, less than 10%, or smaller values.

[0129]

[0131] In some embodiments, the optical subsystem 602 can include an objective lens group 608 (also referred to as objective optical train), a dichroic beam splitter (e.g., a dichroic prism) 604, a first imaging lens group 609 (also referred to as first optical train), and a second imaging lens group 610 (also referred to as second optical train). It will be understood, however, that the optical subsystem 602 may include fewer or more components. Accordingly, the example optical subsystem 602 should not be construed as limiting.

[0130]

[0132] The objective lens group 608 receives light rays 618A from a scene or an environment via an entrance aperture 624, transforms the received light rays, and transmits the transformed light rays 618b to the dichroic beam splitter (e.g., dichroic prism) 604. In some cases, the entrance aperture 624 can include a shutter (e.g., a mechanical or electro-optical shutter) through which light enters the optical subsystem 602 from the scene. An imaging control signal can open the shutter to allow formation of images on the VIS and LWIR image sensors 611 , 612 or close the shutter to block light from entering the optical subsystem 602. In various embodiments, the time at which one or both the first and second image sensors 611 , 612, generate image signals including an image of the scene may be controlled by controlling the shutter and / or by electronically activating the image sensors.

[0131]

[0133] In some examples, light rays 618A, received via entrance aperture 624, are intercepted by a first lens of the objective lens group 608, and the transformed light rays 618B include light rays exiting the last lens of the objective lens group 608. The objective lens group 608 can generate the transformed light rays 618B by redirecting one or more of the light rays that are intercepted by a first lens and outputting the redirected light rays via the last lens. It will be understood, however, that the lens group 608 may include fewer (e.g., one lens) or more lenses (e.g., more than two lenses). Accordingly, the example lens group 608 should not be construed as limiting.

[0132]

[0134] The dichroic beam splitter 604 transmits a first portion 632 of the transformed light rays 618B received from the objective lens group 608 toward the first imaging lens group 609, and redirects a second portion 630 of the transformed light rays 618B toward the second imaging lens group 610. The first portion 632 of the transformed light rays 618B can include light having wavelengths within a first wavelength range (or bandwidth), e.g., VIS wavelength range, and the second portion 630 of the transformed light rays 618B can include light having wavelengths within the second wavelength range different from the first wavelength range, e.g., LWIR (or MWIR) wavelength range. In some cases, the first and second wavelength ranges can be non-overlapping wavelength ranges. In some other cases, the first and second wavelength ranges can be partially overlapping wavelength ranges. The first wavelength range can at least partially overlap with the response spectrum of the first imaging sensor 611 and the second wavelength range can at least partially overlap with the response spectrum of the second imaging sensor 612.

[0133]

[0135] In some cases, dichroic beam splitter 604 may divide light from a scene into a first portion and a second portion having different spectral distributions. In some such cases, the first portion can include wavelengths within visible wavelength range and the second portion includes wavelengths within mid-wave infrared (MWIR) or long-wave infrared (LWIR) wavelength range. In some cases, the spectral distribution of the first portion can have a mean value within visible (VIS) wavelength range and a spectral distribution of the second portion can have a mean value within MWIR or LWIR wavelength range. Accordingly, in some examples, the dichroic beam splitter 604 can transmit light having wavelengths from 380 nm to 780 nm to the first imaging lens group 609 and redirect (e.g., reflect) light having wavelengths from 7.5 micrometers to 12 micrometers, from 12 micrometers to 15 micrometers, or from 8 micrometers to 15 micrometers, to the second imaging lens group 610. As such, in these examples, the first portion 632 of the transformed light rays 618b received by the first imaging lens group 609 can have a wavelength distribution within VIS wavelength range (e.g., having a mean value within VIS wavelength range), and the second portion 630 of the transformed light rays 618b received by the second imaging lens group 610 can have a wavelength distribution within LWIR wavelength range(e.g., having a mean value within LWIR wavelength range).

[0134]

[0136] In some examples, one or more optical surfaces of the first imaging lens group 609 can include an antireflection layer or coating configured to reduce or potentially eliminate Fresnel reflection at least in a portion of the first wavelength range (e.g., VIS wavelength range), and one or more optical surfaces of the second imaging lens group 610 can include an antireflection layer or coating configured to reduce or potentially eliminate Fresnel reflection at least in a portion of the second wavelength range (e.g., LWIR wavelength range).

[0135]

[0137] In some examples, one or more optical surfaces of the first imaging lens group 609 can include coating or layers configured to selectively transmit at least a portion of light having wavelengths within the first wavelength range (e.g., VIS wavelength range) and reject / or block light having wavelengths within the second wavelength range (e.g., LWIR wavelength range). In some examples, one or more optical surfaces of the second imaging lens group 610 can include coating or layers configured to selectively transmit at least a portion of light having wavelengths within the second wavelength range (e.g., LWIR wavelength range) and reject / or block light having wavelengths within the first wavelength range (e.g., VIS wavelength range).

[0136]

[0138] In some embodiments, the lenses in the first imaging lens group 609 include or can be formed from materials having low within the first wavelength range (e.g., VIS wavelength range) and the lenses in the second imaging lens group 610 include or can be formed from materials having low within the second wavelength range (e.g., LWIR wavelength range). For example, the lenses in the first imaging lens group 609 can include silica, quartz, or other type of glasses and the lenses in the second imaging lens group 610 can include zinc selenide (ZnSe), germanium (Ge), GASIR, zinc sulfide (ZnS), calcium fluoride (CaF2), magnesium fluoride (MgF2), and sapphire (AI2O3), and the like.

[0137]

[0139] The first imaging lens group 609 further transforms the first portion 632 of the transformed light rays 618b to form a first image on the first image sensor 611 , and the second imaging lens group 610 further transforms the second portion 630 of the transformed light rays 618b to form a second image on the second image sensor 612. The first and the second lens groups 609 / 608 can be substantially identical lens groups or can have identical optical transformation properties (e.g., redirect a given bundle of input rays the same way, have identical linear and angular magnifications, and the like). As such the first and the second images formed on the first and the second images sensors 611 / 612 can be images of the same portion of the scene and with the same magnification. In some cases, the first and the second images formed on the first and the second images sensors 611 / 612 can be images of the same portion of the scene and with the same magnification while having different spectral characteristics (due to spectral properties of the dichroic beam splitter 604 and possibly coating applied to a component in one or both optical trains). For example, the first image can be formed by light having a wavelength distribution within VIS spectral range (e.g., having a mean value within VIS wavelength range), and the second image can be formed by light having a wavelength distribution within LWIR spectral range (e.g., having a mean value within LWIR wavelength range). As such when the first and the second image sensors 611 , 612 have similar or substantially identical spectral responses, features generated by LWIR light (e.g., from a lidar sensor) can have a greater brightness level in a digital image of a scene generated by the second image sensor 612 compared to a digital image of the same scene generated by the first image sensor 611. The imaging system 600 can include a housing that includes the entrance aperture 624 configured to admit light from the scene or environment and houses the optical subsystem 602, the image sensors 611 , 612. In some implementations, at least a portion of the control and processing system 622 can be included in the housing.

[0138]

[0140] In some cases, the control and processing system 622 can include a memory and at least one processor configured to execute the machine-readable instructions stored in the memory. The control and processing system 622 can include a field programmable gate array (FPGA), a memory unit, a digital signal processing unit, and an internal wireless transceiver.

[0139]

[0141] In some cases, the control and processing system 622, may control the first and second image sensors such that they output image signals associated with the same scene (e.g., captured at the same time) and, in some cases, at the same time. In some implementations the control and processing system 622 can process the VIS image signals 614 and the LWIR image signals 616 such image signals associated with the same scene and at the same time are processes together (e.g., compared together).

[0140]

[0142] The capability of the optical system 600 for generating two images of the scene with substantially equal magnifications (e.g., using substantially identical sequence of optical elements), combined with synchronized generation and processing of the image signals, allows the control and processing system 622 to make a direct comparison between respective portions of the two digital images received from VIS and LWIR image sensors and generate a modified digital image. In some examples, the direct comparison can include pixel-to-pixel comparison, comparing shapes and / or sizes or respective regions on the two images.

