System and method for misalignment and obstacle information diagnosis for flame detection

Abstract

The invention relates to a system and method for misalignment and obstacle information diagnosis for flame detection. A flame detection system is disclosed. The flame detection system includes one or more sensors for detecting one or more targets within a field of view (FOV). Further, the at least one imaging device is mounted based on a distance between the one or more sensors, the one or more targets, and the FOV. The at least one imaging device is configured to capture one or more real-time images of one or more targets within the FOV. Further, the one or more processors are communicatively coupled to the one or more sensors and the at least one imaging device. The one or more processors are configured to receive the one or more real-time images, compare the one or more real-time images to the at least one reference image, and determine misalignment information, obstacle information, or misalignment information and obstacle information within the FOV based at least on a result of the comparison.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to flame detection systems, and more particularly to systems and methods for diagnosing misalignment and obstacle information within the field of view (FOV) of a flame detector. Background Art

[0002] A flame detection system is a point detector that uses a single-pixel non-imaging detector to collect light from all directions within a field of view (FOV), and then uses various algorithms to identify flames, false alarms, or identify flames in the presence of false alarms. Existing infrared (IR) sensor-based flame detection systems do not provide any information about the FOV, i.e., what the flame detection system is looking at or seeing. For flame detection, some areas within the FOV are more important than others. Some areas require highly accurate flame detection, while in some areas, flame detection is not as critical. This lack of information results in inaccurate installation, misalignment problems, and poor obstacle identification of the flame detection system. In addition, the flame detection system is not easy to install and affects the accuracy of flame detection and the ability to detect flame detection objects.

[0003] The inventors have identified many areas for improvement in the prior art and methods, which are the subject of the embodiments described herein. Through the efforts, wisdom, and innovation, including the development of solutions in the embodiments of the present disclosure, many of these deficiencies, challenges, and problems have been solved, and some examples of these solutions are described in detail herein. Summary of the Invention

[0004] A brief overview of some example embodiments is presented below to provide a basic understanding of some aspects of the present disclosure. This utility model content is not an exhaustive review and is neither intended to identify key elements or important elements nor to describe the scope of such elements. It should also be understood that the scope of the present disclosure covers many possible embodiments in addition to those outlined here, and some of these embodiments will be further described in the detailed embodiments presented later.

[0005] In an example implementation, a system is disclosed. The system includes one or more sensors configured to detect one or more targets within a field of view (FOV) of the one or more sensors. Additionally, at least one imaging device is mounted based on a distance between the one or more sensors, the one or more targets, and the FOV of the one or more sensors. The at least one imaging device is configured to capture one or more real-time images of the one or more targets within the FOV. Further, the system includes one or more processors communicatively coupled to the one or more sensors and the at least one imaging device. The one or more processors are configured to receive the one or more real-time images from the at least one imaging device, compare the one or more real-time images with at least one reference image, and determine misalignment information, obstacle information, or misalignment information and obstacle information within the FOV based at least on the comparison results.

[0006] In some implementations, the one or more sensors are one or more infrared (IR) sensors, flame sensors, or photodiodes. In some implementations, the FOV includes a pixel array. Each pixel of the pixel array is associated with a corresponding one or more regions defined by a user. Additionally, each of the corresponding one or more regions is defined with a criticality level. The criticality level of each corresponding region is one of non-critical, critical, or very critical.

[0007] In some implementations, the one or more processors are configured to segment the one or more real-time images into multiple infrared (IR) channels, and the multiple IR channels are masked using at least one filter with the one or more regions defined by the criticality level.

[0008] In some implementations, the one or more processors are further configured to identify multiple key points. The multiple key points include distinct contrast edges, curve coordinate points, or distinct contrast edges and curve coordinate points on the masked multiple IR channels. In some implementations, the at least one reference image is obtained by comparing at least two consecutive real-time images from the one or more real-time images based at least on one or more coordinates of each image of the one or more real-time images.

[0009] In some implementations, at least one accelerometer is configured to determine a change in one or more coordinates of the one or more sensors within a set time delay specified by a user based at least on the comparison results, thereby determining misalignment information.

[0010] In some embodiments, the non-critical regions correspond to regions where misalignment and / or obstacles are not detected, the very critical regions correspond to regions where misalignment and / or obstacles are detected, and the critical regions correspond to regions where misalignment or obstacles can be detected.

[0011] In some embodiments, to determine misalignment information, multiple IR channels are masked based on the identified key points. In some embodiments, to determine obstacle information, multiple IR channels are masked based on the criticality level. In some embodiments, spatial calibration is performed on one or more sensors and at least one imaging device to maintain the same or a similar FOV. In some embodiments, the one or more processors are further configured to send one or more notifications to a user or a remote server via a communication device, at least based on the determined misalignment information, obstacle information, or misalignment information and obstacle information within the FOV.

[0012] In another exemplary embodiment, a method is disclosed. The method includes the following steps: detecting one or more targets within the field of view (FOV) of the one or more sensors via the one or more sensors; capturing one or more real-time images of the one or more targets within the FOV via at least one imaging device; and receiving the one or more real-time images from the at least one imaging device via the one or more processors. Additionally, the method includes the following steps: comparing the one or more real-time images with at least one reference image via the one or more processors; and determining misalignment information, obstacle information, or misalignment information and obstacle information within the FOV via the one or more processors, at least based on the comparison results.

