Exposed object detection

Abstract

A system for monitoring a vehicle environment includes a perception system in communication with a vehicle sensor, the perception system configured to receive perception data from the vehicle sensor. The system also includes a scene detection module configured to detect a first object based on the perceptual data and analyze a behavior of the first object to predict whether a revealed scene is occurring or is about to occur, where the occluded object is revealed in the revealed scene. The system also includes a control module configured to perform at least one of controlling the vehicle to respond to the occluded object and presenting information about the occluded object to a user based on detecting the occluded object as an exposed object.

Description

Technical Field

[0001] This subject matter disclosure relates to the field of vehicle perception. More specifically, this subject matter disclosure relates to systems and methods for monitoring the vehicle environment and / or controlling vehicle perception systems based on the detection of exposed objects. Background Technology

[0002] Vehicles are increasingly equipped with sensors and perception devices that enhance vehicle control systems and driver awareness, thereby enabling autonomous control and / or driver support. For example, vehicles may feature autonomous and / or semi-autonomous driving modes, such as fully autonomous control and automated control for specific functions (e.g., parking assistance, automated control during highway driving, brake assist, etc.). Perception systems are designed to detect a wide variety of dynamic situations and objects. Improvements are expected in all aspects of object detection and response to dynamic events. Summary of the Invention

[0003] In one exemplary embodiment, a system for monitoring a vehicle environment includes a perception system in communication with vehicle sensors, the perception system being configured to receive perception data from the vehicle sensors. The system also includes a scene detection module configured to detect a first object based on the perception data and analyze the behavior of the first object to predict whether a revealing scene is occurring or about to occur, wherein an occluded object is revealed in the revealing scene. The system further includes a control module configured to, based on detecting the occluded object as a revealed object, perform at least one of controlling the vehicle to respond to the occluded object and presenting information about the occluded object to a user.

[0004] In addition to one or more features described herein, the perception system is configured to operate in a normal detection mode and a modified detection mode, performing object detection based on a set of normal criteria in the normal detection mode and performing object detection based on a set of modified criteria in the modified detection mode, and the scene detection module is configured to reveal that a scene is occurring or will occur based on prediction, enabling the perception system to switch from the normal detection mode to the modified detection mode.

[0005] In addition to one or more features described herein, the normal detection mode specifies that the perception system performs object detection based on a first number of detection modalities, and the modified detection mode specifies that the perception system performs object detection based on a reduced number of detection modalities, where the reduced number is less than the first number.

[0006] In addition to one or more of the features described herein, the normal detection mode is associated with a first delay, and the modified detection mode is associated with a second delay, which is less than the first delay.

[0007] In addition to one or more features described herein, the scene detection module is configured to predict and reveal whether a scene is happening or about to happen based on manipulations performed by a first object.

[0008] In addition to one or more features described herein, the first object is a vehicle traveling in front of the vehicle, the obstructing object is a third vehicle in front of the vehicle, and the maneuver is an aggressive maneuver performed by the first object.

[0009] In addition to one or more features described in this paper, the scene detection module is configured to predict and reveal whether a scene is happening or about to happen based on the classification of behavior according to a machine learning model.

[0010] In addition to one or more features described in this paper, the first object is the vehicle ahead of the vehicle, and the machine learning model is configured to determine whether the behavior is classified as aggressive maneuvering.

[0011] In addition to one or more features described herein, the perception system is configured to perform object detection based on a normal detection mode and a modified detection mode, the normal detection mode being associated with a first delay and the modified detection mode being associated with a second delay less than the first delay, and the scene detection module is configured to classify a determined behavior as an aggressive maneuver, causing the perception system to operate in the modified detection mode.

[0012] In another exemplary embodiment, a method for monitoring a vehicle environment includes receiving perception data from vehicle sensors of a vehicle's perception system, detecting a first object in the environment surrounding the vehicle based on the perception data, and analyzing the behavior of the first object to predict whether a revealing scene is occurring or about to occur, wherein an occluded object is revealed in the revealing scene. The method further includes: based on the prediction that a revealing scene is occurring or about to occur, and based on detecting the occluded object as a revealed object, performing at least one of controlling the vehicle in response to the occluded object and presenting information about the occluded object to a user.

