Systems, methods, and computer program products for recursive hyperspectral imaging

By generating recursively modified spectral absorption data using infrared imaging equipment, the problem of gas leak detection and quantification in imaging systems when the field of view changes is solved, thus achieving accurate detection and quantification of gas leaks.

CN116448703BActive Publication Date: 2026-11-17HONEYWELL INTERNATIONAL INC
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202211593466.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2022-01-14
Filing Date
2022-12-13
Publication Date
2026-11-17
Estimated Expiration
2042-12-13

AI Technical Summary

Technical Problem

Existing imaging systems cannot accurately detect and quantify gas leaks when the field of view of the imaging device changes, especially in handling the effects of gas burning into the background.

Method used

Infrared imaging equipment is used to generate recursively modified spectral absorption data. By iteratively generating spectral absorption data, a modification protocol for different pixel sets is determined using computing equipment, and recursively modified inputs are generated to adapt to the repositioning of the imaging system and environmental changes.

Benefits of technology

It enables accurate detection and quantification of gas leaks when the field of view of the imaging device changes, thus improving the accuracy and reliability of gas leak detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116448703B_ABST
    Figure CN116448703B_ABST
Patent Text Reader

Abstract

This invention provides systems, methods, and computer program products for recursive modification. An exemplary imaging system includes a first infrared (IR) imaging device and a computing device, the first IR imaging device generating first IR image data with a first field of view at a first time, and the computing device being operatively connected to the first IR imaging device. The computing device receives the first IR image data from the first IR imaging device and determines a first pixel set and a second pixel set from a plurality of pixels associated with the first IR image data. The computing device further determines a first modification protocol for the first pixel set and a second modification protocol for the second pixel set. In response, the computing device generates recursive modification input based on the first modification protocol and the second modification protocol.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Exemplary embodiments of this disclosure generally relate to imaging systems, and more specifically, to hyperspectral and / or infrared (IR) imaging for detecting and quantifying gas leaks. Background Technology

[0002] In many environments, such as manufacturing facilities, drilling sites, pipelines, and / or similar environments, gases may be used and stored, transferred, moved, etc. For example, natural gas pipelines can transport natural gas (e.g., methane and / or the like) between two locations. During transport, some gas may be released from such exemplary pipelines, such as due to leaks in the pipeline system (e.g., due to poor sealing at pipe joints, impacts to the pipeline, etc.). To identify leaks and / or quantify the amount of gas emitted from such leaks (e.g., fugitive emissions), a hyperspectral camera can be used. The inventors have identified many deficiencies in the prior art in the art, and remedies for these deficiencies are the subject of the embodiments described herein. Summary of the Invention

[0003] As mentioned above, many industries and environments rely on or otherwise utilize gases in performing various operations related to these industries. For example, the natural gas industry extracts, transports, and processes natural gas (e.g., methane and / or similar substances) for subsequent use in generating heat, producing electricity, fueling vehicles, and so on. Such emissions of gases into the external environment, such as due to leaks in one or more systems, can result in significant product loss costs and substantial fines from, for example, government regulatory agencies. Furthermore, leaks of gases such as methane can pose hazardous conditions to workers or otherwise affect workplace safety. Therefore, accurate detection and quantification of gas leaks (e.g., gas plumes) are crucial for maximizing profits while preventing hazardous situations.

[0004] In infrared, hyperspectral, and / or thermal imaging applications used to detect or quantify gas leaks, the temperature associated with a specific location within an image (e.g., represented by one or more pixels) can indicate the temperature of any location, object, fluid, gas, etc., present or otherwise associated with that pixel. In other words, the temperature value or data associated with a particular pixel is affected by the temperature at every location along a line extending from the imaging device to the resolution limit of the device. An infrared (IR) imaging device or camera can determine the temperature of a particular pixel, which is influenced, for example, by the temperature of the leaking gas captured by the camera and associated with that pixel, as well as the temperature of the pixel's foreground / background. Thus, the temperature of an exemplary background can be operated to affect the camera's ability to properly quantify the presence or amount of gas at a particular location.

[0005] These detection and quantification operations become more complex when the imaging system moves, translates, tilts, or otherwise alters the field of view of the imaging device utilized by the imaging system. For example, an imaging device (e.g., a hyperspectral and / or IR camera) can be translated and / or tilted, causing changes in the image data generated by that device (e.g., the associated FOV indicating the device). However, in the determination or estimation of the foreground / background associated with a particular pixel, gases (e.g., venting emissions or other emissions) within the device's FOV can conventionally be included. In other words, conventional systems cannot adequately account for the effects of gases that may potentially be present in a particular FOV (e.g., gas burning into the background) in the initial determination, resulting in the inability to properly detect and / or quantify venting emissions with such FOVs, especially when the imaging device's FOV is modified. For example, a conventional system may fail to account for "burning in," where unintended properties associated with the foreground / background of the image are "burned in" into the imaging system's output.

[0006] To address these and other issues, exemplary embodiments of the present disclosure can utilize infrared (IR) imaging devices (such as those implemented in hyperspectral camera embodiments) and modification protocols to generate recursive modification inputs for iteratively generating spectral absorption data. For example, an exemplary imaging system can generate IR image data in a first-time event, analyze the IR image data to determine pixel sets from the pixels associated with the IR image data. Different or interrelated modification protocols are determined for each pixel set, and recursive modification inputs can also be generated based on these modification protocols to iteratively generate spectral absorption data by the imaging system. For example, a first pixel set may indicate the presence of a detected gas or otherwise be associated with the presence of a detected gas, such that the rate at which IR image data is used to replace or otherwise update these pixels differs from the rate at which IR image data is used to replace or otherwise update other pixels (e.g., a second pixel set). In this way, embodiments of the present disclosure can illustrate the repositioning of imaging systems in relation to the evolving environmental or surrounding conditions of a gas leak (e.g., fugitive emissions) to accurately detect and quantify the detected gas observed by these systems (e.g., IR cameras, hyperspectral cameras, etc.).

[0007] Apparatus, methods, systems, devices, and associated computer program products for generating recursive modifications are provided for hyperspectral imaging applications. An exemplary imaging system may include a first infrared (IR) imaging device configured to generate first IR image data with a first field of view of the first IR imaging device at a first time; and a computing device operatively connected to the first IR imaging device. The computing device may be configured to receive the first IR image data from the first IR imaging device, determine a first pixel set from a plurality of pixels associated with the first IR image data, and determine a second pixel set from the plurality of pixels associated with the first IR image data. Each pixel in the first pixel set may include first IR image data indicating the presence of a detected gas, and each pixel in the second pixel set may include first IR image data indicating the absence of a detected gas. The computing device may be configured to further determine a first modification protocol for the first pixel set, determine a second modification protocol for the second pixel set, and generate recursive modification input based on the first modification protocol and the second modification protocol.

[0008] In some implementations, the computing device may be further configured to generate spectral absorption data based on first IR image data at a first time.

[0009] In some implementations, the computing device may be further configured to receive first IR image data of a first field of view of a first IR imaging device at a second time, and generate spectral absorption data based on recursively modified input and the first IR image data at the second time.

[0010] In some implementations, the computing device may be further configured to iteratively generate the recursive modified input in order to iteratively generate spectral absorption data based on the iteratively generated recursive modified input and the iteratively generated first IR image data.

[0011] In some implementations, the first modification protocol may define the rate at which the IR image data for one or more pixels in the first pixel set is replaced, and the second modification protocol may define the rate at which the IR image data for one or more pixels in the second pixel set is replaced.