[0013] In some embodiments, the method includes the following steps: segmenting the one or more real-time images into multiple IR channels via the one or more processors; masking the multiple IR channels with one or more regions having a criticality level via the one or more processors; and identifying multiple key points via the one or more processors. The multiple key points include distinct contrast edges, curve coordinate points, or distinct contrast edges and curve coordinate points on the masked multiple IR channels.

[0014] In some embodiments, the method further includes: determining, via the one or more processors, changes in the one or more coordinates of the one or more sensors within a set time delay specified by the user, at least based on the comparison results of the at least two consecutive real-time images, so as to determine misalignment information.

[0015] The above Summary of the Invention is provided only for the purpose of summarizing some example embodiments to provide a basic understanding of some aspects of the present disclosure. Accordingly, it should be understood that the above embodiments are merely examples and should not be construed as narrowing the scope or essence of the present disclosure in any way. It should be understood that, in addition to those summarized herein, the scope of the present disclosure also encompasses many possible embodiments, some of which will be further described below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Accordingly, certain example embodiments of the present disclosure have been generally described, and will be described below with reference to the accompanying drawings, which are not necessarily drawn to scale, and in which:

[0017] Figure 1 illustrates an example embodiment of a system for determining misalignment information and obstacle information according to an example embodiment of the present disclosure;

[0018] Figure 2A illustrates the synchronization of one or more sensors and at least one imaging device of a system according to an example embodiment of the present disclosure;

[0019] Figure 2B illustrates an adjusted field of view of at least one imaging device of a system according to an example embodiment of the present disclosure;

[0020] Figures 3A to 3B illustrates the masking of one or more real-time images of a system according to an example embodiment of the present disclosure;

[0021] Figure 4A illustrates one or more real-time images segmented into multiple infrared (IR) channels according to an example embodiment of the present disclosure;

[0022] Figure 4B illustrates one or more real-time images with misalignment information determined by the system according to an example embodiment of the present disclosure;

[0023] Figure 5A illustrates one or more real-time images segmented into multiple IR channels according to an example embodiment of the present disclosure;

[0024] Figure 5B illustrates one or more real-time images with obstacle information determined by the system according to an example embodiment of the present disclosure;

[0025] Figure 6 illustrates an exemplary scenario of the installation of a system according to an example embodiment of the present disclosure;

[0026] Figure 7 illustrates an exemplary scenario of determining misalignment information according to an example embodiment of the present disclosure;

[0027] Figure 8 Illustrates an exemplary scenario for determining obstacle information according to an example embodiment of the present disclosure;

[0028] Figure 9 Illustrates a flowchart showing the steps of a method for determining misalignment information and obstacle information according to an example embodiment of the present disclosure;

[0029] Figure 10 Illustrates a flowchart showing the steps of a method for determining misalignment information according to an example embodiment of the present disclosure; and

[0030] Figure 11 Illustrates a flowchart showing the steps of a method for determining obstacle information according to an example embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] Some embodiments will now be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all, embodiments of the disclosure are shown. In fact, the various embodiments 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 so that this disclosure will satisfy applicable legal requirements.

[0032] The components illustrated in the drawings represent components that may or may not be present in the various embodiments of the disclosure described herein, such that an embodiment may include fewer or more components than shown in the figures without departing from the scope of the disclosure. Some components may be omitted from one or more of the figures, or shown in dashed lines to make the components below visible.

[0033] As used herein, the term "comprising" means including but not limited to, and should be interpreted in the manner typically used in the patent context. The use of broader terms such as "including", "containing" and "having" should be understood to provide support for narrower terms such as "consisting of", "consisting essentially of" and "substantially consisting of".

[0034] Phrases such as "in various embodiments", "in one embodiment", "according to one embodiment", "in some embodiments", etc. generally mean that the particular feature, structure or characteristic following the phrase may be included in at least one embodiment of the present disclosure, and may be included in more than one embodiment of the present disclosure (importantly, such phrases do not necessarily refer to the same embodiment).

[0035] As used herein, the term "example" or "exemplary" means "serving as an example, instance, or illustration". Any particular implementation described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other particular implementations.

[0036] If the specification states that a component or feature "may", "can", "might", "should", "would", "preferably", "possibly", "typically", "optionally", "for example", "usually", or "may" (or other such language) be included or have a characteristic, then the particular component or feature need not be included or have that characteristic. Such a component or feature may optionally be included in some embodiments, or it may be excluded.

[0037] The present disclosure provides various embodiments of systems and methods for determining misalignment information and obstacle information within a field of view (FOV) of a sensor. The embodiments may provide high-resolution thermal imaging to enable precise and early identification of flames. The embodiments may provide accurate installation, notification of misalignment and blocked line of sight of the detector to improve the accuracy of flame detection. The embodiments may provide real-time monitoring capabilities to ensure immediate response to any misalignment and obstacles present in the FOV. The embodiments may further provide better installation where the user can see which sensors of the system are detecting and known fire sources, such as flare stacks, that can be captured from the FOV. Additionally, the various embodiments may be integrated into various settings from industrial facilities to fire detection systems, thereby providing a robust and reliable flame detection solution for improved fire safety and reduced risk to life and property.