[0013] In addition to one or more features described herein, the perception system is configured to operate in a normal detection mode and a modified detection mode, performing object detection based on a set of normal criteria in the normal detection mode and performing object detection based on a set of modified criteria in the modified detection mode.

[0014] In addition to one or more features described herein, the method includes enabling the perception system to switch from a normal detection mode to a modified detection mode based on predictions that reveal a scene is occurring or will occur.

[0015] In addition to one or more features described herein, the normal detection mode specifies that the perception system performs object detection based on a first number of detection modalities, and the modified detection mode specifies that the perception system performs object detection based on a reduced number of detection modalities, where the reduced number is less than the first number.

[0016] In addition to one or more features described in this paper, the prediction reveals whether a scenario is happening or will happen based on manipulation performed by the first object.

[0017] In addition to one or more features described in this paper, the prediction reveals whether a scenario is happening or will happen based on classifying behaviors according to a machine learning model.

[0018] In addition to one or more features described in this paper, the first object is the vehicle ahead of the vehicle, and the machine learning model is configured to determine whether the behavior is classified as aggressive maneuvering.

[0019] In yet another exemplary embodiment, the vehicle system includes a perception system in communication with vehicle sensors, configured to receive perception data from the vehicle sensors and perform object detection. The perception system is configured to operate in a normal detection mode and a modified detection mode, performing object detection based on a set of normal criteria in the normal detection mode and performing object detection based on a modified set of criteria in the modified detection mode. The vehicle system also includes a scene detection module configured to detect a first object based on the perception data and analyze the behavior of the first object to predict whether a revealing scene is occurring or about to occur, wherein an occluded object is revealed in the revealing scene. The scene detection module is configured to switch the perception system from the normal detection mode to the modified detection mode based on the prediction that a revealing scene is occurring or about to occur.

[0020] In addition to one or more features described herein, the normal detection mode specifies that the perception system performs object detection based on a first number of detection modalities, and the modified detection mode specifies that the perception system performs object detection based on a reduced number of detection modalities, where the reduced number is less than the first number.

[0021] In addition to one or more features described herein, the scene detection module is configured to predict whether a scene is happening or about to happen based on manipulations performed by a first object.

[0022] In addition to one or more features described in this paper, the scene detection module is configured to predict whether a scene is happening or about to happen based on the classification of behavior according to a machine learning model.

[0023] The above-described features and advantages, as well as other features and advantages, of this disclosure will become apparent when taken in conjunction with the accompanying drawings and the following detailed description. Attached Figure Description

[0024] Other features, advantages, and details appear by way of example only in the following detailed description, which is described in detail with reference to the accompanying drawings, wherein:

[0025] Figure 1 This is a schematic top view of a motor vehicle according to an exemplary embodiment;

[0026] Figure 2 Examples of situations in which the scene might be revealed are depicted;

[0027] Figure 3 An example of a scene being revealed is depicted, in which a target object makes an aggressive maneuver that results in the revelation of another object;

[0028] Figure 4 These are flowcharts depicting various aspects of an exposed object detection method according to exemplary embodiments; and

[0029] Figure 5 A computer system according to an exemplary embodiment is described. Detailed Implementation

[0030] The following description is exemplary in nature only and is not intended to limit this disclosure, its application, or use. It should be understood that throughout the drawings, corresponding reference numerals denote the same or corresponding parts and features.

[0031] According to one or more exemplary embodiments, methods and systems are provided for monitoring and detecting or predicting exposed objects. An "exposed object" is an object that is exposed (i.e., observed in the vehicle's expected path) or predicted to be exposed, such that the vehicle's perception system may not normally detect the object in a timely manner, enabling the vehicle to react to the object (e.g., completely avoid the object or at least reduce damage).

[0032] An embodiment of the system is configured to monitor the vehicle's environment during driving and analyze perception data to predict whether a revealing scenario is likely to occur. A machine learning classifier can be used to predict revealing scenarios to classify objects, object manipulation, and other features of the environment. In one embodiment, based on the predicted revealing scenario, the system causes the perception system to switch from a normal mode to a modified mode. In modified mode, the perception system is configured to detect objects based on a modified set of criteria that allows the perception system to confidently identify objects in a shorter time than when the perception system is in normal mode.