[0012] In some other implementations, the rate defined by the first modification protocol may be less frequent compared to the rate defined by the second modification protocol.

[0013] In some embodiments, the imaging system may further include a second IR imaging device configured to generate second IR image data of the field of view of the second IR imaging device at a first time, and operatively connected to the computing device. In such embodiments, the computing device may be further configured to generate spectral absorption data based on the first IR image data and the second IR image data at the first time.

[0014] The above description of the invention is provided merely to outline some exemplary embodiments to provide a basic understanding of some aspects of this disclosure. Therefore, it should be understood that the above embodiments are merely examples and should not be construed as limiting the scope or substance of this disclosure in any way. It should be understood that, in addition to those summarized herein, the scope of this disclosure covers many possible embodiments, some of which will be further described below. Attached Figure Description

[0015] Some exemplary embodiments of this disclosure have been described in general terms above; reference will now be made to the accompanying drawings. In some embodiments described herein, the components shown in the drawings may or may not be present. Some embodiments may include fewer (or more) components than those shown in the figures.

[0016] Figure 1 Exemplary imaging systems utilizing emission sources are illustrated according to some exemplary embodiments described herein;

[0017] Figure 2 A schematic block diagram of an exemplary circuit system capable of performing various operations according to some exemplary embodiments described herein is shown;

[0018] Figure 3 An exemplary flowchart for generating recursive modifications according to some exemplary embodiments described herein is shown;

[0019] Figure 4 An exemplary flowchart for iteratively generating spectral absorption data according to some exemplary embodiments described herein is shown; and

[0020] Figure 5 An exemplary flowchart for a specific implementation of multiple imaging devices according to some exemplary embodiments described herein is shown. Detailed Implementation

[0021] Some embodiments of this disclosure will be described more fully below with reference to the accompanying drawings, which illustrate some, but not all, embodiments of this disclosure. In fact, this disclosure may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided to enable this disclosure to meet applicable legal requirements. Throughout this document, similar reference numerals refer to similar elements. As used herein, the computing device of the exemplary imaging system may be referred to as an exemplary “device.” However, elements of the device described herein are equally applicable to methods and computer program products protected by the claims. Therefore, the use of any such term should not be construed as limiting the spirit and scope of the embodiments of this disclosure.

[0022] Definition of terminology

[0023] As used herein, the terms “data,” “content,” “information,” “electronic information,” “signal,” “command,” and similar terms are used interchangeably to refer to data capable of being transmitted, received, and / or stored according to embodiments of the present invention. Therefore, the use of any such terms should not be construed as limiting the substance or scope of embodiments of this disclosure. Furthermore, where the first device is described herein as receiving data from the second device, it should be understood that data can be received directly from the second device or indirectly via one or more intermediate computing devices (such as, for example, one or more servers, repeaters, routers, network access points, base stations, hosts, etc., sometimes referred to herein as a “network”). Similarly, where the first device is described herein as sending data to the second device, it should be understood that data can be sent directly to the second device or indirectly via one or more intermediate computing devices (such as, for example, one or more servers, remote servers, cloud-based servers (e.g., cloud tools), repeaters, routers, network access points, base stations, hosts, etc.).

[0024] As used herein, the term “comprising” means including but not limited to, and should be interpreted in the manner commonly used in the patent context. It should be understood that the use of broad terms such as “comprising,” “including,” and “having” provides support for narrower terms such as “consisting of,” “substantially composed of,” and “substantially constituted by.”

[0025] As used herein, phrases such as “in one embodiment,” “according to one embodiment,” and “in some embodiments” generally refer to a specific feature, structure, or characteristic that follows the phrase and may be included in at least one embodiment of this disclosure. Therefore, such specific feature, structure, or characteristic may be included in more than one embodiment of this disclosure, such that these phrases do not necessarily refer to the same embodiment.

[0026] As used herein, the term “exemplary” means “used as an example, instance, or illustration.” Any specific implementation described herein as an “example” is not necessarily to be construed as preferred or advantageous over other specific implementations.

[0027] As used herein, the terms "first IR imaging device" or "first IR imager" refer to one or more devices capable of generating first IR image data. Exemplary first IR imaging devices may include thermal imaging cameras, IR imagers, IR cameras, thermal imaging cameras, and / or similar devices capable of generating IR image data indicating the field of view (FOV) of the first IR imaging device. In other words, a first IR imaging device may include any device, apparatus, system, etc., capable of detecting infrared energy / radiation and converting that infrared energy / radiation into a corresponding electronic signal (e.g., first IR image data). As a non-limiting example, a first IR imaging device may include an IR camera configured to capture IR energy emitted by fugitive emissions from exemplary emission sources described below, located within a first FOV associated with the first IR imaging device. The first IR imaging device may also be associated with a first filter defining a first bandpass frequency (e.g., a device that allows frequencies within a certain range to pass and attenuates frequencies outside that range). As described below, the first filter can be configured to deliver IR radiation to a first IR imaging device having a frequency associated with a fugitive emission (e.g., a detection gas) (e.g., methane, etc.) that the imaging device is designed to monitor.

[0028] As used herein, the term "second IR imaging device" or "second IR imager" refers to one or more devices capable of generating second IR image data. Exemplary second IR imaging devices may also include thermal imaging cameras, IR imagers, IR cameras, thermal imaging cameras, and / or similar devices capable of generating IR image data indicating the field of view (FOV) of the second IR imaging device. In other words, a second IR imaging device may include any device, apparatus, system, etc., capable of detecting infrared energy / radiation and converting said infrared energy / radiation into corresponding electronic signals (e.g., second IR image data). As a non-limiting example, a second IR imaging device may also include an IR camera configured to capture IR energy emitted by fugitive emissions from an exemplary emission source described below, located within a second FOV associated with the second IR imaging device. The second IR imaging device may also be associated with a second filter (e.g., a device that allows frequencies within a certain range to pass and attenuates frequencies outside that range) defining a second bandpass frequency. As described below, the second filter may be configured to deliver IR radiation to a second IR imaging device having a frequency associated with the fugitive emissions (e.g., detection gases) (e.g., methane, etc.) that the imaging device is designed to monitor, and the second filter may be further configured to be used at the same frequency as the first filter. Although this disclosure refers to two (2) IR imaging devices, based on the intended application of the imaging system, the disclosure contemplates that the imaging system may include any number of IR imaging devices.

[0029] As used herein, the term "computing device" means any user equipment, controller, object, or system capable of physically or network-communicating with the first IR imaging device and / or the second IR imaging device as described below. For example, a computing device may refer to a wireless electronic device configured to perform various IR image-related operations in response to first IR image data and / or second IR image data generated by the first IR imaging device and the second IR imaging device, respectively. The computing device may be configured to communicate with the first IR imaging device and / or the second IR imaging device via Bluetooth, NFC, Wi-Fi, 3G, 4G, 5G protocols, etc. In some cases, the computing device may include the first IR imaging device and / or the second IR imaging device (e.g., an integrated configuration).