[0141]

[0143] Although shown as a dichroic beam splitter 604, it will be understood that other prisms can be used as the beam splitter. In some cases, the beam splitter can generate two images having similar or the same spectral properties with same or different intensities. For example, when the peak spectral response of the first and the second image sensors 611 , 612 are sufficiently different or the second image sensor 612 has very low sensitivity to VIS wavelengths, the dichroic beam splitter 604 can be replaced by a non-dichroic beam splitter (e.g., a spectrally neutral beam splitter) having a splitting ratio between 95 / 5 to 50 / 50 within a spectral range at least partially overlapping with the LWIR and VIS spectral ranges. In these examples, the splitting ratio of the beam splitter can be selected based on the spectral sensitivity of the first and the second image sensors 611 , 612 to facilitate balancing the brightness of the VIS and LWIR images formed on the VIS and LWIR image sensors 611 , 612.

[0142]

[0144] It should be understood, in various implementations, one or a combination of components and / or features including but not limited to dichroic beam splitting, coatings or filters having wavelength selective transmission or reflection properties, and imaging sensors having different spectral responses, can be used to provide a first image signal 614 (e.g., a VIS image signal) comprising a first digital image of a scene and a second image signal 616 (e.g., a LWIR image signal) comprising a second digital image of the same scene, where signatures of LWIR light from the scene on the second digital image are brighter than the respective signatures on the first digital image.

[0143]

[0145] In some various implementations, the optical subsystem 602 can have a narrow, medium size, or wide field of view (FOV). The FOV of the optical subsystem 602 may be determined based at least in part on the characteristics of the one or both the first and second image sensors 611 , 612.

[0144]

[0146] In some embodiments, the optical paths from the entrance aperture 624 to the first and second image sensors 611 / 612 may include the same field of view (FOV).

[0145]

[0147] In various implementations, the optical subsystem 602 can have narrow, mid-size, or wide-angle field of view (FOV). In some examples, the optical subsystem 602 can be from 20 to 50 degrees, from 50 to 100 degrees, from 100 to 150 degrees, from 150 to 180 degrees, or any range formed by these values or larger or smaller values.

[0146]

[0148] In some embodiments, the relative alignment accuracy between vision and thermal optical images captured by the first and second image sensors 611 , 612 of the imaging system 600 cannot be affected by mechanical vibrations and thermal movement. As such the composite images generated using the first and second image signals 614, 616 respectively may be used to generate an accurate composite image with greatly reduced alignment error and robust image quality (compared to a composite image generated using image signals received from separate VIS and thermal cameras). In some examples, the reduced alignment error can result in more efficient, accurate and robust sensor fusion process. In some examples, due to reduced alignment error, the imaging system 600 can generate a more accurate composite image by consuming less power and / or computational resources and in a shorter processing time, using digital images captured by the optical subsystem 602. Further, since the VIS and LWIR optical paths of the optical subsystem 602 share at least the objective lens group 608, the imaging system may generate multiple images using a smaller number of optical components and may have a smaller form factor compared to a lower bill of materials (BOM) compared to imaging systems, to imaging systems having separate VIS and LWIR imaging systems.

[0147]

[0149] In some embodiments, the first optical path from the entrance aperture 624 to the first image sensor 611 and the second optical path from the entrance aperture 624 to the second image sensor 612 may provide different F-numbers. For example, when the first image sensor is a VIS image sensor and the second image sensor is a LWIR image sensor (e.g., a thermal image sensor), the F number of the first optical path can be larger than that of the second optical path to allow more light to be provided to the LWIR image sensor.

[0148]

[0150] In some embodiments, one or both the first and second image signals 614, 616 may be transmitted to another system (e.g., the autonomous vehicle compute 202f of the autonomous system 202 in vehicle 200) and can be separately processed. In some embodiments, the control and processing system 622 can transmit one or more of the first, second, and third image signal 616, 614, 626 to a navigation system that uses at least the third image signal for navigation in an environment.

[0149]

[0151] FIG. 7 is a block diagram illustrating optical subsystem 702 that is an example implementation of the optical subsystem 602 showing example arrangement of optical components for the objective, first, and second lens groups in the optical subsystem 602.

[0150]

[0152] The first and second imaging lens groups 709, 710, of the optical subsystem 702, each may include a plurality of lenses including positive, negative, doublet, singlet lenses, and the like configured to transform the optical rays received from the objective lens group 708 to form an image having specified properties on the respective image sensors. In some embodiments, the first and second imaging lens groups 709, 710 may include groups of lenses arranged and positioned to form first and second images configured according to characteristics of the first and second image sensors 611 , 612, respectively.

[0151]

[0153] In some embodiments, the first and second images may include substantially the same portion of a scene captured by the objective lens group 708. In some embodiments, images features of the captured scene may include substantially the same geometrical relation with respect to each other, on the first and second images. In some embodiments, a first geometrical relation between a feature of the first image and a first boundary of the first image can be substantially identical to a second geometrical relation between a respective feature of the second image and a second boundary of the second image.

[0152]

[0154] In the example shown in FIG. 7, the objective lens group 708 of the optical subsystem 702 includes two singlet lenses, the first imaging lens group 709 of the optical subsystem includes three doublet lenses and three singlet lenses, and the second imaging lens group 710 of the optical subsystem 702 includes four singlet lenses. In some cases, the first and second imaging lens groups can have different spectral transmissions and can be configured to form two images of the same portion of a scene on two different image sensors having different spectral responses, where the two images are magnified by substantially the same amount, are captured through the same field of view, and include the same perspective of the scene.

[0153]

[0155] In some examples, a lens of the first and / or second imaging lens groups 709, 710 may be bonded (e.g., pre-bonded) to the dichroic beam splitter 604. In some examples, using dichroic beam splitter 604 with pre-bonded singlet lenses can facilitate the optical alignment of the optical subsystem 702 and improve its accuracy. In some cases, the dichroic beam splitter 604 includes at least one pre-bonded singlet lens (e.g., a single lens in the first imaging lens group 709). In some cases, the dichroic beam splitter 604 includes two pre-bonded singlet lenses in the first and second imaging lens groups 709, 710, respectively. Additionally, pre-bonding the singlet lenses to the dichroic beam splitter 604 can reduce or potentially eliminate Fresnel reflections (e.g., by eliminating or reducing the air gap between the singlet lens and the dichroic beam splitter) and thereby improve optical transmission to from the objective lens group 708 to the lenses in each of the imaging lens groups.

[0156] In some embodiments, one or both the VIS optical path, from the entrance aperture 624 to the VIS imaging sensor 611 , and the LWIR optical path, from the entrance aperture 624 to the LWIR imaging sensor 612, may include one or more aperture stops positioned along the respective optical path. In some cases, an entrance pupil or aperture stop 706 of VIS imaging may be located on an exit surface of the dichroic beam splitter 604 facing the first imaging lens group 709. In some cases, an entrance pupil or aperture stop 706 for LWIR imaging may be located on an entrance surface of the dichroic beam splitter 604 facing the objective lens group 708. In some examples, the first imaging lens group

[0154] 709 and the corresponding aperture stop may be configured to provide an F number of 2.4 for the VIS image formed on the first image sensor 611. In some examples, the first imaging lens group 709 and the corresponding aperture stop may be configured to provide an F number of 1 for the LWIR image formed on the first image sensor 611. However, the embodiments are not so limited and various embodiments, the F numbers associated with the LWIR and VIS optical paths can have other values, e.g., the F number for the LWIR image can be from 0.8 to 1 , from 1 to 1 .3, from 1 .3 to 1 .6, or other values, and F number for the VIS image can be from 1 .2 to 1 .5, from 1 .5 to 3, from 3 to 8, from 8 to 16, or other values depending on the lighting condition (e.g., day, night, dark, bright and the like)

[0155]

[0157] In some embodiments, the objective lens group 708 may be configured to allow transmission of light having wavelength within a broad wavelength range spanning at least portions of VIS wavelength range and LWIR wavelength range to allow both VIS and LWIR light to be transmitted to the dichroic beam splitter 604. Accordingly, in some examples, the lenses of the objective imaging lens group 708 may include a material having low absorption for light having wavelengths within at least portions of VIS wavelength range and LWIR wavelength range.

[0156]

[0158] For example, the lenses of the objective imaging lens group 708 may include zinc selenide (ZnS) that can transmit light having wavelengths from 0.4 micrometers to 18 micrometers with relative low absorption.