[0033] The embodiments described herein present numerous advantages. For example, the embodiments provide enhanced detection and the ability of the vehicle or driver to resolve dynamic conditions. Furthermore, the embodiments provide improvements to the vehicle perception system, for example, in situations where uncertainty in perception might lead to missed detections.

[0034] Systems in autonomous and manually controlled vehicles, such as adaptive cruise control (ACC), rely on radar and cameras to detect and track objects. However, radar uncertainty can lead to false detections or missed objects. This uncertainty is even more pronounced with visible objects. Therefore, perception systems may take longer to confirm object detection. This delay can result in the vehicle or driver not having enough time to react effectively to visible objects.

[0035] The embodiments described herein address such limitations by providing a robust detection algorithm for exposed objects. This robust detection algorithm leverages a system algorithm to mitigate the effects of radar uncertainty by intelligently inferring the presence of objects based on their exposure to the surrounding environment, utilizing surrounding objects and features, enabling timely detection of exposed objects. The embodiments allow for object detection in revealing scenarios and other challenging scenarios, such as low-visibility conditions or when objects are partially occluded.

[0036] Figure 1 An embodiment of a motor vehicle 10 is shown, which includes a body 12 that at least partially defines a passenger compartment 14. The body 12 also supports various vehicle subsystems, including a propulsion system 16 and other subsystems to support the functions of the propulsion system 16 and other vehicle components, such as a braking subsystem, a suspension system, a steering subsystem, and, if the vehicle is a hybrid electric vehicle, a fuel injection subsystem, an exhaust subsystem, etc.

[0037] Vehicle 10 may be an internal combustion engine vehicle, an electric vehicle (EV), or a hybrid vehicle. In one embodiment, vehicle 10 is a hybrid vehicle including an internal combustion engine system 18 and at least one electric motor 20. Vehicle 10 may be a fully electric vehicle having one or more electric motors.

[0038] The propulsion system 16 includes various other components, such as a drivetrain 22 for applying torque to a front driveshaft 24 connected to the front wheels 26. The propulsion system 16 is not limited thereto. For example, the propulsion system 16 may include components (e.g., a transmission, an electric motor 20, and / or an additional electric motor) for driving a rear driveshaft 28 connected to the rear wheels 30.

[0039] The vehicle 10 also includes various control devices for controlling various aspects of vehicle operation. Such devices include, for example, an accelerator 32, a steering wheel 34, a front brake 36, and a rear brake 38.

[0040] The vehicle also includes a perception system and a vehicle control system, aspects of which may be integrated into or connected to the vehicle 10. The perception system receives perception data (e.g., images) from various sensors, which can represent various types of detection modalities. In one embodiment, the sensors include one or more optical cameras 40 configured to capture images, which may be still images and / or video images. Additional devices or sensors may be included, such as one or more radar components 42 included in the vehicle 10. The perception system is not limited to this and may include other types of sensors, such as lidar, infrared cameras, microphones, etc.

[0041] Control devices and actuators, as well as other components such as monitoring systems, can be controlled via one or more control units, which are collectively represented by vehicle controller 44. Vehicle controller 44 includes processing components for controlling various aspects of vehicle operation, such as propulsion, braking, and steering control, as well as functions such as monitoring and path planning.

[0042] The vehicle controller 44 can be configured to control the vehicle 10 according to various forms of automation control. In embodiments, the vehicle controller 44 is configured for one or more levels of automation, such as Level 1, Level 2, and / or Level 3 automation. Level 1 automation includes driver assistance. Level 2 automation allows the vehicle to control steering and acceleration, where the driver monitors and is ready to take control at any time. In Level 3 automation (conditional automation), the vehicle can monitor the environment and automatically control its operation.