[0030] As used herein, the terms “escape emission,” “gas leak,” “gas plume,” “detection gas,” and / or “gas leak plume” can refer to a collection of gas atoms or particles, wherein the individual atoms or particles are widely spaced. Such gases may leak or otherwise be emitted from a containment vessel (e.g., a natural gas pipeline, etc.) or an emission source, and may form a plume or column. The plume may be a vertical body of a first fluid (e.g., the leaking gas) that moves relative to or through another second fluid (e.g., ambient air). As will be apparent from this disclosure, the intensity of a gas can dissipate with increasing distance between the leaking gas and the leak source. For example, a gas leak from a pipeline containing methane gas can result in a gas plume of methane gas emitted from the pipeline, such that the intensity (e.g., concentration) of the methane gas decreases with increasing distance between the methane gas particles and the leak location. Although described herein with reference to exemplary methane gas applications, this disclosure contemplates that the imaging systems described herein can be configured for use with detection gases of any type, concentration, etc.

[0031] As used herein, the term "computer-readable medium" refers to non-transitory storage hardware, non-transitory storage device, or non-transitory computer system memory that can be accessed by a computing device, microcomputing device, computing system, or module of a computing system to encode computer-executable instructions or software programs thereon. A non-transitory "computer-readable medium" can be accessed by a computing system or module of a computing system to retrieve and / or execute computer-executable instructions or software programs encoded on that medium. Exemplary non-transitory computer-readable media may include, but are not limited to, one or more types of hardware memory, non-transitory tangible media (e.g., one or more magnetic storage disks, one or more optical disks, one or more USB flash drives), computer system memory, or random access memory (such as DRAM, SRAM, EDO RAM), etc.

[0032] After listing a series of necessary definitions throughout this application, exemplary system architectures and exemplary apparatuses for implementing exemplary embodiments and features of this disclosure are described below.

[0033] Device architecture and exemplary apparatus

[0034] refer to Figure 1An exemplary imaging system 100 is shown having a first IR imaging device 102 and a second IR imaging device 104, which are operatively connected to a computing device 200 via a network 106. As defined above, the first IR imaging device 102 may include a device capable of generating first IR image data and may be a thermal imaging camera, IR imager, IR camera, thermal imaging camera, and / or similar device. The first IR imaging device 102 may be associated with a field of view (FOV) 103. FOV 103 may refer to an observable area in which the first IR imaging device 102 can capture images (e.g., generate first IR image data). As described below, in some embodiments, the first IR imaging device 102 may be positioned or oriented such that the emission source 10 is physically located within the FOV 103 of the first IR imaging device 102. In other words, the FOV 103 of the first IR imaging device 102 allows the first IR image data generated by the first IR imaging device 102 (e.g., the IR image captured by the FOV 103) to include IR image data indicating the emission source 10 or otherwise associated with it. This disclosure contemplates that the first IR imaging device 102 can be positioned at any physical location and in any orientation based on the intended application of the system 100, and that the location pointed to by the first IR imaging device 102 can similarly change during operation. Furthermore, this disclosure contemplates that the FOV 103 can vary based on the operating parameters of the first IR imaging device 102.

[0035] In some embodiments, the imaging system 100 may include a second IR imaging device 104, which may include a device capable of generating second IR image data and may be a thermal imaging camera, IR imager, IR camera, thermal imaging camera, and / or similar device. The second IR imaging device 104 may be associated with a field of view (FOV) 105. FOV 105 may refer to an observable area in which the second IR imaging device 104 can capture images (e.g., generate second IR image data). As described below, in some embodiments, the second IR imaging device 104 may be positioned or oriented such that the emission source 10 is physically located within the FOV 105 of the second IR imaging device 104. In other words, the FOV 105 of the second IR imaging device 104 may allow the second IR image data generated by the second IR imaging device 104 (e.g., IR images captured by the FOV 105) to include IR image data indicating the emission source 10 or otherwise associated with it. This disclosure envisions that the second IR imaging device 104 can be positioned at any physical location and in any orientation based on the intended application of system 100. Furthermore, this disclosure envisions that the field of view (FOV) 105 can vary based on the operating parameters of the second IR imaging device 104. As will be apparent from this disclosure, the first FOV 103 and the second FOV 105 can be different based on the different positions of the corresponding first IR imaging device 102 and second IR imaging device 104. In other embodiments, the first FOV 103 and the second FOV 105 can at least partially overlap or coincide.

[0036] In some embodiments as described herein, the first IR imaging device 102 and the second IR imaging device 104 may be formed as an integrated device, or may otherwise be housed together, such as via the housing 108 of the hyperspectral camera. In such embodiments, FOV 103 and FOV 105 may overlap, for example, at least partially as described above. In other embodiments, the first IR imaging device 102 and the second IR imaging device 104 may be positioned separately. In any embodiment, this disclosure contemplates that FOV 103 and / or FOV 105 may be dynamically adjusted (e.g., tilted, translated, pivoted, etc.) during the performance of the operations described herein.

[0037] See below for reference Figures 3 to 5As described in the operation, the imaging system 100 of this disclosure can be located close to the emission source 10 (e.g., from which gas may leak or from any feature, vessel, container, etc.) to detect and quantify fugitive emissions 20 emitted from the emission source 10. This location allows for the existence of a distance between the emission source 10 and the associated fugitive emissions 20. As will be apparent from the relative positions of the first IR imaging device 102 and the second IR imaging device 104, the first IR image data generated by the first IR imaging device 102 and the second IR image data generated by the second IR imaging device 104 can differ due to the different viewing angles (e.g., FOVs 103, 105) of these devices 102, 104. Therefore, the first set of features (e.g., geometric center, centroid, etc.) or features (e.g., corners, edges, contours, etc.) of the fugitive emissions 20 in the first IR image data can differ from the second set of features (e.g., geometric center, centroid, etc.) or features (e.g., corners, edges, contours, etc.) of the same fugitive emissions 20 in the second IR image data. (See below for reference.) Figure 5 The embodiments of this disclosure can utilize multiple sources of IR image data (e.g., first IR imaging device 102, second IR imaging device 104, etc.) to provide a robust solution for generating thermal spectral absorption data. Therefore, any differences between the characteristics of fugitive emissions 20 in the first IR image data and the characteristics of fugitive emissions 20 in the second IR image data can be identified, described, or otherwise considered to ensure accurate generation of spectral absorption data.

[0038] Continue to refer to Figure 1The imaging system 100 may include a computing device 200 connected via a network 106 to a first IR imaging device 102 and / or a second IR imaging device 104. In some cases, the first IR imaging device 102 may include all or part of the computing device 200. In some cases, the second IR imaging device 104 may include all or part of the computing device 200. In other cases, the first IR imaging device 102, the second IR imaging device 104, and the computing device 200 may be formed as a single integrated device. The computing device 200 may include circuitry, a networked processor, etc., configured to perform some or all of the process described herein in a device-based (e.g., IR image-based) process, and may be any suitable processing device and / or network server. In this respect, the computing device 200 may be embodied by any of a variety of devices. For example, computing device 200 may be configured to receive / transmit data (e.g., IR image data, etc.) and may include any terminal from a variety of fixed terminals, such as a server, desktop computer, or kiosk, or any mobile terminal from a variety of mobile terminals, such as a portable digital assistant (PDA), mobile phone, smartphone, laptop computer, tablet computer, or, in some embodiments, a peripheral device connected to one or more fixed or mobile terminals. The exemplary embodiments contemplated herein may have various form factors and designs, but will still include at least Figure 2 The components shown and described in conjunction with the figures. In some embodiments, computing device 200 may include several servers or computing devices performing interconnect and / or distributed functions. Although many arrangements are envisioned herein, computing device 200 is shown and described herein as a single computing device to avoid unnecessarily complicating this disclosure.