[0157]

[0159] The first imaging lens group 709 may be configured to allow transmission of light having wavelengths within VIS wavelength range, and the second imaging lens group

[0158] 710 may be configured to allow transmission of light having wavelengths within LWIR wavelength range. In some embodiments, the first imaging lens group 709 may be further configured to prevent transmission of light having wavelengths within LWIR wavelength range, and the second imaging lens group 710 may be further configured to prevent transmission of light having wavelengths within VIS wavelength range. In some examples, the lenses of the first imaging lens group 709 may include a material having low absorption in VIS wavelength range, and in some cases high absorption in LWIR range. In some examples, the lenses of the second imaging lens group 709 may include a material having low absorption at least in LWIR wavelength range, and in some cases high absorption in VIS range. In some examples, the lenses of the first imaging lens group 709 may include a coating configured to reduce reflection of light having wavelengths within VIS wavelengths range and increase reflection of light having wavelengths within LWIR (or MWIR) wavelengths. In some examples, the lenses of the second imaging lens group 710 may include a coating configured to reduce reflection of light having wavelengths within LWIR (or MWIR) wavelengths range and increase reflection of light having wavelengths within VIS wavelength.

[0159]

[0160] As described above, the imaging system 600 may be configured to capture images (e.g., two images) of a scene using light having wavelengths within two or more different wavelength ranges (e.g., two different wavelength ranges) via partially overlapping optical paths and using image sensors (e.g., two image sensors) having different spectral responses. In some implementations, the two different wavelength ranges can be VIS and LWIR wavelength ranges or VIS and MWIR wavelength ranges). The two or more images may be digitized and then be fused to generate composite or fused images comprising at least one feature that appears on the two images with different intensities (visibilities or contrasts), and / or at least one feature that appear on the second image (e.g., mid-wave IR or long-wave R image) but not on the first image (e.g., the VIS image). In some embodiments, two images formed on the two image sensors 611 , 612 of the imaging system 600 by the optical subsystem 602 may be aligned such that geometrical relations between the corresponding features on the first and second images are substantially identical allowing the generation of the composite image with no or very small amount of geometrical adjustment (e.g., translating and / or transforming a coordinate of a geometrical feature).

[0161] In some embodiments, the control and processing system 622 may use the first and second image sensors 614, 616, to generate first and second digital images corresponding to the first and second images projected on the first and second image sensors 611 , 612 and fuse the first and second digital images to generate the composite image. In some such embodiments, the control and processing system may process one or both the first and second digital images before combining them as the composite image. In some examples, the control and processing system may process one or both the first and second digital images by adjusting one or more characteristics such as the brightness, contrast, hue, saturation sharpness, color balance, noise, and the like, e.g., to provide a composite image comprising a balanced combination of features that can appear on the first and second digital images with different characteristics. For example, the brightness of a region of the captured scene that appears significantly brighter on the second image compared to the brightest feature of the first digital image may be reduced prior to combining.

[0160]

[0162] In some embodiments, the optical imaging subsystem 702 can be a wide-angle imaging system configured to capture light within a large field of view (FOV), e.g., larger than 60 degrees, larger than 80 degrees, or larger than 100 degrees. In some embodiments, the optical imaging subsystem can be an ultra-wide-angle imaging system configured to capture light within a large field of view (FOV), e.g., larger than 120 degrees, larger than 150 degrees, or larger than 180 degrees. In some embodiments, at least of the lenes (e.g., the first lens after the entrance aperture 624), can be a fisheye lens or a wide-angle lens.

[0161]

[0163] FIG. 8 schematically illustrates a first VIS image 802, a second thermal image 804, and a composite image 806 generated by an example implementation of the imaging system 600 mounted on a vehicle from a scene in front of the vehicle using the VIS and LWIR image sensors of the imaging system shown in FIG. 6 and an imaging generated by fusing the VIS and LWIR images.

[0162]

[0164] In the example shown, the captures scene (or the portion of the scene captured by the imaging system 600), includes an oncoming vehicle and a pedestrian. In some embodiments, a geometrical feature on the first image 802 can be substantially equal to the corresponding geometrical feature on the second image 804. In some embodiments, a geometrical relation (e.g., a ratio) between two geometrical features on the first image 802 can be substantially equal to that of the corresponding geometrical features on the second image 804. In some cases, the first and second images 802, 804, may have substantially the same magnifications, e.g., with respect to the captured scenes. In some embodiments, the coordinates of a feature of the captured scene on the first image 802, e.g., with respect to a first frame of the first image 802 can be substantially equal to the coordinates of the same feature on the second image 804, e.g., with respect to a second frame of the second image 804. In some such embodiments, aligning / aligning the first and second frames may automatically align the first and second images 802, 804, such that different features of the captured scene in the first and second images 802, 804, overlap on the composite image.

[0163]

[0165] In some cases, objects having higher temperatures may appear brighter and / or with more contrast on the second image 804 and the objects that are colder may appear brighter (or with higher contrast) on the first image 802. For example, the image of the oncoming vehicle image 811a, the camera 813a, and the lidar systems 815a, on the first image 802 can be more visible than the image of the oncoming vehicle 811 b, the camera 813b, and the lidar systems 815b, on the second image 804. As another example, the pedestrian image 810b on the second image 804 can be more visible than the pedestrian image 810a on the first image 802. In some cases, an object in the scene may generate both visible light and thermal radiation and thereby appear with high brightness on both the first and second images 802, 084. For example, the image of the headlight 806a on the first image 802, and the image of the headlight 806b on the second image 804, may both have high brightness.

[0164]

[0166] In some embodiments, the imaging system 600 may process the first and second images 802, 804, to adjust the brightness of the different features prior to generation of the composite image 806 such that they appear with a balanced brightness on the composite image 806. For example, the brightness of the pedestrian image 810b on the second image 804 may be reduced based at least in part of the brightness of the oncoming vehicle image 811 a such that the image 811 c and 810c of the vehicle and pedestrian on the composite image provides a balanced image of the scene that can be used by a user, driver, or a computing system to take an action, generate a command, or a warning to avoid collision with the oncoming vehicle of the pedestrian.

[0165]

[0167] In some embodiments, a processor of the control and processing system 622 may generate a composite image of a scene using first and second image signals 616, 614 generated by the first and second image sensors 611 , 612, in response to receiving VIS and LWIR images or generally two images comprising two distinct wavelength ranges by registering and fusing the first and second images. In some cases, registering may include aligning the first and second images to ensure that corresponding points in the scene match up and fusing may include combining the aligned first and second images to retain the most relevant information from both first and second images captured using different modalities (e.g., VIS and IR imaging). In some imaging systems, the registration of two images, projected on two different image sensors, can additionally include geometric transformations to correct for differences in perspective and scale. Advantageously, when the two images are captured by the imaging system 600 using the optical subsystem 602 (or 702), the aligning step may not include any geometric transformation or a geometric transformation that results in significantly smaller change in the transformed image relative to the original image, compared to a case where the two images are captured by two separate imaging systems or via two non-overlapping optical paths. In some embodiments, the processor of the control and processing system 622 may execute a fusion algorithm stored as machine readable instructions in a non- transitory memory of the processing system 622. In various implementations, the fusion algorithm may include pixel averaging, wavelet transform, a deep learning method, high- pass filtering, intensity-hue-saturation (IHS) transform, principal component analysis (PCA), Laplacian pyramid, and the like. These algorithms may be used to the images into intensity, hue, and saturation components, fusing the intensity components, and transforming back to the original color space, reducing the dimensionality of the data, extracting the most significant features from the images and combining them into a single image, decomposing images into different frequency components, fusing the different frequency components, and then reconstructing the image to preserve both spatial and spectral information. In some embodiments, fusing an IR image (e.g., a mid-wave infrared or a long wave infrared) and a visible image of a scene can combine the strengths of both modalities to enhance detail and contrast, and improve target detection. For example, mid-wave Infrared (MWIR) and / or LWIR imaging can capture thermal information, which is useful for detecting heat signatures, while visible imaging provides high-resolution details and color information; combining these images enhances overall detail and contrast, making it easier to identify and analyze objects. MWIR and LWIR (thermal) imaging can detect objects based on their thermal properties, even in low-light or obscured conditions. When fused with visible images, it improves the accuracy of target detection and identification, especially in challenging environments. In some cases, MWIR or LWIR imaging can be less affected by weather conditions like fog, smoke, or darkness as such fusing them with visible imaging ensures reliable performance in various environmental conditions, providing consistent imaging capabilities day and night. The fusion of different imaging modalities can provide a more comprehensive view of the scene, enhancing situational awareness for applications such as surveillance, security, and search and rescue operations. Moreover, a composite image can retain the thermal information from the MWIR / LWIR and the detailed visual information from the visible spectrum, resulting in a richer dataset for further analysis and interpretation.