[0043] In one embodiment, the perception system includes a monitoring unit 46 configured to receive data from sensing devices such as an optical camera 40 and a radar assembly 42. The monitoring unit 46 is configured to detect objects and conditions in the environment surrounding the vehicle and provide object detection information to the driver and / or vehicle controller 44. For example, the monitoring unit 46 may present object detection and vehicle trajectory information to the driver via an onboard computer system 50 and / or an infotainment system (e.g., as a graphical and / or text display).

[0044] Monitoring unit 46 includes or is connected to scene detection module 48, which is configured to detect or predict scenes associated with increased uncertainty. Such scenes may include any condition or feature of the environment that increases uncertainty, such as low visibility scenes and revealing scenes. In this embodiment, scene detection module 48 is configured to detect or predict revealing scenes. Revealing scenes can be predicted using machine learning model 47 as further described herein.

[0045] A “revealing scenario” is a situation in which an object (which may have been previously blocked or partially blocked) appears in the expected path of vehicle 10, causing vehicle 10 to need to react to avoid a collision or other unintended consequences. Also in a revealing scenario, the perception system may not typically (i.e., when in normal detection mode) be able to detect the object with certainty (using normal criteria, such as the requirement to use multiple modalities to detect and confirm the presence of the object) before vehicle 10 may need to react.

[0046] As further discussed herein, the scene detection module 48 is configured to predict and reveal whether a scene is occurring or about to occur, and to guide the perception system to switch to a less stringent or less robust detection mode than the normal mode (referred to as the "modified detection mode"). In the modified detection mode, the perception system can analyze the perception data and detect any exposed objects more quickly because the criteria used for object detection are relaxed compared to the normal detection mode.

[0047] In this way, the inherent latency in normal detection modes caused by a prescribed set of criteria (“normal criteria”) can be reduced, allowing for faster detection. For example, in normal detection modes, the perception system needs to analyze optical and radar images (or multiple detection modalities from other sets). In modified detection modes, the perception system may only need to use one modality or fewer modalities (e.g., optical or radar images), thus allowing it to determine whether an object has been detected in a shorter time.

[0048] Vehicle 10, monitoring systems, vehicle controller 44, and other vehicle systems are included in or connected to onboard computer system 50, which includes one or more processing units 52 and user interface 54. User interface 54 may include a touchscreen, a voice recognition system, and / or various buttons for allowing users to interact with features of the vehicle. User interface 54 may be configured to interact with a user or driver via visual communication (e.g., text and / or graphical displays), tactile communication or alarms (e.g., vibration), and / or auditory communication.

[0049] Figure 2 An example of a possible scenario is depicted. At a first time t1 (“current time”), vehicle 10 is traveling along road 60, such as a highway. The road includes lanes 62 and 64, and vehicle 10 is currently traveling in lane 62. Another vehicle 66 (“vehicle ahead”) is traveling in lane 62 in front of vehicle 10. Furthermore, a third vehicle 68 is traveling in lane 62 in front of vehicle 66. At the first time t1, the third vehicle 68 is at least partially obscured from the view of vehicle 10.

[0050] At a second time t2, the vehicle 66 ahead may choose to maneuver into lane 64. The maneuver can be relatively gradual, allowing the vehicle 10's perception system to detect the third vehicle 68 according to normal detection patterns. However, if the maneuver is sudden or aggressive, the perception system may not be able to detect the third vehicle 68 quickly enough to warn the vehicle 10 and / or the user and allow sufficient time for the vehicle 10 to react appropriately and effectively avoid the third vehicle 68.

[0051] Figure 3 An example of a maneuver performed by a detected object is depicted, which is associated with the revealed scene. In this example, the vehicle ahead 66 performs an aggressive lane-changing maneuver (indicated by arrow 70), where the vehicle ahead 66 makes a sudden lane change to avoid or overtake an obstacle vehicle 68. In the implementation, the scene detection module 48 analyzes the dynamic behavior of the vehicle ahead and determines whether the maneuver is classified as an "aggressive maneuver" (e.g., using a classifier or other machine learning model).

[0052] Figure 4 An embodiment of a method 80 for monitoring a vehicle environment is depicted. Method 80 is discussed in conjunction with boxes 81-85. Method 80 is not limited to the number or order of its steps, as some steps represented by boxes 81-85 may be performed in a different order than that described below, or fewer than all steps may be performed.