[0039] Network 106 may include one or more wired or wireless communication networks, including, for example, wired and / or wireless local area networks (LANs), personal area networks (PANs), metropolitan area networks (MANs), wide area networks (WANs), etc., and any hardware, software, and / or firmware (e.g., network routers, switches, hubs, etc.) used to implement the one or more networks. For example, network 106 may include cellular phones, mobile broadband, Long Term Evolution (LTE), GSM / EDGE, UMTS / HSPA, IEEE 802.11, IEEE 802.16, IEEE 802.20, Wi-Fi, dial-up, and / or WiMAX networks. Furthermore, network 106 may include public networks (such as the Internet), private networks (such as intranets), or combinations thereof, and may utilize various networking protocols currently available or developed in the future, including but not limited to TCP / IP-based networking protocols. In some embodiments, network 106 may refer to a collection of wired connections such that the first IR imaging device 102, the second IR imaging device 104, and / or computing device 200 can be physically connected via one or more network cables, etc.

[0040] like Figure 2 As shown, computing device 200 may include processor 202, memory 204, input / output circuitry 206, and communication circuitry 208. Furthermore, computing device 200 may include image processing circuitry 210 and / or machine learning circuitry 212. Computing device 200 may be configured to perform the following combined Figures 3 to 5 The operation described herein. While functional language is used in some cases to describe components 202 to 212, it should be understood that a particular specific implementation necessarily includes the use of specific hardware. It should also be understood that some components of these components 202 to 212 may include similar or common hardware. For example, both sets of circuit systems may use the same processor 202, memory 204, communication circuit system 208, etc., to perform their associated functions, so that each set of circuit systems does not require duplicate hardware. The use of the term "circuit system" as used herein includes specific hardware configured to perform the functions associated with the corresponding circuit system described herein. As described in the examples above, in some embodiments, various elements or components of the circuit system of computing device 200 may be housed within the first IR imaging device 102 and / or the second IR imaging device 104. In this regard, it should be understood that some of the components described in connection with computing device 200 may be housed in Figure 1 The equipment is located within one or more devices, while other components are housed within another device within these devices, or are composed of... Figure 1 Another device not explicitly shown in the text.

[0041] Of course, while the term "circuit system" should be broadly understood to include hardware, in some implementations, the term "circuit system" may also include software used to construct the hardware. For example, although "circuit system" may include processing circuitry, storage media, network interfaces, input / output devices, etc., other elements of the computing device 200 may provide or supplement the functionality of a particular circuit system.

[0042] In some embodiments, processor 202 (and / or coprocessor or any other processing circuitry system assisting or otherwise associated with the processor) may communicate with memory 204 via a bus for transferring information between components of computing device 200. Memory 204 may be non-transitory and may include, for example, one or more volatile and / or non-volatile memories. In other words, for example, memory may be an electronic storage device (e.g., a non-transitory computer-readable storage medium). Memory 204 may be configured to store information, data, content, applications, instructions, etc., for enabling computing device 200 to perform various functions according to exemplary embodiments of this disclosure.

[0043] Processor 202 can be embodied in a variety of different ways and may include, for example, one or more processing devices configured to execute independently. Alternatively, the processor may include one or more processors configured in series via a bus to enable independent execution of instructions, pipelines, and / or multiple threads. The term "processing circuit system" is understood to include single-core processors, multi-core processors, multiple processors within a computing device, and / or remote or "cloud" processors.

[0044] In an exemplary embodiment, processor 202 may be configured to execute instructions stored in memory 204 or otherwise accessible to processor 202. Alternatively or additionally, processor 202 may be configured to perform hard-coded functions. Thus, whether configured by hardware or by a combination of hardware and software, processor 202 may represent an entity (e.g., physically embodied in the form of a circuit system) capable of performing operations and being configured accordingly according to embodiments of this disclosure. Alternatively, for example, when processor 202 embodies an executor of software instructions, these instructions may specifically configure processor 202 to perform the algorithms and / or operations described herein when executing these instructions.

[0045] The computing device 200 also includes an input / output circuitry 206 that can communicate with the processor 202 to provide output to a user and receive input from the user, user equipment, or another source. In this regard, the input / output circuitry 206 may include a display operable by a mobile application. In some embodiments, the input / output circuitry 206 may also include additional functionality, including a keyboard, mouse, joystick, touchscreen, touch area, softkeys, microphone, speaker, or other input / output mechanisms. The processor 202 and / or the user interface circuitry including the processor 202 may be configured to control one or more functions of the display via computer program instructions (e.g., software and / or firmware) stored in processor-accessible memory (e.g., memory 204, etc.).

[0046] The communication circuit system 208 can be any device, such as a hardware or hardware and software combination embodied device or circuit system, configured to receive and / or transmit data from / to a network and / or to / with the computing device 200. In this regard, the communication circuit system 208 may include, for example, a network interface for enabling communication with wired or wireless communication networks. For example, the communication circuit system 208 may include one or more network interface cards, antennas, buses, switches, routers, modems, and supporting hardware and / or software, or any other device suitable for enabling communication via a network. Additionally or alternatively, the communication interface may include circuitry for interacting with one or more antennas to enable signal transmission via the antennas or to process signals received via the antennas. These signals may be transmitted by the computing device 200 using any of a variety of wireless personal area network (PAN) technologies, such as... Versions 1.0 to 3.0, Bluetooth Low Energy (BLE), infrared wireless (e.g., IrDA), ultra-wideband (UWB), inductive wireless transmission, etc. Furthermore, it should be understood that these signals can be transmitted using Wi-Fi, Near Field Communication (NFC), Global Microwave Access Interoperability (WiMAX), or other proximity-based communication protocols.

[0047] Image processing circuitry system 210 includes hardware components designed to analyze first and / or second IR image data to determine or otherwise identify a set of pixels from a plurality of pixels associated with the first and / or second IR image data. As part of determining an associated modification protocol for a particular pixel, image processing circuitry system 210 may further determine the presence or absence of an exemplary detection gas associated with that particular pixel. Image processing circuitry system 210 may utilize processing circuitry systems such as processor 202 to perform its corresponding operations and may utilize memory 204 to store the collected information. In some cases, image processing circuitry system 210 may also include machine learning circuitry system 212, which includes hardware components designed to analyze IR image data using artificial intelligence, supervised learning, unsupervised learning, etc., to iteratively generate recursively modified inputs to subsequently iteratively generate spectral absorption data. By way of example, the machine learning circuit system 212 may include or utilize an artificial neural network or convolutional neural network trained on at least a plurality of captured IR image data and / or user confirmations associated with a gas leak or plume to improve subsequent operations of the operations described herein. The machine learning circuit system 212 may also utilize a processing circuit system such as processor 202 to perform its corresponding operations, and may utilize memory 204 to store the collected information.

[0048] It should also be understood that, in some embodiments, the image processing circuitry 210 and / or the machine learning circuitry 212 may include a separate processor, a specially configured field-programmable gate array (FPGA), or a special-purpose interface circuit (ASIC) to perform their respective functions. Furthermore, computer program instructions and / or other types of code may be loaded onto a computer, processor, or other programmable circuitry system to produce a machine, such that the computer, processor, or other programmable circuitry system executing the code on that machine forms means for implementing various functions, including those described in conjunction with the components of computing device 200.

[0049] As will be understood from the above and based on this disclosure, embodiments of this disclosure can be configured as apparatuses, systems, methods, etc. Therefore, embodiments may include various means, including entirely hardware or any combination of software and hardware. Furthermore, embodiments may take the form of a computer program product comprising instructions (e.g., computer software stored on a hardware device) stored on at least one non-transitory computer-readable storage medium. Any suitable computer-readable storage medium may be used, including non-transitory hard disks, CD-ROMs, flash memory, optical storage devices, or magnetic storage devices.