[0166]

[0168] In some embodiments, a portion or region of a scene may be imaged as a first image region of the first digital image 802 received from the first image sensor 611 (e.g., a VIS image sensor) and a second image region of the second digital image 804 received from the second image sensor 612 (e.g., a LWIR or MWIR image sensor). In some cases, a first normalized brightness of the first image region can be different from a second brightness of the second image region. For example, the second normalized brightness can be greater than the first normalized brightness. In some implementations, the first normalized brightness can be normalized to a maximum brightness of the first digital image and the second normalized brightness can be normalized to a maximum brightness of the second digital image. In some embodiments, the control and processing system 622 (e.g., an electronic processor of the control and processing system 622) can identify the first image region on the first digital image 802 and the second image region on the second digital image 804, and generate the composite image 806 based at least in part on the identified first and second image regions (e.g., characteristic or the first and second image regions). For example, the control and processing system 622 can compare the first and second normalized brightnesses and generate the composite image 806 based at least in part on a result of such comparison. In some embodiments, in response to determining that the second normalized brightness is larger than the first normalized brightness, the control and processing system 622 can enhance the brightness of the corresponding region in the composite image is closer to that of the second normalized brightness. In some embodiments, in response to determining that the second normalized brightness is larger than the first normalized brightness by a threshold amount, the control and processing system 622 may determine that an object or element in the scene (e.g., an object generating thermal radiation) is not sufficiently visible in the first digital image and generate an alert signal indicating the presence of the object. Alternatively, or in addition, in response to determining that the second normalized brightness is larger than the first normalized brightness by a threshold amount, the control and processing system 622 can provide a warning control signal to a control system of an autonomous or semi- autonomous vehicle (e.g., safety controller 202g) of the vehicle 200 to prevent possible collision with the object.

[0167]

[0169] In some embodiments, features, configurations, and systems described above with respect to a long-wave infrared (LWIR) image sensor, formation of an image via a LWIR optical path and processing of the resulting LWIR image to generate a composite image by fusing a visible (VIS) and the LWIR image, e.g., in the context of imaging systems 600 and 700, may be implemented based on a mid-wave infrared (MWIR) image sensor, formation of imaging via a MWIR optical path and processing of the resulting MWIR images to generate a composite image by fusing a VIS and the MWIR image. As such, in some embodiments, an imaging system may be configured to generate a VIS image on a VIS image sensor via VIS optical path, generate MWIR image on a MWIR image sensor via a MWIR optical path that partially overlaps with the VIS optical path (e.g., includes the same aperture and objective lens group), and fuse the corresponding digital VIS and MWIR images to generate a composite image capturing features of an imaged scene imaged based on VIS and MWIR light. In some such embodiments, the MWIR optical path may be formed using optical components comprising materials that are transparent within the MWIR wavelength range and may include surface coated by an antireflection layer configured to reduce reflection of light having wavelengths un the MWIR wavelength range. In some cases, for example, the lenses in the MWIR optical train may include zinc selenide (ZnSe), germanium (Ge), GASIR, zinc sulfide (ZnS), calcium fluoride (CaF2), magnesium fluoride (MgF2), sapphire (AI2O3) and the like. In some embodiments, a MIR image sensor can be a MWIR photodetector array comprising, indium antimonide (InSb) photodiodes, mercury cadmium telluride (MCT) photodetectors, lead salt detectors (PbSe and PbS), quantum cascade detectors (QCDs), and the like.

[0168]

[0170] In some embodiments, the cameras 202a of the vehicle 200 may include the imaging system 600 and the control and processing system 622 can be configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and / or safety controller 202g via a bus to transmit the third image signal 626 to the communication device 202e, autonomous vehicle compute 202f, and / or safety controller 202g via the bus to provide the composite image or information associated with or extracted from the composite image to a user, user interface, or system that may use the composite image and / or the corresponding information, e.g., to trigger an action. In some embodiments, the control and processing system 622 of the imaging system 600 may transmit the third image signal 626 a perception system of the vehicle (e.g., the perception system 402 in the autonomous vehicle compute 400) and the perception system may use the third image signal 626 and / or the corresponding composite digital image (e.g., VIS / thermal digital image) to detect and / or identify a physical object in an environment and classify the physical object (e.g., as a bicycles, a vehicle, a traffic sign, a pedestrian, and / or the like).

[0169]

[0171] In various implementations, the component of the optical imaging subsystem 602 can be contained and integrated within a single enclosure. In some cases, the control and processing system 622 and the optical imaging subsystem 602, and the image sensors 611 , 612, can be contained and integrated within a single enclosure. In some cases, the optical imaging subsystem 702, and the image sensors 611 , 612, can be contained and integrated within a single enclosure. In some cases, the component of the optical imaging subsystem 702 can be contained and integrated within a single enclosure. Example Embodiments

[0170]

[0172] Example embodiments described herein have several features, no single one of which is indispensable or solely responsible for their desirable attributes. A variety of example systems and methods are provided below.

[0171]

[0173] Example 1. An imaging system of a vehicle, comprising: an optical subsystem configured to: receive light from a scene via a single entrance aperture; divide the received light into a first portion and a second portion having different spectral distributions; form a first image of the scene using the first portion, and form a second image of the scene using the second portion, a first image sensor having a first spectral response, configured to generate a first digital image using the first image of the scene; a second image sensor having a second spectral response, configured to generate a second digital image using the second image of the scene; and at least one processor configured to fuse the first digital image with the second digital image to generate a composite digital image, wherein the first image of the scene and the second image of the scene comprise substantially the same portion of the scene; and wherein a second peak sensitivity wavelength of the second spectral response is greater than a first peak sensitivity wavelength of the first spectral response by at least two micrometers.

[0172]

[0174] Example 2. The imaging system of Example 1 , wherein the first portion comprises wavelengths within visible wavelength range and the second portion comprises wavelengths within mid-wave infrared (MWIR) or long-wave infrared (LWIR) wavelength range.

[0173]

[0175] Example 3. The imaging system of any one of Examples 1-2, wherein a spectral distribution of the first portion has a mean value within visible (VIS) wavelength range and a spectral distribution of the second portion has a mean value within MWIR or LWIR wavelength range.

[0176] Example 4. The imaging system of any one of Examples 1-2, wherein the first peak sensitivity wavelength is within visible (VIS) wavelength range and the second peak sensitivity wavelength is within MWIR or LWIR wavelength range.

[0174]

[0177] Example 5. The imaging system of Example 4, wherein the second peak sensitivity wavelength is within LWIR wavelength range.

[0175]

[0178] Example s. The imaging system of Example 4, wherein the second peak sensitivity wavelength is within MWIR wavelength range.

[0176]

[0179] Example 7. The imaging system of any one of Examples 1-7, wherein a first response bandwidth of the first spectral response includes wavelengths from 400 nm to 700 nm.

[0177]

[0180] Example s. The imaging system of Example 5, wherein a second response bandwidth of the second spectral response includes wavelengths from 9 to 12 micrometers.

[0178]

[0181] Example 9. The imaging system of Example 5, wherein a second response bandwidth of the second spectral response includes wavelengths from 3 to 5 micrometers.

[0179]

[0182] Example 10. The imaging system of any one of Examples 1-9, wherein the first image sensor comprises a CMOS sensor.

[0180]

[0183] Example 11. The imaging system of any one of Examples 1 -10, wherein the second image sensor comprises a microbolometer.

[0181]

[0184] Example 12. The imaging system of any one of Examples 1 -11 , wherein the second image sensor comprises an antimony-based photodetector.

[0182]

[0185] Example 13. The imaging system of any one of Examples 1 -12, wherein the optical subsystem is configured to form the first image of the scene via a first optical path extended from an entrance aperture to the first image sensor and to form the second image of the scene via a second optical path extended from the entrance aperture to the second image sensor, wherein the first optical path partially overlaps with the second optical path.

[0183]

[0186] Example 14. The imaging system of Example 13, wherein the first and second optical paths comprise substantially the same field of view (FOV).

[0187] Example 15. The imaging system of Example 13, wherein an F-number of the first optical path is greater than the F-number of the second optical path.

[0184]

[0188] Example 16. The imaging system of Example 13, wherein optical transmission of the first optical path is greater than the optical transmission of the second optical path for light having wavelengths in VIS wavelength range and the optical transmission of the second optical path is greater than the optical transmission of the first optical path for light having wavelengths in one or both MWIR and LWIR wavelength ranges.

[0185]

[0189] Example 17. The imaging system of Example 13, wherein the optical subsystem comprises an objective optical train, a first optical train, a second optical train, and a dichroic beam splitter that receives light from the scene through the entrance aperture and the objective optical train, transmits the first portion to the first optical train, and redirects the second portion to the second optical train.