[0053] Combination Figure 1 Method 80 is discussed in relation to vehicle 10 and scene detection module 48, but is not limited thereto, and can be performed by any suitable processing device or combination of processing devices (e.g., computer system 50, monitoring unit 46, or a combination thereof).

[0054] In addition, refer to Figure 2 and Figure 3 Method 80 is discussed in light of the situations and scenarios shown. Method 80 is not limited to this and can be used in any situation where previously occluded or undetected objects are revealed.

[0055] In box 81, during vehicle operation, the perception system monitors the surrounding environment and detects one or more objects in a normal detection mode. The normal detection mode includes recognition methods that define functions, such as feeding image data into a machine learning model (e.g., a deep neural network (DNN)) and recognizing objects in the environment.

[0056] Normal detection modes may require the use of multiple modalities to identify objects. For example, in normal detection mode, the perception system uses both optical images from one or more cameras 40 and radar images from one or more radar components 42 for object identification. Data fusion methods can be combined with other processes (e.g., object classification) to detect objects. For example, monitoring unit 46 receives optical and radar images and detects that a vehicle 66 is traveling ahead.

[0057] Vehicle 10 can be operated manually, autonomously, or semi-autonomously. For example, object detection information can be provided to the autonomous control system or used for semi-autonomous control, such as adaptive cruise control (ACC). Alternatively, information about the environment can be presented to the user (e.g., the driver) on a touchscreen or head-up display.

[0058] At box 82, scene detection module 48 acquires historical data related to the trajectory and behavior of detected objects (i.e., objects detected via normal detection mode). The historical data is used to predict the trajectory of the detected objects. The historical data can be recorded observations of objects (and / or similar types of objects and / or objects in a similar environment). Observations include one or more behaviors associated with a given manipulation or action of the object.

[0059] The behavior of an object can be predicted by comparing the behavior of the detected object with its historical behavior. In this embodiment, a machine learning model is used to predict the trajectory of the detected object.

[0060] For example, the perception system monitors a vehicle 66 ahead and identifies various behaviors, such as changes in speed and direction, and determines which behaviors of the vehicle 66 ahead are aggressive maneuvers or other behaviors associated with the revealed scene. For example, trajectories from previous observations are used for comparison.

[0061] At box 83, scene detection module 48 determines whether the observed behavior indicates a revealed scene. In a revealed scene, the uncertainty associated with the detection modality may be relatively high, which may lead to a corresponding delay. In normal detection mode, the delay can be attributed to increased processing time in order to reduce or minimize false positives.

[0062] Observed behavior can be compared with behaviors stored in a lookup table (or other data structure) to determine whether the observed behavior indicates a revealing scenario. In an embodiment, a machine learning model is used to learn behaviors associated with revealing scenarios, and perceptual data is input into the model to identify behaviors associated with revealing scenarios.

[0063] For example, scene detection module 48 performs a manipulation assessment, where perceived data is fed into a trained machine learning model, such as a classifier. Various criteria can be used to classify the behavior, such as kinematic and dynamic analysis of the vehicle ahead 66 and / or any other observation. For example, semantic cues can be used, such as whether brake lights are on, observed movement by the driver of the vehicle ahead (e.g., which may indicate excitement), road features (e.g., solid or dashed center lines), road signs, etc.

[0064] At box 84, if the detected behavior is classified in a category associated with the revealing scene, the scene detection module 48 determines that the revealing scene is occurring and the occluded object may be revealed.

[0065] In box 85, based on this determination, the perception system is adjusted to change one or more criteria used for object detection. This adjustment enables the perception system to perform affirmative object recognition in a shorter time than the perception system using normal criteria. Although changing the criteria may reduce the confidence of the detection, the perception system can detect exposed objects more quickly.

[0066] Upon entering the modified detection mode, the perception system monitors the environment around the vehicle and performs object detection using a modified standard. If an exposed object is detected (e.g., Figure 2 and Figure 3 The third vehicle (68) can then autonomously or semi-autonomously control vehicle 10 to react to the displayed object. Additionally or alternatively, information about the displayed object is presented to the user or driver.