[0050] Exemplary detection of recursive modification operations

[0051] Figure 3 A flowchart is shown that includes a series of operations for generating a recursive modification, as illustrated above. Figure 3 The operations shown may be performed, for example, by a device (e.g., computing device 200), with the assistance of the device, and / or under the control of the device. In this regard, the execution of these operations may invoke one or more of the processor 202, memory 204, input / output circuitry 206, communication circuitry 208, image processing circuitry 210, and / or machine learning circuitry 212.

[0052] As shown in operation 305, the apparatus (e.g., computing device 200) includes means such as processor 202, communication circuitry 208, and image processing circuitry 210 for receiving first IR image data associated with the field of view 103 of the first IR imaging device 102 at a first time. The first IR image data generated by the first IR imaging device 102 may include multiple data entries, one or more of which may be associated with a specific pixel representing the FOV 103 of the first IR imaging device 102. Figure 1 As shown, the first IR image data may include one or more data entries associated with emission source 10 to include background that may be present during an emission event (e.g., the presence of fugitive emission 20). In other words, the first IR image data received in operation 305 may refer to IR image data generated by the first IR imaging device 102 in the presence of fugitive emission 20. For example, the first IR image data may indicate the intensity of IR radiation received by the first IR imaging device 102 for each pixel captured for FOV 103 (including those pixels associated with the background of potential emission source 10 and / or fugitive emission 20 (e.g., detection gas 20)). As will be apparent from this disclosure, the first IR image data may occur (e.g., be generated) at a first time in the presence of fugitive emission 20 to determine a set of pixels associated with or otherwise indicating the presence of fugitive emission 20 (e.g., the detection gas). To this end, the imaging system 100 may employ various image processing techniques to determine whether the detected gas (e.g., fugitive emissions 20) is present or absent in the FOV 103 at the first moment of generating the first IR image data.

[0053] In embodiments where a computing device 200 and a first IR imaging device 102 are housed within a common or integrated device (e.g., the computing device 200 includes the first IR imaging device 102), first IR image data may be received by the computing device 200 as part of the normal operation of the first IR imaging device 102 (e.g., internally transmitted, if any). In other embodiments where the computing device 200 and the first IR imaging device 102 are located separately (e.g., connected via network 106), the computing device 200 may be configured to receive first IR image data from the first IR imaging device 102 in response to the generation of first IR image data. In other words, each instance of the first IR image data generation may be transmitted to the computing device 200 after generation. In other embodiments, the computing device 200 may periodically (e.g., according to a defined rate or sampling protocol) request first IR image data from the first IR imaging device 102.

[0054] In some embodiments, the first IR imaging device 102 may be configured to iteratively generate first IR image data of FOV 103 (e.g., at a first time, a second time, ..., at an nth time). This iteratively generated first IR image data may be iteratively received by the computing device 200 in operation 305 and may include an associated timestamp indicating the time when the first IR image data was generated. Furthermore, the first IR imaging device 102 may be moved, translated, tilted, or otherwise modified in its orientation. In doing so, one or more pixels of a plurality of pixels associated with the first IR image data generated at a particular time may change. In such embodiments, the computing device 200 may receive the first IR image data in operation 305 in response to such a change in the orientation or positioning of the first IR imaging device 102. In other words, this disclosure contemplates that the first time for generating the first IR image data for the computing device 200 to receive in operation 305 may refer to the time immediately following a reorientation of the first IR imaging device 102 that results in a change in FOV 103.

[0055] Subsequently, as shown in operations 310 and 315, the apparatus (e.g., computing device 200) includes means such as processor 202, communication circuitry 208, image processing circuitry 210, machine learning circuitry 212, etc., for determining a first set of pixels from a plurality of pixels associated with the first IR image data, and determining a second set of pixels from the plurality of pixels associated with the first IR image data. Each pixel in the first set of pixels may include first IR image data indicating the presence of a detected gas (e.g., fugitive emission 20), while each pixel in the second set of pixels may include first IR image data indicating the absence of a detected gas (e.g., fugitive emission 20). As will be apparent from this disclosure, the first IR image data received by computing device 200 may refer to a hyperspectral image cube, wherein a given x / y position or location in a conventional red / blue / green (RGB) vision camera also includes various IR radiation values ​​(e.g., λ1, λ2, etc.), which indicate the intensity of IR radiation received by the first IR imaging device 102 for each pixel captured for FOV 103. To determine whether a particular pixel indicates the presence or absence of a detection gas as described herein, computing device 200 may utilize one or more radiation transfer models, cosine similarity detectors, etc.

[0056] In some embodiments, in the absence of a detection gas (e.g., fugitive emissions 20), computing device 200 may receive or iteratively receive first IR image data of one or more FOVs 103. In doing so, computing device 200 may be trained, via image processing circuitry 210 and / or machine learning circuitry 212, to determine various attributes (e.g., temperature, etc.) of pixels associated with the first IR image data (e.g., data associated with the background and / or foreground) in the absence of a detection gas. Therefore, computing device 200 may be configured to compare subsequent first IR image data with one or more previously generated first IR image data generated in the absence of a detection gas to determine the presence or absence of a detection gas. For example, first IR image data substantially identical to first IR image data generated in the absence of a detection gas (e.g., one or more attributes or parameters are substantially the same) may indicate the absence of a detection gas, and vice versa. Furthermore, the exemplary cosine similarity detector of this disclosure can be used and operated as a statistical method to correlate continuous and / or categorical predictors (e.g., RGB values ​​and IR radiance values ​​of the first IR image data) with a single outcome variable (e.g., the presence or absence of a detection gas). In other words, the cosine similarity detector can access or otherwise utilize individual instances of IR image data generated at different times by the various IR imaging devices to provide a continuous solution for determining, predicting, and / or evaluating the foreground / background to determine whether the detected gas (e.g., dispersible emission 20) is absent or present.

[0057] Therefore, determining the first pixel set in operation 310 may refer to comparing each of the plurality of pixels associated with the first IR image data at the first time with one or more previous iterations of the operation described below, using a cosine similarity detector, a radiative transfer model, etc. By way of example, computing device 200 may compare the first IR image data of each pixel associated with the FOV 103 at the first time with the presence and / or absence of various previously detected detection gases (e.g., fugitive emissions 20) and associated thresholds (e.g., similarity determination, confidence determination, etc.) to assign a subject pixel to the first pixel set. By way of a particular example, the first IR image data of the subject pixel may include a data entry associated with the IR radiation of the subject pixel at the first (e.g., current) time, and computing device 200 may compare the IR radiation with the IR radiation received for the subject pixel, neighboring pixels, and / or any other pixels within the FOV 103, or otherwise, to determine that the subject pixel, for example, indicates the presence of a detection gas (e.g., fugitive emissions).

[0058] Similarly, determining the second pixel set in operation 315 may refer to comparing each of the plurality of pixels associated with the first IR image data at the first time with one or more previous iterations of these operations using a cosine similarity detector, a radiative transfer model, etc. As an example, computing device 200 may compare the first IR image data of each pixel associated with the FOV 103 at the first time with the presence and / or absence of various previously detected detection gases (e.g., fugitive emissions 20) and associated thresholds (e.g., similarity determination, confidence determination, etc.) to assign a subject pixel to the second pixel set. As a particular example, the first IR image data of the subject pixel may include a data entry associated with the IR radiation of the subject pixel at the first (e.g., current) time, and computing device 200 may compare the IR radiation with the IR radiation received for the subject pixel, neighboring pixels, and / or any other pixels within the FOV 103, or otherwise, to determine that the subject pixel, for example, indicates the absence of a detection gas (e.g., fugitive emissions).