[0186]

[0190] Example 18. The imaging system of Example 17, wherein the first optical path comprises the first optical train, the second optical path comprises the second optical train, and an overlapping portion of the first and a second optical paths comprises the objective optical train.

[0187]

[0191] Example 19. The imaging system of Example 13, wherein the first optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in VIS wavelength range compared to light having wavelengths in one or both MWIR or LWIR wavelength ranges.

[0188]

[0192] Example 20. The imaging system of Example 13, wherein the second optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in MWIR or LWIR wavelength range compared to light having wavelengths in VIS wavelength range.

[0189]

[0193] Example 21. The imaging system of any one of Examples 1 -20, wherein the imaging system comprises a camera of a navigation system of the vehicle.

[0190]

[0194] Example 22. The imaging system of any one of Examples 1 -21 , wherein to generate the composite digital image, the at least one processor is configured to compare the first digital image and the second digital image.

[0191]

[0195] Example 23. The imaging system of any one of Examples 1-22, wherein a first normalized brightness of at least a first image region of the first digital image is less than a second normalized brightness of a respective second image region of the second digital image.

[0192]

[0196] Example 24. The imaging system of Example 23, wherein each of the first normalized brightness, the second normalized brightness, is normalized to a maximum brightness of the respective digital image.

[0193]

[0197] Example 25. The imaging system of Example 23, wherein the at least one processor is configured to identify the first image region on the first digital image and the second image region on the second digital image and generate the composite image based on the identified first and second image regions.

[0194]

[0198] Example 26. The imaging system of Example of Example 23, wherein the at least one processor is further configured to compare the first and second normalized brightnesses, and generate the composite image based at least in part on the comparison.

[0195]

[0199] Example 27. The imaging system of any one of Examples 1 -26, wherein the at least one processor is further configured to receive the first and second digital images substantially at the same time.

[0196]

[0200] Example 28. The imaging system of any one of Examples 1 -27, wherein a spectral distribution of the second portion has a mean value within MWIR wavelength range, and the at least one processor is further configured to operate the imaging system in sync with a lidar system of the vehicle to receive at least the second digital image in a period when the lidar system does not emit optical beams.

[0197]

[0201] Example 29. The imaging system of any one of Examples 1 -28, wherein the first and second images comprise the same magnification with respect to the scene.

[0198]

[0202] Example 30. The imaging system of any one of Examples 1 -29, wherein the first and second images comprise substantially the same perspective of the scene.

[0199]

[0203] Example 31. The imaging system of any one of Examples 1 -30, wherein imaged features of the scene comprise substantially the same geometrical relation with respect to each other, on the first and second images.

[0200]

[0204] Example 32. A method comprising: by an optical subsystem of an imaging system of a vehicle: receiving light from a scene via a single entrance aperture; dividing the received light into a first portion and a second portion having different spectral distributions; forming a first image on a first image sensor having a first spectral response, using the first portion of the received light forming a second image on a second image sensor having a second spectral response, using the second portion of the received light, wherein the first image and the second image, comprise a same imaged portion of the scene with the same magnification; receiving, by at least one processor of the imaging system, at least a first digital image from the first image sensor and at least a second digital image from the second image sensor; and generating, by the at least one processor, a composite digital image by fusing the first digital image and the second digital image, wherein the first image of the scene and the second image of the scene comprise substantially the same portion of the scene; and wherein a second peak sensitivity wavelength of the second spectral response is greater than a first peak sensitivity wavelength of the first spectral response by at least 2 micrometers.

[0201]

[0205] Example 33. The method of Example 32, wherein the first portion comprises wavelengths within visible wavelength range and the second portion comprises wavelengths within mid-wave infrared (MWIR) or long-wave infrared (LWIR) wavelength range.

[0202]

[0206] Example 34. The method of Example 32, wherein a spectral distribution of the first portion has a mean value within visible (VIS) wavelength range and a spectral distribution of the second portion has a mean value within MWIR or LWIR wavelength range.

[0203]

[0207] Example 35. The method of Example 32, wherein the first peak sensitivity wavelength is within visible (VIS) wavelength range and the second peak sensitivity wavelength is within MWIR or LWIR wavelength range.

[0204]

[0208] Example 36. The method of Example 35, wherein the second peak sensitivity wavelength is within LWIR wavelength range.

[0209] Example 37. The method of Example 35, wherein the second peak sensitivity wavelength is within MWIR wavelength range.

[0205]

[0210] Example 38. The method of Example 32, wherein a first response bandwidth of the first spectral response includes wavelengths from 400 nm to 700 nm.

[0206]

[0211] Example 39. The method of Example 36, wherein a second response bandwidth of the second spectral response includes wavelengths from 9 to 12 micrometers.

[0207]

[0212] Example 40. The method of Example 36, wherein a second response bandwidth of the second spectral response includes wavelengths from 3 to 5 micrometers.

[0208]

[0213] Example 41 . The method of Example 1 , wherein the first image sensor comprises a CMOS sensor.

[0209]

[0214] Example 42. The method of Example 1 , wherein the second image sensor comprises a microbolometer.

[0210]

[0215] Example 43. The method of Example 1 , wherein the second image sensor comprises an antimony-based photodetector.

[0211]

[0216] Example 44. The method of Example 1 , wherein the optical subsystem is configured to form the first image of the scene via a first optical path extended from an entrance aperture to the first image sensor and to form the second image of the scene via a second optical path extended from the entrance aperture to the second image sensor, wherein the first optical path partially overlaps with the second optical path.

[0212]

[0217] Example 45. The method of Example 44, wherein the first and second optical paths comprise substantially the same field of view (FOV).

[0213]

[0218] Example 46. The method of Example 44, wherein an F-number of the first optical path is greater than the F-number of the second optical path.

[0214]

[0219] Example 47. The method of Example 44, wherein optical transmission of the first optical path is greater than the optical transmission of the second optical path for light having wavelengths in VIS wavelength range and the optical transmission of the second optical path is greater than the optical transmission of the first optical path for light having wavelengths in one or both MWIR and LWIR wavelength ranges.

[0215]

[0220] Example 48. The method of Example 44, wherein the optical subsystem comprises an objective optical train, a first optical train, a second optical train, and a dichroic beam splitter that receives light from the scene through the entrance aperture and the objective optical train, transmits the first portion to the first optical train, and redirects the second portion to the second optical train.

[0216]

[0221] Example 49. The method of Example 48, wherein the first optical path comprises the first optical train, the second optical path comprises the second optical train, and an overlapping portion of the first and a second optical paths comprises the objective optical train.

[0217]

[0222] Example 50. The method of Example 44, wherein the first optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in VIS wavelength range compared to light having wavelengths in one or both MWIR or LWIR wavelength ranges.

[0218]

[0223] Example 51. The method of Example 44, wherein the second optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in MWIR or LWIR wavelength range compared to light having wavelengths in VIS wavelength range.

[0219]

[0224] Example 52. The method of Example 32, wherein the imaging system comprises a camera of a navigation system of the vehicle.

[0220]

[0225] Example 53. The method of Example 32, wherein generating the composite digital image, comprises comparing the first digital image and the second digital image.

[0221]

[0226] Example 54. The method of Example 32, wherein a first normalized brightness of at least a first image region of the first digital image is less than a second normalized brightness of a respective second image region of the second digital image.

[0222]

[0227] Example 55. The method of Example 54, wherein each of the first normalized brightness, the second normalized brightness, is normalized to a maximum brightness of the respective digital image.

[0223]

[0228] Example 56. The method of Example 54, further comprising, by the at least one processor of the imaging system, identifying the first image region on the first digital image and the second image region on the second digital image and generating the composite image based on the identified first and second image regions.

[0224]

[0229] Example 57. The method of Example of Example 54, further comprising, by the at least one processor, comparing the first and second normalized brightnesses, and generating the composite image based at least in part on the comparison.

[0230] Example 58. The method of Example 32, wherein receiving, by at least one processor of the imaging system, at least a first digital image from the first image sensor and at least a second digital image from the second image sensor comprises the first and second digital images substantially at the same time.

[0225]

[0231] Example 59. The method of Example 32, wherein a spectral distribution of the second portion has a mean value within MWIR wavelength range, and the method comprises, by the at least one processor of the imaging system, operating the imaging system in sync with a lidar system of the vehicle to receive at least the second digital image in a period when the lidar system does not emit optical beams.

[0226]

[0232] Example 60. The method of Example 32, wherein the first and second images comprise the same magnification with respect to the scene.