[0067] In one embodiment, the scene detection module 48, in response to a predicted scene, causes the monitoring unit 46 to switch the perception system from a normal detection mode to a modified detection mode. In the modified detection mode, the criteria used for object detection are modified. The detection criteria are relaxed in the modified detection mode, allowing the monitoring unit 46 to perform object detection in a shorter time.

[0068] In this embodiment, the normal detection mode specifies that the sensing system performs object detection based on a first number of detection modalities. The modified detection mode allows object detection to be performed using a reduced number of detection modalities.

[0069] For example, in normal detection mode, Figure 1 The perception system uses both optical images from one or more cameras 40 and radar images from one or more radar components 42 for object recognition. Data fusion methods can be combined with other processes (e.g., object classification) to detect objects. If the vehicle ahead 66 changes lanes in a normal manner, making a third vehicle 68 visible but giving vehicle 10 time to react, the perception system detects the third vehicle according to a normal detection pattern.

[0070] However, if the revealed scene is predicted, the perception system switches to a modified detection mode and performs object detection. Only optical or radar images are used to detect the third vehicle.

[0071] In one embodiment, the perception system is switched to a modified detection mode by adjusting (e.g., reducing or setting to zero) one or more weights assigned to one or more modalities. For example, when the perception system is in the modified detection mode, the weights associated with optical image data or radar data are set to zero or reduced. Detection can be performed more quickly (in the modified detection mode, the driver and / or vehicle 10 is able to react faster than using the normal detection mode).

[0072] In addition to adjusting the criteria used for object detection, method 80 may also include one or more other actions. For example, presenting the user with information related to the environment, detected objects, and / or the revealed scene. For instance, the driver may be notified that the perception system has switched to a modified detection mode, detected previously occluded objects, and / or identified the revealed scene. Other information may include trajectory and object information, such as in a graphical display.

[0073] Vehicle 10 can be autonomously controlled or controlled to assist the driver. For example, vehicle controller 44 controls vehicle 10 to perform evasive maneuvers, or a driver assistance system is activated.

[0074] Figure 5 Examples of embodiments of a computer system 140 are shown, which can perform various aspects of the embodiments described herein. The computer system 140 includes at least one processing means 142, which generally includes one or more processors for performing various aspects of the image acquisition and analysis methods described herein.

[0075] The components of computer system 140 include processing device 142 (such as one or more processors or processing units), memory 144, and bus 146, which couples various system components, including system memory 144, to processing device 142. System memory 144 may be a non-transitory computer-readable medium and may include various computer system-readable media. Such media may be any available media accessible by processing device 142, and includes volatile and non-volatile media as well as removable and non-removable media.

[0076] For example, system memory 144 includes non-volatile memory 148 such as a hard disk drive, and may also include volatile memory 150 such as random access memory (RAM) and / or cache memory. Computer system 140 may also include other removable / non-removable, volatile / non-volatile computer system storage media.

[0077] System memory 144 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments described herein. For example, system memory 144 stores various program modules that generally perform the functions and / or methods of the embodiments described herein. One or more modules 152 may be included to perform the functions discussed herein. System 140 is not limited thereto, as other modules may be included. As used herein, the term "module" means that it may include application-specific integrated circuits (ASICs), electronic circuitry, processing circuitry of a processor (shared, dedicated, or group) and memory executing one or more software or firmware programs, combinational logic circuitry, and / or other suitable components that provide the described functions.

[0078] The processing device 142 can also communicate with one or more external devices 156, which may be a keyboard, a pointing device, and / or any device that enables the processing device 142 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Communication with various devices may occur via input / output (I / O) interfaces 164 and 165.

[0079] The processing device 142 can also communicate via network adapter 168 with one or more networks 166, such as a local area network (LAN), a general wide area network (WAN), a bus network, and / or a public network (e.g., the Internet). It should be understood that, although not shown, other hardware and / or software components may be used in conjunction with the computer system 140. Examples include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, and data archiving storage systems.