[0059] In some embodiments, the determination of the second pixel set in operation 315 may occur in response to the determination of the first pixel set in operation 310, or otherwise based on the result of operation 310. By way of example, computing device 200 may assign one or more pixels from a plurality of pixels associated with first IR image data, indicating that these pixels indicate the presence of a detected gas, to the first pixel set in operation 310. In such embodiments, computing device 200 may assign pixels not assigned to the first pixel set to the second pixel set. In other words, those pixels not determined in operation 310 to include first IR image data indicating the presence of a detected gas may conversely be determined to include first IR image data indicating the absence of a detected gas, and thus be determined as part of the second pixel set. In any embodiment, computing device 200 may utilize, for example, augmented or supervised learning, where a user associated with imaging system 100 is operable to confirm the presence or absence of a detected gas for specific pixels, in order to improve… Figure 3 The confirmation operation.

[0060] In some embodiments, determining a first set of pixels in operation 310 and / or a second set of pixels in operation 315 may utilize the relationships between the determined pixels. By way of example, if a particular pixel is determined to indicate the presence of a detected gas and is therefore determined to be part of the first set of pixels, pixels that are close to, adjacent to, or otherwise near that particular pixel are also likely to indicate the presence of the detected gas (e.g., fugitive emission 20). By way of additional example, if a particular pixel is surrounded by neighboring pixels (each of which is determined to be part of the first set of pixels (e.g., indicating the presence of a detected gas)), the probability that the particular pixel indicates the presence of a detected gas increases relative to other pixels. Furthermore, this disclosure contemplates that the first set of pixels and / or the second set of pixels may also include various subsets of pixels. As will be apparent from this disclosure, the confidence level of a particular pixel of computing device 200 indicating the presence or absence of a detected gas (e.g., fugitive emission) may vary among pixels. For example, compared to another pixel that also indicates the presence of a detected gas, the computing device 200, based on the first IR image data generated in the first time, has a higher confidence level in indicating the presence of a detected gas for a particular pixel, such that both pixels are assigned to a first pixel set with different confidence values. Therefore, the first pixel set may include various subsets of pixels, each indicating the presence of a detected gas. Although described herein with reference to subsets of pixels within the first pixel set, the invention contemplates that a second pixel set may also include various subsets of pixels, each indicating the absence of a detected gas.

[0061] Subsequently, as shown in operation 320, the apparatus (e.g., computing device 200) includes means such as processor system 202, communication circuitry system 208, image processing circuitry system 210, machine learning circuitry system 212, etc., for determining a first modification protocol for a first set of pixels and a second modification protocol for a second set of pixels. To improve the gas detection and quantization operations of the imaging system 100, the computing device 200 can be operated to determine pixel-specific modification protocols. See below for reference. Figure 4 The computing device 200 is operable to iteratively generate spectral absorption data based on IR image data received iteratively from the first IR imaging device. As mentioned above, conventional imaging systems cannot adequately account for the influence of gases that may potentially be present in a particular FOV (e.g., gas burning into the background) in the initial determination, resulting in the inability to properly detect and / or quantify fugitive emissions (e.g., detect gas 20) with such FOV 103, especially when the FOV 103 of the imaging device is modified. For example, these conventional systems are operable to substantially replace each previous instance of the first IR image data in response to first IR image data generated at a second time (e.g., a time after the first time), or otherwise cannot take into account first IR image data generated at other times.

[0062] In operation 320, the embodiments of this application alternatively illustrate the impact of previous instances of first IR image data generation by determining a modification protocol for each pixel set used in subsequent generation of recursively modified inputs, as described below. In other words, the imaging system 100 of this disclosure can utilize, for example, the generation of spectral absorption data of first IR image data generated not only at the current time but also at one or more previous times (e.g., a first time or other times). Figure 3 The output of the operation serves as input to subsequent operations of the imaging system 100. For example, a first modification protocol may be determined for a first pixel set, and this first modification protocol defines the rate at which IR image data for one or more pixels in the first pixel set is replaced. Similarly, a second modification protocol may be determined for a second pixel set, and this second modification protocol defines the rate at which IR image data for one or more pixels in the second pixel set is replaced. Although the first and second modification protocols are described below with reference to being substantially the same for each pixel in the first pixel set and each pixel in the second pixel set, this disclosure contemplates that each of these modification protocols may also describe a subset of pixels within the first pixel set and / or the second pixel set. In other words, a modification protocol for a particular pixel set may include different replacement rates for different pixels.

[0063] In embodiments of this application, computing device 200 may determine that IR image data indicating the presence of a detected gas (e.g., fugitive emission 20) at a first time is more likely to indicate the presence of the detected gas at a second time or a subsequent time. As will be apparent from the nature of the detected gas (e.g., fugitive emission 20) described herein, the gas emitted by exemplary emission source 10 may occur over a period of time (e.g., before the leak stops). Therefore, imaging system 100 may determine that pixels indicating the presence of a detected gas (e.g., pixels in a first pixel set) are updated, replaced, modified, or otherwise addressed less frequently than pixels indicating the absence of a detected gas (e.g., pixels in a second pixel set). By way of example, pixels in the second pixel set having IR image data indicating the absence of a detected gas (e.g., first IR image data generated at a second time, a third time, ..., the nth time) may be updated with each iteration of the operations described herein. See below for reference. Figure 4As described, computing device 200 can iteratively receive first IR image data from first IR imaging device 102 at various times and iteratively generate spectral absorption data. In such embodiments, computing device 200 is operable to analyze the first IR image data of each pixel in a second pixel set to determine whether a pixel in the second pixel set indicates the presence of a detection gas (e.g., fugitive emission 20), and therefore whether it should be assigned to the first pixel set. Although this document refers to the updating or replacement of the first IR image data of pixels in the second pixel set (in... Figure 3 The operation occurs during each iteration of the process described herein, but this disclosure contemplates that the rate defined by the second modified protocol may include any rate based on the intended application of the imaging system 100.

[0064] However, compared to the rate defined by the second modification protocol, pixels in the first pixel set containing IR image data indicating the presence of detected gas can be updated, replaced, modified, or otherwise addressed at a less frequent rate. (See below for reference.) Figure 4 As described, computing device 200 can iteratively receive first IR image data from first IR imaging device 102 at various times and iteratively generate spectral absorption data. In such embodiments, computing device 200 is operable to analyze the first IR image data of each pixel in a first pixel set to determine whether the pixels in the first pixel set continue to indicate the presence of a detected gas (e.g., fugitive emission 20), and therefore whether they should still be assigned to the first pixel set. However, due to the potential possibility that the first IR image data of the first pixel set continues to indicate the presence of a detected gas, the frequency of analyzing the first IR image data of the first pixel set can be less frequent compared to the frequency of analyzing the first IR image data of the second pixel set. By way of example, while a second modification protocol may define the replacement rate of analyzing the first IR image data associated with the second pixel set at each iteration (e.g., each subsequent generation of the first IR image data), a first modification protocol may define the replacement rate of analyzing the first IR image data associated with the first pixel set every other iteration, every two iterations, ..., and / or every n-1 iterations.