[0227]

[0233] Example 61. The method of Example 32, wherein the first and second images comprise substantially the same perspective of the scene.

[0228]

[0234] Example 62. The method of Example 32, wherein imaged features of the scene comprise substantially the same geometrical relation with respect to each other, on the first and second images.

[0229]

[0235] Example 63. An imaging system of a vehicle, comprising: an optical subsystem configured to: receive light from a scene from a single entrance aperture; divide the received light into a first portion and a second portion having different spectral distributions; form a first image of the scene using the first portion, and form a second image of the scene using the second portion, a first image sensor having a first spectral response, configured to generate a first image signal using the first image of the scene; and a second image sensor having a second spectral response, configured to generate a second image signal using the second image of the scene, wherein the first image of the scene and the second image of the scene comprise substantially the same portion of the scene, and wherein a second peak sensitivity wavelength of the second spectral response is greater than a first peak sensitivity wavelength of the first spectral response by at least two micrometers.

[0230]

[0236] Example 64. The imaging system of Example 63, further comprising at least one processor configured to receive the first and second image signals and use the first and second image signals, generate a composite digital image signal by fusing the first and second images, and generate a third image signal comprising the composite.

[0231]

[0237] Example 65. The imaging system of Example 63, wherein the first portion comprises wavelengths within visible wavelength range and the second portion comprises wavelengths within mid-wave infrared (MWIR) or long-wave infrared (LWIR) wavelength range.

[0232]

[0238] Example 66. The imaging system of Example 63, wherein a spectral distribution of the first portion has a mean value within visible (VIS) wavelength range and a spectral distribution of the second portion has a mean value within MWIR or LWIR wavelength range.

[0233]

[0239] Example 67. The imaging system of Example 63, wherein the first peak sensitivity wavelength is within visible (VIS) wavelength range and the second peak sensitivity wavelength is within MWIR or LWIR wavelength range.

[0234]

[0240] Example 68. The imaging system of Example 66, wherein the second peak sensitivity wavelength is within LWIR wavelength range.

[0235]

[0241] Example 69. The imaging system of Example 66, wherein the second peak sensitivity wavelength is within MWIR wavelength range.

[0236]

[0242] Example 70. The imaging system of Example 63, wherein a first response bandwidth of the first spectral response includes wavelengths from 400 nm to 700 nm.

[0237]

[0243] Example 71. The imaging system of Example 67, wherein a second response bandwidth of the second spectral response includes wavelengths from 9 to 12 micrometers.

[0238]

[0244] Example 72. The imaging system of Example 67, wherein a second response bandwidth of the second spectral response includes wavelengths from 3 to 5 micrometers.

[0239]

[0245] Example 73. The imaging system of Example 63, wherein the first image sensor comprises a CMOS sensor.

[0240]

[0246] Example 74. The imaging system of Example 63, wherein the second image sensor comprises a microbolometer.

[0241]

[0247] Example 75. The imaging system of Example 63, wherein the second image sensor comprises an antimony-based photodetector.

[0248] Example 76. The imaging system of Example 63, wherein the optical subsystem is configured to form the first image of the scene via a first optical path extended from an entrance aperture to the first image sensor and to form the second image of the scene via a second optical path extended from the entrance aperture to the second image sensor, wherein the first optical path partially overlaps with the second optical path.

[0242]

[0249] Example 77. The imaging system of Example 76, wherein the first and second optical paths comprise substantially the same field of view (FOV).

[0243]

[0250] Example 78. The imaging system of Example 76, wherein an F-number of the first optical path is greater than the F-number of the second optical path.

[0244]

[0251] Example 79. The imaging system of Example 76, wherein optical transmission of the first optical path is greater than the optical transmission of the second optical path for light having wavelengths in VIS wavelength range and the optical transmission of the second optical path is greater than the optical transmission of the first optical path for light having wavelengths in one or both MWIR and LWIR wavelength ranges.

[0245]

[0252] Example 80. The imaging system of Example 76, wherein the optical subsystem comprises an objective optical train, a first optical train, a second optical train, and a dichroic beam splitter that receives light from the scene through the entrance aperture and the objective optical train, transmits the first portion to the first optical train, and redirects the second portion to the second optical train.

[0246]

[0253] Example 81. The imaging system of Example 80, wherein the first optical path comprises the first optical train, the second optical path comprises the second optical train, and an overlapping portion of the first and a second optical paths comprises the objective optical train.

[0247]

[0254] Example 82. The imaging system of Example 76, wherein the first optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in VIS wavelength range compared to light having wavelengths in one or both MWIR or LWIR wavelength ranges.

[0248]

[0255] Example 83. The imaging system of Example 76, wherein the second optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in MWIR or LWIR wavelength range compared to light having wavelengths in VIS wavelength range.

[0249]

[0256] Example 84. The imaging system of Example 63, wherein the imaging system comprises a camera of a navigation system of the vehicle.

[0257] Example 85. The imaging system of Example 64, wherein to generate the composite digital image, the at least one processor is configured to compare the first image and the second image.

[0250]

[0258] Example 86. The imaging system of Example 85, wherein a first normalized brightness of at least a first image region of the first image is less than a second normalized brightness of a respective second image region of the second image.

[0251]

[0259] Example 87. The imaging system of Example 86, wherein each of the first normalized brightness, the second normalized brightness, is normalized to a maximum brightness of the respective image.

[0252]

[0260] Example 88. The imaging system of Example 86, wherein the at least one processor is configured to identify the first image region on the first image region and the second image region on the second image and generate the composite digital image based on the identified first and second image regions.

[0253]

[0261] Example 89. The imaging system of Example 86, wherein the at least one processor is further configured to compare the first and second normalized brightnesses, and generate the composite image based at least in part on the comparison.

[0254]

[0262] Example 90. The imaging system of Example 64, wherein the at least one processor is further configured to receive the first and second images substantially at the same time.

[0255]

[0263] Example 91. The imaging system of Example 63, wherein a spectral distribution of the second portion has a mean value within MWIR wavelength range, and the at least one processor is further configured to operate the imaging system in sync with a lidar system of the vehicle to receive at least the second image in a period when the lidar system does not emit optical beams.

[0256]

[0264] Example 92. The imaging system of Example 63, wherein the first and second images comprise the same magnification with respect to the scene.

[0257]

[0265] Example 93. The imaging system of Example 63, wherein the first and second images comprise substantially the same perspective of the scene.

[0258]

[0266] Example 94. The imaging system of Example 63, wherein imaged features of the scene comprise substantially the same geometrical relation with respect to each other, on the first and second images.

[0259]

[0267] Example 95. The imaging system of any of the Examples above, wherein the optical systems and the image sensors are contained within a single enclosure. Terminology

[0260]

[0268] In this description numerous specific details are set forth in order to provide a thorough understanding of the present disclosure for the purposes of explanation. It will be apparent, however, that the embodiments described by the present disclosure can be practiced without these specific details. In some instances, well-known structures and devices are illustrated in block diagram form in order to avoid unnecessarily obscuring aspects of the present disclosure.

[0261]

[0269] Specific arrangements or orderings of schematic elements, such as those representing systems, devices, modules, instruction blocks, data elements, and / or the like are illustrated in the drawings for ease of description. However, it will be understood by those skilled in the art that the specific ordering or arrangement of the schematic elements in the drawings is not meant to imply that a particular order or sequence of processing, or separation of processes, is required unless explicitly described as such. Further, the inclusion of a schematic element in a drawing is not meant to imply that such element is required in all embodiments or that the features represented by such element cannot be included in or combined with other elements in some embodiments unless explicitly described as such.

[0262]

[0270] Although the terms first, second, third, and / or the like are used to describe various elements, these elements should not be limited by these terms. The terms first, second, third, and / or the like are used only to distinguish one element from another. For example, a first contact could be termed a second contact and, similarly, a second contact could be termed a first contact without departing from the scope of the described embodiments. The first contact and the second contact are both contacts, but they are not the same contact.

[0263]

[0271] The terminology used in the description of the various described embodiments herein is included for the purpose of describing particular embodiments only and is not intended to be limiting. As used in the description of the various described embodiments and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well and can be used interchangeably with “one or more” or “at least one,” unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “includes,” and / or “comprising,” when used in this description specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0264]

[0272] As used herein, the term “if” is, optionally, construed to mean “when”, “upon”, “in response to determining,” “in response to detecting,” and / or the like, depending on the context. Similarly, the phrase “if it is determined” or “if [a stated condition or event] is detected” is, optionally, construed to mean “upon determining,” “in response to determining,” “upon detecting [the stated condition or event],” “in response to detecting [the stated condition or event],” and / or the like, depending on the context. Also, as used herein, the terms “has”, “have”, “having”, or the like are intended to be open-ended terms. Further, the phrase “based on” is intended to mean “based at least partially on” unless explicitly stated otherwise.