[0080] The terms “a” and “an” do not indicate a limitation of quantity, but rather that at least one of the referenced items is present. Unless the context clearly indicates otherwise, the term “or” means “and / or”. Throughout the specification, the reference to “aspect” means that a particular element described in connection with that aspect (e.g., a feature, structure, step, or characteristic) is included in at least one aspect described herein and may or may not be present in other aspects. Furthermore, it should be understood that the described elements may be combined in any suitable manner in the aspects.

[0081] When an element, such as a layer, film, region, or substrate, is referred to as being “on” another element, it can be directly on the other element, or there may be intermediate elements present. Conversely, when an element is referred to as being “directly” on another element, there are no intermediate elements present.

[0082] Unless otherwise specified herein, all test standards are the most recent standards in effect up to the filing date of this application, or, if priority is claimed, the filing date of the earliest priority application in which a test standard appears.

[0083] Unless otherwise defined, the technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0084] While the foregoing disclosure has been described with reference to exemplary embodiments, those skilled in the art will understand that various changes can be made and elements can be substituted with equivalents without departing from its scope. Furthermore, many modifications can be made to adapt particular situations or materials to the teachings of this disclosure without departing from the basic scope of this disclosure. Therefore, this disclosure is intended to be limited to the specific embodiments disclosed, but will include all embodiments falling within its scope.

Claims

1. A system for monitoring a vehicle environment, comprising: A perception system that communicates with vehicle sensors, the perception system being configured to receive perception data from the vehicle sensors; A scene detection module is configured to detect a first object based on the perception data and analyze the behavior of the first object to predict whether a revealing scene is happening or about to happen, wherein an occluded object is revealed in the revealing scene. and A control module configured to, based on detecting the occluded object as a visible object, perform at least one of controlling the vehicle to respond to the occluded object and presenting information about the occluded object to the user.

2. The system according to claim 1, wherein, The perception system is configured to operate in a normal detection mode and a modified detection mode. In the normal detection mode, object detection is performed based on a set of normal criteria, and in the modified detection mode, object detection is performed based on a set of modified criteria. The scene detection module is configured to reveal whether a scene is occurring or about to occur based on prediction, thereby enabling the perception system to switch from the normal detection mode to the modified detection mode.

3. The system according to claim 2, wherein, The normal detection mode specifies that the perception system performs object detection based on a first number of detection modes, and the modified detection mode specifies that the perception system performs object detection based on a reduced number of detection modes, the reduced number being less than the first number.

4. The system of claim 2, wherein the normal detection mode is associated with a first delay, and the modified detection mode is associated with a second delay, the second delay being less than the first delay.

5. The system of claim 1, wherein the scene detection module is configured to predict whether the revealing scene is occurring or will occur based on the manipulation performed by the first object.

6. The system according to claim 5, wherein, The first object is a vehicle traveling in front of the vehicle, the obstructing object is a third vehicle in front of the vehicle in front, and the maneuver is an aggressive maneuver performed by the first object.

7. The system of claim 1, wherein the scene detection module is configured to predict whether the revealed scene is occurring or will occur based on classifying the behavior according to a machine learning model.

8. The system according to claim 7, wherein, The first object is a vehicle traveling in front of the vehicle, and the machine learning model is configured to determine whether the behavior is classified as aggressive maneuvering.

9. The system according to claim 8, wherein, The perception system is configured to perform object detection based on a normal detection mode and a modified detection mode, the normal detection mode being associated with a first delay and the modified detection mode being associated with a second delay less than the first delay, and the scene detection module is configured to cause the perception system to operate in the modified detection mode based on determining that the behavior is classified as the aggressive manipulation.

10. A method for monitoring vehicle environment, comprising: Receive perception data from vehicle sensors in the vehicle's perception system; Detect a first object in the environment surrounding the vehicle based on the perceived data; Analyze the behavior of the first object to predict whether a revealing scene is happening or about to happen, in which an occluded object is revealed; and Based on the prediction that the revealed scene is happening or will happen, and based on detecting the occluded object as a revealed object, the vehicle is controlled to respond to the occluded object and to present information about the occluded object to the user at least one of the following:

Images