[0065] This disclosure envisions that the rate at which first IR image data associated with pixels in a first pixel set is replaced may vary based on the intended application of the imaging system 100, user or operator input, instructions from the computing device 200, etc. The rate at which IR image data for one or more pixels in the first pixel set is replaced may depend on the rate at which IR image data for one or more pixels in a second pixel set is replaced. For example, if a second modification protocol modifies the rate associated with the second pixel set (e.g., reduces the frequency defined by that rate), the rate associated with the first pixel set may be similarly modified. Furthermore, this disclosure envisions embodiments described herein that illustrate instances where the first modification protocol and / or the second modification protocol are refreshed, zeroed, etc., such as instances where the imaging system 100 determines that each pixel associated with the first IR image data indicates the presence or absence of a detected gas (e.g., fugitive emission 20). For example, as part of reinforcement learning techniques or otherwise, the operator of the imaging system 100 may provide instructions to the computing device to refresh, zero out, etc., the first modification protocol and / or the second modification protocol in order to refresh the first modification protocol and / or the second modification protocol in order to detect the presence of a gas (e.g., emission event or other means) in one or more pixels associated with the pixels associated with the first IR image data.

[0066] As shown in operation 325, the apparatus (e.g., computing device 200) includes means such as processor system 202, communication circuit system 208, image processing circuit system 210, machine learning circuit system 212, etc., for generating recursive modification inputs based on a first modification protocol and a second modification protocol. (See below for more details.) Figure 4 The imaging system 100 can be configured to iteratively generate IR image data (e.g., first IR image data generated at an exemplary second or subsequent time), the IR image data utilizing a rate defined by a first modification protocol and / or a second modification protocol. Therefore, the computing device 200 can generate a recursive modification input, operating as an additional input to the system, based on the first and second modification protocols. For example, the computing device 200 can utilize a Kalman filter that receives the first IR image data as an additional modification input (e.g., Figure 3 The results of the operation are taken together with the input to improve the detection and / or quantification of the detected gas as described herein. Although described herein with reference to an exemplary Kalman filter, this disclosure contemplates that the embodiments described herein may utilize other techniques or mechanisms (e.g., MOG2, GSOC, etc.) for background / foreground considerations.

[0067] In some implementations, as shown in operation 330, the apparatus (e.g., computing device 200) includes means such as processor system 202, communication circuitry system 208, image processing circuitry system 210, machine learning circuitry system 212, etc., for generating spectral absorption data based on first IR image data at a first time. The spectral absorption data (e.g., absorption cube, etc.) can be operated as an output of imaging system 100, for example, as to be examined by an operator of imaging system 100. As described above, the first IR image data received by computing device 200 may refer to a hyperspectral image cube, wherein a given x / y position or location in a conventional red / blue / green (RGB) vision camera also includes various IR radiation values ​​(e.g., λ1, λ2, etc.), which indicate the intensity of IR radiation received by first IR imaging device 102 for each pixel captured for FOV 103. Radiative transfer may refer to energy transfer in the form of electromagnetic radiation, which propagates through the environment and is affected by absorption, emission, and / or scattering. As will be apparent from this disclosure, spectral absorption data can refer to the spectrum of absorption lines, absorption bands, etc., formed by radiation (e.g., light) produced by a heating source (e.g., in an environment with a temperature difference from the source's surroundings). A source producing a continuous spectrum (e.g., fugitive emission 20) passes through a gas at a relatively low temperature, and the associated absorption spectrum indicates a portion of the incident electromagnetic radiation absorbed by the material within a frequency range. Such spectra associated with the spectral absorption data can be used as the total output of the imaging system 100 as described in operation 330.

[0068] Figure 4 A flowchart is shown, illustrating a series of operations for iteratively generating spectral absorption data. As described above, Figure 4 The operations shown may be performed, for example, by a device (e.g., computing device 200), with the assistance of the device, and / or under the control of the device. In this regard, the execution of these operations may invoke one or more of the processor 202, memory 204, input / output circuitry 206, communication circuitry 208, image processing circuitry 210, and / or machine learning circuitry 212.

[0069] As shown in operation 405, the apparatus (e.g., computing device 200) includes means such as processor system 202, communication circuitry system 208, and image processing circuitry system 210 for receiving first IR image data associated with the field of view 103 of the first IR imaging device 102 at a second time from the first infrared (IR) imaging device 102. Similar to operation 305 above, the first IR image data generated by the first IR imaging device 102 may include multiple data entries, one or more of which may be associated with a specific pixel representing the FOV 103 of the second IR imaging device 102 at a second time. In embodiments where the computing device 200 and the first IR imaging device 102 are housed within a common or integrated device (e.g., the computing device 200 includes the first IR imaging device 102), the first IR image data may be received by the computing device 200 (e.g., internally transmitted, if any) as part of the normal operation of the first IR imaging device 102. In other embodiments where the computing device 200 is located separately from the first IR imaging device 102 (e.g., connected via network 106), the computing device 200 may be configured to receive first IR image data from the first IR imaging device 102 in response to the generation of first IR image data at a second time. In other words, each instance of the generated first IR image data may be transmitted to the computing device 200 after generation. In other embodiments, the computing device 200 may periodically (e.g., according to a defined rate or sampling protocol) request the first IR image data from the first IR imaging device 102.

[0070] Subsequently, as shown in operation 410, the apparatus (e.g., computing device 200) includes means such as processor system 202, communication circuitry system 208, image processing circuitry system 210, machine learning circuitry system 212, etc., for generating spectral absorption data based on recursively modified inputs and first IR image data at a second time. As detailed herein, embodiments of this disclosure may be recursive or otherwise sequential, wherein previous instances of generated first IR image data may be used in conjunction with current generation of first IR image data to improve the detection and / or quantification of the detected gas (e.g., fugitive emissions 20). Thus, in operation 410, computing device 200 may receive first IR image data generated at a second time as input, and recursively modified inputs as input, via a Kalman filter, etc., as described above, to generate spectral absorption data. For example, computing device 200 may receive first IR image data generated at a second time, which includes first IR image data associated with the FOV 103 of imaging system 100 at a second time. Based on a first modification protocol and a second modification protocol for recursively modifying the input, computing device 200 can update, replace, modify, or otherwise address the first IR image data generated in a second time on a pixel-by-pixel basis, wherein pixels in the second pixel set can be updated, replaced, modified, or otherwise addressed at a greater frequency than pixels in the first pixel set. In a particular non-limiting example manner, computing device 200 can generate spectral absorption data for each pixel among the pixels associated with the first IR image data; however, the spectral absorption data of some pixels (e.g., pixels in the first pixel set) may be based solely on previous instances of the first IR image data (e.g., the first IR image data generated in a first time for generating the recursively modified input).

[0071] In some implementations, as shown in operation 415, the apparatus (e.g., computing device 200) includes means such as processor system 202, communication circuitry system 208, image processing circuitry system 210, machine learning circuitry system 212, etc., for iteratively generating recursively modified inputs. Computing device 200 can iteratively generate recursively modified inputs to iteratively generate spectral absorption data, such as..., based on the iteratively generated recursively modified inputs and iteratively generated first IR image data. Figure 4 As shown. For example, computing device 200 may receive first IR image data generated at multiple subsequent times (e.g., a third time, a fourth time, ..., and / or the nth time) and iteratively execute... Figures 3 to 4 The operation is designed to provide recursive and continuous mechanisms for improving gas detection and quantification. This disclosure envisions intended applications based on the imaging system 100. Figures 3 to 4 This iterative, recursive operation can be performed at any rate or frequency.