Claims

WHAT IS CLAIMED IS:1 . An imaging system of a vehicle, comprising: an optical subsystem configured to: receive light from a scene from a single entrance aperture, divide the received light into a first portion and a second portion having different spectral distributions; form a first image of the scene using the first portion, and form a second image of the scene using the second portion, a first image sensor having a first spectral response, configured to generate a first digital image using the first image of the scene; a second image sensor having a second spectral response, configured to generate a second digital image using the second image of the scene; and at least one processor configured to fuse the first digital image with the second digital image to generate a composite digital image, wherein the first image of the scene and the second image of the scene comprise substantially the same portion of the scene, and wherein a second peak sensitivity wavelength of the second spectral response is greater than a first peak sensitivity wavelength of the first spectral response by at least two micrometers.

2. The imaging system of claim 1 , wherein the first portion comprises wavelengths within visible wavelength range and the second portion comprises wavelengths within mid-wave infrared (MWIR) or long-wave infrared (LWIR) wavelength range.

3. The imaging system of any one of claims 1 -2, wherein a spectral distribution of the first portion has a mean value within visible (VIS) wavelength range and a spectral distribution of the second portion has a mean value within MWIR or LWIR wavelength range.

4. The imaging system of any one of Claims 1 -3, wherein the first peak sensitivity wavelength is within visible (VIS) wavelength range and the second peak sensitivity wavelength is within MWIR or LWIR wavelength range.

5. The imaging system of claim 4, wherein the second peak sensitivity wavelength is within LWIR wavelength range.

6. The imaging system of claim 4, wherein the second peak sensitivity wavelength is within MWIR wavelength range.

7. The imaging system of claim 1 , wherein a first response bandwidth of the first spectral response includes wavelengths from 400 nm to 700 nm.

8. The imaging system of claim 5, wherein a second response bandwidth of the second spectral response includes wavelengths from 9 to 12 micrometers.

9. The imaging system of claim 5, wherein a second response bandwidth of the second spectral response includes wavelengths from 3 to 5 micrometers.

10. The imaging system of any one of claims 1 -9, wherein the first image sensor comprises a CMOS sensor.11 . The imaging system of any one of claims 1 -10, wherein the second image sensor comprises a microbolometer.

12. The imaging system o any one of claims 1-11 , wherein the second image sensor comprises an antimony-based photodetector.

13. The imaging system of any one of claims 1 -12, wherein the optical subsystem is configured to form the first image of the scene via a first optical path extended from an entrance aperture to the first image sensor and to form the second image of the scene via a second optical path extended from the entrance aperture to the second image sensor, wherein the first optical path partially overlaps with the second optical path.

14. The imaging system of claim 13, wherein the first and second optical paths comprise substantially the same field of view (FOV).

15. The imaging system of claim 13, wherein an F-number of the first optical path is greater than the F-number of the second optical path.

16. The imaging system of claim 13, wherein optical transmission of the first optical path is greater than the optical transmission of the second optical path for light having wavelengths in VIS wavelength range and the optical transmission of the second optical path is greater than the optical transmission of the first optical path for light having wavelengths in one or both MWIR and LWIR wavelength ranges.

17. The imaging system of claim 13, wherein the optical subsystem comprises an objective optical train, a first optical train, a second optical train, and a dichroic beam splitter that receives light from the scene through the entrance aperture and the objective optical train, transmits the first portion to the first optical train, and redirects the second portion to the second optical train.

18. The imaging system of claim 17, wherein the first optical path comprises the first optical train, the second optical path comprises the second optical train, and an overlapping portion of the first and a second optical paths comprises the objective optical train.

19. The imaging system of claim 13, wherein the first optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in VIS wavelength range compared to light having wavelengths in one or both MWIR or LWIR wavelength ranges.

20. The imaging system of claim 13, wherein the second optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in MWIR or LWIR wavelength range compared to light having wavelengths in VIS wavelength range.21 . The imaging system of any one of claims 1 -20, wherein the imaging system comprises a camera of a navigation system of the vehicle.

22. The imaging system of any one of claims 1 -21 , wherein to generate the composite digital image, the at least one processor is configured to compare the first digital image and the second digital image.

23. The imaging system of any one of claims 1 -22, wherein a first normalized brightness of at least a first image region of the first digital image is less than a second normalized brightness of a respective second image region of the second digital image.

24. The imaging system of claim 23, wherein each of the first normalized brightness, the second normalized brightness, is normalized to a maximum brightness of the respective digital image.

25. The imaging system of claim 23, wherein the at least one processor is configured to identify the first image region on the first digital image and the second imageregion on the second digital image and generate the composite image based on the identified first and second image regions.

26. The imaging system of claim 23, wherein the at least one processor is further configured to compare the first and second normalized brightnesses, and generate the composite image based at least in part on the comparison.

27. The imaging system of any one of claims 1-26, wherein the at least one processor is further configured to receive the first and second digital images substantially at the same time.

28. The imaging system of any one of claims 1 -27, wherein a spectral distribution of the second portion has a mean value within MWIR wavelength range, and the at least one processor is further configured to operate the imaging system in sync with a lidar system of the vehicle to receive at least the second digital image in a period when the lidar system does not emit optical beams.

29. The imaging system of any one of claims 1 -28, wherein the first and second images comprise the same magnification with respect to the scene.

30. The imaging system of any one of claims 1 -29, wherein the first and second images comprise substantially the same perspective of the scene.31 . The imaging system of any one of claims 1 -31 , wherein imaged features of the scene comprise substantially the same geometrical relation with respect to each other, on the first and second images.

32. A method comprising: by an optical subsystem of an imaging system of a vehicle: receiving light from a scene via a single entrance aperture; dividing the received light into a first portion and a second portion having different spectral distributions; forming a first image on a first image sensor having a first spectral response using the first portion of the received light forming a second image on a second image sensor having a second spectral response using the second portion of the received light, wherein the first image and the second image, comprise a same imaged portion of the scene with the same magnification;receiving, by at least one processor of the imaging system, at least a first digital image from the first image sensor and at least a second digital image from the second image sensor; and generating, by the at least one processor, a composite digital image by fusing the first digital image and the second digital image; wherein the first image of the scene and the second image of the scene comprise substantially the same portion of the scene; wherein a second peak sensitivity wavelength of the second spectral response is greater than a first peak sensitivity wavelength of the first spectral response by at least 2 micrometers.

33. The method of claim 32, wherein the first portion comprises wavelengths within visible wavelength range and the second portion comprises wavelengths within mid-wave infrared (MWIR) or long-wave infrared (LWIR) wavelength range.

34. The method of any one of claims 32-33, wherein a spectral distribution of the first portion has a mean value within visible (VIS) wavelength range and a spectral distribution of the second portion has a mean value within MWIR or LWIR wavelength range.

35. The method of any one of claims 32-34, wherein the first peak sensitivity wavelength is within visible (VIS) wavelength range and the second peak sensitivity wavelength is within MWIR or LWIR wavelength range.

36. The method of claim 35, wherein the second peak sensitivity wavelength is within LWIR wavelength range.

37. The method of claim 35, wherein the second peak sensitivity wavelength is within MWIR wavelength range.

38. The method of any one of claims 32-37, wherein a first response bandwidth of the first spectral response includes wavelengths from 400 nm to 700 nm.

39. The method of claim 36, wherein a second response bandwidth of the second spectral response includes wavelengths from 9 to 12 micrometers.

40. The method of claim 36, wherein a second response bandwidth of the second spectral response includes wavelengths from 3 to 5 micrometers.41 . The method of any one of claims 32-40, wherein the first image sensor comprises a CMOS sensor.

42. The method of any one of claims 32-41 , wherein the second image sensor comprises a microbolometer.

43. The method of any one of claims 32-42, wherein the second image sensor comprises an antimony-based photodetector.

44. The method of any one of claims 32-43, wherein the optical subsystem is configured to form the first image of the scene via a first optical path extended from an entrance aperture to the first image sensor and to form the second image of the scene via a second optical path extended from the entrance aperture to the second image sensor, wherein the first optical path partially overlaps with the second optical path.

45. The method of claim 44, wherein the first and second optical paths comprise substantially the same field of view (FOV).

46. The method of claim 44, wherein an F-number of the first optical path is greater than the F-number of the second optical path.

47. The method of claim 44, wherein optical transmission of the first optical path is greater than the optical transmission of the second optical path for light having wavelengths in VIS wavelength range and the optical transmission of the second optical path is greater than the optical transmission of the first optical path for light having wavelengths in one or both MWIR and LWIR wavelength ranges.

48. The method of claim 44, wherein the optical subsystem comprises an objective optical train, a first optical train, a second optical train, and a dichroic beam splitter that receives light from the scene through the entrance aperture and the objective optical train, transmits the first portion to the first optical train, and redirects the second portion to the second optical train.

49. The method of claim 48, wherein the first optical path comprises the first optical train, the second optical path comprises the second optical train, and an overlapping portion of the first and a second optical paths comprises the objective optical train.

50. The method of claim 44, wherein the first optical path comprises at least one optical surface coated to provide greater optical transmission for light havingwavelengths in VIS wavelength range compared to light having wavelengths in one or both MWIR or LWIR wavelength ranges.51 . The method of claim 44, wherein the second optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in MWIR or LWIR wavelength range compared to light having wavelengths in VIS wavelength range.

52. The method of any one of claims 32-51 , wherein the imaging system comprises a camera of a navigation system of the vehicle.

53. The method of any one of claims 32-52, wherein generating the composite digital image, comprises comparing the first digital image and the second digital image.

54. The method of any one of claims 32-53, wherein a first normalized brightness of at least a first image region of the first digital image is less than a second normalized brightness of a respective second image region of the second digital image.

55. The method of claim 54, wherein each of the first normalized brightness, the second normalized brightness, is normalized to a maximum brightness of the respective digital image.

56. The method of claim 54, further comprising, by the at least one processor of the imaging system, identifying the first image region on the first digital image and the second image region on the second digital image and generating the composite image based on the identified first and second image regions.

57. The method of claim of claim 54, further comprising, by the at least one processor, comparing the first and second normalized brightnesses, and generating the composite image based at least in part on the comparison.

58. The method of any one of claims 32-57, wherein receiving, by at least one processor of the imaging system, at least a first digital image from the first image sensor and at least a second digital image from the second image sensor comprises the first and second digital images substantially at the same time.

59. The method of any one of claims 32-58, wherein a spectral distribution of the second portion has a mean value within MWIR wavelength range, and the method comprises, by the at least one processor of the imaging system, operating the imagingsystem in sync with a lidar system of the vehicle to receive at least the second digital image in a period when the lidar system does not emit optical beams.

60. The method of any one of claims 32-59, wherein the first and second images comprise the same magnification with respect to the scene.

61. The method of any one of claims 32-60, wherein the first and second images comprise substantially the same perspective of the scene.

62. The method of any one of claims 32-61 , wherein imaged features of the scene comprise substantially the same geometrical relation with respect to each other, on the first and second images.

63. An imaging system of a vehicle, comprising: an optical subsystem configured to: receive light from a scene from a single entrance aperture; divide the received light into a first portion and a second portion having different spectral distributions; form a first image of the scene using the first portion, and form a second image of the scene using the second portion, a first image sensor having a first spectral response, configured to generate a first image signal using the first image of the scene; and a second image sensor having a second spectral response, configured to generate a second image signal using the second image of the scene, wherein the first image of the scene and the second image of the scene comprise substantially the same portion of the scene, and wherein a second peak sensitivity wavelength of the second spectral response is greater than a first peak sensitivity wavelength of the first spectral response by at least two micrometers.

64. The imaging system of claim 63, further comprising at least one processor configured to receive the first and second image signals and use the first and second image signals, generate a composite digital image signal by fusing the first and second images, and generate a third image signal comprising the composite.

65. The imaging system any one of claims 63-64, wherein the first portion comprises wavelengths within visible wavelength range and the second portioncomprises wavelengths within mid-wave infrared (MWIR) or long-wave infrared (LWIR) wavelength range.

66. The imaging system of any one of claims 63-65, wherein a spectral distribution of the first portion has a mean value within visible (VIS) wavelength range and a spectral distribution of the second portion has a mean value within MWIR or LWIR wavelength range.

67. The imaging system of any one of claims 63-66, wherein the first peak sensitivity wavelength is within visible (VIS) wavelength range and the second peak sensitivity wavelength is within MWIR or LWIR wavelength range.

68. The imaging system of any one of claims 63-67, wherein the second peak sensitivity wavelength is within LWIR wavelength range.

69. The imaging system of any one of claims 63-68, wherein the second peak sensitivity wavelength is within MWIR wavelength range.

70. The imaging system of any one of claims 63-69, wherein a first response bandwidth of the first spectral response includes wavelengths from 400 nm to 700 nm.71 . The imaging system of claim 67, wherein a second response bandwidth of the second spectral response includes wavelengths from 9 to 12 micrometers.

72. The imaging system of claim 67, wherein a second response bandwidth of the second spectral response includes wavelengths from 3 to 5 micrometers.

73. The imaging system of any one of claims 63-72, wherein the first image sensor comprises a CMOS sensor.

74. The imaging system of any one of claims 63-73, wherein the second image sensor comprises a microbolometer.

75. The imaging system of any one of claims 63-74, wherein the second image sensor comprises an antimony-based photodetector.

76. The imaging system of any one of claims 63-75, wherein the optical subsystem is configured to form the first image of the scene via a first optical path extended from an entrance aperture to the first image sensor and to form the second image of the scene via a second optical path extended from the entrance aperture to the second image sensor, wherein the first optical path partially overlaps with the second optical path.

77. The imaging system of claim 76, wherein the first and second optical paths comprise substantially the same field of view (FOV).

78. The imaging system of claim 76, wherein an F-number of the first optical path is greater than the F-number of the second optical path.

79. The imaging system of claim 76, wherein optical transmission of the first optical path is greater than the optical transmission of the second optical path for light having wavelengths in VIS wavelength range and the optical transmission of the second optical path is greater than the optical transmission of the first optical path for light having wavelengths in one or both MWIR and LWIR wavelength ranges.

80. The imaging system of claim 76, wherein the optical subsystem comprises an objective optical train, a first optical train, a second optical train, and a dichroic beam splitter that receives light from the scene through the entrance aperture and the objective optical train, transmits the first portion to the first optical train, and redirects the second portion to the second optical train.81 . The imaging system of claim 80, wherein the first optical path comprises the first optical train, the second optical path comprises the second optical train, and an overlapping portion of the first and a second optical paths comprises the objective optical train.

82. The imaging system of claim 76, wherein the first optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in VIS wavelength range compared to light having wavelengths in one or both MWIR or LWIR wavelength ranges.

83. The imaging system of claim 76, wherein the second optical path comprises at least one optical surface coated to provide greater optical transmission for light having wavelengths in MWIR or LWIR wavelength range compared to light having wavelengths in VIS wavelength range.

84. The imaging system of any one of claims 63-83, wherein the imaging system comprises a camera of a navigation system of the vehicle.

85. The imaging system of any one of claims 63-84, wherein to generate the composite digital image, the at least one processor is configured to compare the first image and the second image.

86. The imaging system of claim 85, wherein a first normalized brightness of at least a first image region of the first image is less than a second normalized brightness of a respective second image region of the second image.

87. The imaging system of claim 86, wherein each of the first normalized brightness, the second normalized brightness, is normalized to a maximum brightness of the respective image.

88. The imaging system of claim 86, wherein the at least one processor is configured to identify the first image region on the first image region and the second image region on the second image and generate the composite digital image based on the identified first and second image regions.

89. The imaging system of claim 86, wherein the at least one processor is further configured to compare the first and second normalized brightnesses, and generate the composite image based at least in part on the comparison.

90. The imaging system of any one of claims 63-89, wherein the at least one processor is further configured to receive the first and second images substantially at the same time.

91. The imaging system of any one of claims 63-90, wherein a spectral distribution of the second portion has a mean value within MWIR wavelength range, and the at least one processor is further configured to operate the imaging system in sync with a lidar system of the vehicle to receive at least the second image in a period when the lidar system does not emit optical beams.

92. The imaging system of any one of claims 63-91 , wherein the first and second images comprise the same magnification with respect to the scene.

93. The imaging system of any one of claims 63-92, wherein the first and second images comprise substantially the same perspective of the scene.

94. The imaging system of any one of claims 63-93, wherein imaged features of the scene comprise substantially the same geometrical relation with respect to each other, on the first and second images.

Images