[0072] Figure 5 A flowchart illustrating a series of operations implemented for multiple devices is shown. As described above, Figure 5 The operations shown may be performed, for example, by a device (e.g., computing device 200), with the assistance of the device, and / or under the control of the device. In this regard, the execution of these operations may invoke one or more of the processor 202, memory 204, input / output circuitry 206, communication circuitry 208, image processing circuitry 210, and / or machine learning circuitry 212.

[0073] As shown in operation 505, the apparatus (e.g., computing device 200) includes means such as processor system 202, communication circuitry system 208, and image processing circuitry system 210 for receiving second IR image data associated with the field of view 105 of the second IR imaging device 104 at a first time from the second infrared (IR) imaging device 104. Similar to operation 305, the second IR image data generated by the second IR imaging device 104 may include multiple data entries, one or more of which may be associated with a specific pixel representing the FOV 105 of the second IR imaging device 104. Figure 1 As shown, the second IR image data may include one or more data entries associated with or otherwise indicating the potential emission source 10. For example, the second IR image data may also indicate the intensity of IR radiation received by the second IR imaging device 104 for each pixel captured for the FOV 105. In embodiments where the computing device 200 and the second IR imaging device 104 are housed within a common or integrated device (e.g., the computing device 200 includes the second IR imaging device 104), the second IR image data may be received by the computing device 200 (e.g., internally transmitted, if any) as part of the normal operation of the second IR imaging device 104. In other embodiments where the computing device 200 and the second IR imaging device 104 are located separately (e.g., connected via network 106), the computing device 200 may be configured to receive the second IR image data from the second IR imaging device 104 in response to the generation of the second IR image data. In other words, each instance of the generated second IR image data may be transmitted to the computing device 200 at the time of generation. In other embodiments, computing device 200 may periodically (e.g., according to a defined rate or sampling protocol) request second IR image data from second IR imaging device 104.

[0074] As shown in operation 510, the apparatus (e.g., computing device 200) includes means such as processor system 202, communication circuitry system 208, image processing circuitry system 210, etc., for generating spectral absorption data based on first IR image data and second IR image data at a first time. As will be apparent from the relative positioning between the first IR imaging device 102 and the second IR imaging device 104, one or more pixels associated with the first IR image data can similarly be associated with the second IR image data. To provide additional data sources to improve the generation of spectral absorption data, imaging system 100 may combine the first IR image data with the second IR image data. Thus, computing device 200 is operable to refine the generation of spectral absorption data based on an increased dataset (e.g., a higher confidence output). Although described herein with reference to the second IR imaging device 104 and associated second IR image data, this disclosure contemplates the use of data input from various additional sources, including additional broadband IR image data, visual image data (e.g., VIS and / or RGB data), and / or similar data, to further improve upon the above references. Figures 3 to 5 The aforementioned operations.

[0075] therefore, Figures 3 to 5 A flowchart illustrating the operation of an apparatus, method, and computer program product according to an exemplary embodiment contemplated herein is shown. It should be understood that each flowchart block, and combinations thereof, can be implemented by various means, such as hardware, firmware, processors, circuit systems, and / or other devices associated with the execution of software including one or more computer program instructions. For example, one or more of the operations described above can be implemented by means of executing computer program instructions. In this regard, the computer program instructions can be stored in the memory 204 of computing device 200 and executed by the processor 202 of computing device 200.

[0076] It should be understood that any such computer program instructions can be loaded onto a computer or other programmable device (e.g., hardware) to produce a machine, such that the resulting computer or other programmable device performs the function specified in the flowchart block. These computer program instructions can also be stored in a computer-readable storage medium that instructs the computer or other programmable device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of writing, the execution of which performs the function specified in the flowchart block. The computer program instructions can also be loaded onto a computer or other programmable device to cause a series of operations to be performed on the computer or other programmable device, thereby producing a computer-implemented process, such that the instructions executing on the computer or other programmable device provide operations for performing the function specified in the flowchart block.

[0077] Flowchart frames support combinations of devices for performing specified functions and combinations of operations for performing specified functions. It should be understood that one or more frames in a flowchart, and combinations of frames in a flowchart, can be implemented by a hardware-based dedicated computer system or a combination of dedicated hardware and computer instructions to perform the specified function.

Claims

1. An imaging system, the imaging system comprising: A first IR imaging device, the first IR imaging device being configured to generate first IR image data of a first field of view of the first IR imaging device at a first time; and A computing device operatively connected to the first IR imaging device, wherein the computing device includes an image processing circuit configured to: Receive the first IR image data from the first IR imaging device; A first set of pixels is determined from a plurality of pixels associated with the first IR image data, wherein each pixel in the first set of pixels includes first IR image data indicating the presence of a detected gas; A second set of pixels is determined from the plurality of pixels associated with the first IR image data, wherein each pixel in the second set of pixels includes the first IR image data indicating the absence of the detected gas; A first modification protocol is determined, the first modification protocol defining a first rate at which the first IR image data for one or more pixels in the first pixel set is replaced; A second modification protocol is determined, which defines a second rate at which the first IR image data for one or more pixels in the second pixel set is replaced; as well as Based on the first modification protocol and the second modification protocol, a recursive modification input is generated, wherein the first rate is less than the second rate; as well as Spectral absorption data is generated based on the first IR image data at the first time point.

2. The imaging system of claim 1, wherein the computing device is further configured to: Receive first IR image data from the first field of view of the first IR imaging device at a second time after a first time; and Based on the recursive modification input and the first IR image data received at the second time, spectral absorption data is generated.

3. The imaging system of claim 1, wherein the computing device is further configured to iteratively generate the recursive modification input in order to iteratively generate spectral absorption data based on the iteratively generated recursive modification input and the iteratively generated first IR image data.

4. A computer-implemented method, the computer-implemented method comprising: Receive first IR image data generated by the first field of view of the first IR imaging device at a first time from the first IR imaging device; A first pixel set is determined from a plurality of pixels associated with the first IR image data by means of the image processing circuitry of the computing device, wherein each pixel in the first pixel set includes the first IR image data indicating the presence of the detected gas; A second set of pixels is determined from the plurality of pixels associated with the first IR image data by the image processing circuitry of the computing device, wherein each pixel in the second set of pixels includes the first IR image data indicating the absence of the detected gas; The image processing circuitry of the computing device determines a first modification protocol, which defines a first rate at which the first IR image data for one or more pixels in the first pixel set is replaced. The image processing circuit of the computing device determines a second modification protocol, which defines a second rate at which the first IR image data for one or more pixels in the second pixel set is replaced. as well as The image processing circuit of the computing device generates a recursive modification input based on the first modification protocol and the second modification protocol, wherein the first rate is less than the second rate; as well as The image processing circuit of the computing device generates spectral absorption data based on the first IR image data generated at the first time.

5. The computer-implemented method according to claim 4, further comprising: Receive first IR image data from the first field of view of the first IR imaging device at a second time after a first time. as well as Based on the recursive modification input and the first IR image data received at the second time, spectral absorption data is generated.

6. The computer-implemented method of claim 4, further comprising iteratively generating the recursive modification input to iteratively generate spectral absorption data based on the iteratively generated recursive modification input and the iteratively generated first IR image data.

Citation Information

Patent Citations

  • Background radiance estimation and gas concentration-length quantification method for optical gas imaging camera

    US10234380B1

  • Gas lens filter systems and methods

    US20210310941A1