[0038] Figure 1 An example embodiment of a system 100 for determining misalignment information and obstacle information in accordance with an example embodiment of the present disclosure is illustrated. The system 100 may include one or more sensors 102, at least one imaging device 104, one or more processors 106, at least one digital output 108, at least one analog output 110, and at least one communication output 112.

[0039] One or more sensors 102 may be communicatively coupled to at least one imaging device 104. In some embodiments, one or more sensors 102 may include one or more infrared (IR) sensors, flame sensors, or photodiodes. One or more sensors 102 may detect one or more targets within a field of view (FOV) 114 of one or more sensors 102. Each of one or more sensors 102 and the imaging device 104 may have its own field of view. One or more sensors 102 may be configured to analyze the FOV 114 of one or more captured images.

[0040] In some embodiments, system 100 may include at least one imaging device 104. The at least one imaging device 104 may be mounted based on the distance between one or more sensors 102, one or more targets, and the FOV 114 of the one or more sensors 102. The at least one imaging device 104 may capture one or more real-time images within the FOV 114. The one or more real-time images may include an accurate record of the scene or object within the FOV 114. Note that the FOV 114 may correspond to the observable area that an individual can view via the at least one imaging device 104. In some embodiments, the at least one imaging device 104 may include at least one of a multi-pixel digital camera or a dual infrared (IR) camera. The at least one imaging device 104 may include various capture modes and storage options. The at least one imaging device 104 may allow sharing of visual data in the form of the one or more captured real-time images. Additionally, the FOV 114 may include a pixel array. In some embodiments, each pixel in the pixel array may be a single picture element that constitutes the visual content of the one or more captured real-time images. Additionally, each pixel of the pixel array may be associated with a corresponding one or more regions defined by the user.

[0041] In some embodiments, the one or more sensors 102 and the at least one imaging device 104 may be spatially calibrated to maintain the same or a similar FOV 114. As Figure 2A shown, the one or more sensors 102 and the at least one imaging device 104 may be spatially calibrated to analyze the FOV 114 of the one or more captured real-time images, as indicated by arrow 200. Additionally, arrow 200 may indicate the process of restricting the FOV114 of the one or more sensors and the at least one image capture device 104. First, the FOV 202 of the at least one imaging device 104 may be greater than the FOV114 of the one or more sensors 102. Additionally, the one or more sensors 102 and the at least one imaging device 104 may be spatially calibrated to only restrict and process the portion that is the intersection of the one or more sensors 102 and the at least one imaging device 104 in the one or more real-time images. Such spatial calibration may ensure that each pixel in the pixel array may have the same or nearly the same FOV 114. It will be apparent to those skilled in the art that the at least one imaging device 104 and the one or more sensors 102 may be spatially calibrated by correlating one or more stored images with known values and then applying the calibration results to the uncalibrated one or more real-time images. In some embodiments, the same FOV 114 of the pixel array may be ensured by eliminating the parallax and different orientations of the one or more captured real-time images.

[0042] In some embodiments, spatial calibration may include the process of aligning and synchronizing data from at least one imaging device 104 and one or more sensors 102 to accurately study the FOV 114. In one example, spatial calibration may be performed on a dual IR camera and an IR sensor to precisely locate and measure the temperature of a flame within the FOV 114. Additionally, spatial calibration may ensure that one or more real-time images captured by at least one imaging device 104 and the thermal radiation or infrared (IR) emissions detected and measured from the data of one or more sensors 102 correspond to the same region of interest, thereby allowing for accurate flame detection.

[0043] System 100 may further include one or more processors 106. The one or more processors 106 may be communicatively coupled to the one or more sensors 102 and at least one imaging device 104. In some embodiments, the FOV 202 of at least one imaging device 104 may be adjusted using the FOV 114 of the one or more sensors 102, as described in connection with Figure 2B that. The FOV 202 of at least one imaging device 104 may be calculated using one or more known parameters. The one or more known parameters may include the distance between the one or more sensors 102 and the at least one imaging device 104, denoted by "ds". Additionally, the one or more known parameters may include the distance of an object or scene in one or more real-time images from the one or more sensors 102, denoted by "D". Additionally, the one or more known parameters may include half of the FOV 114 at a given distance, denoted by "θ". Additionally, the one or more known parameters may include "H" which may be defined as half of the diameter of the FOV 114 of the one or more sensors 102. "H" may be calculated using the formula: H = D × tanθ. In one example, when θ is 45 degrees and D is 10 meters (m), H may be calculated as 16.20 m. Note that θ may gradually decrease as D increases. Additionally, the FOV 202 of at least one imaging device 104 may be measured on one side, denoted by "α". "α" may be measured using the formula: Additionally, the FOV 202 of at least one imaging device 104 may be measured on the other side, denoted by "β". "β" may be measured using the formula:

[0044] In some embodiments, one or more processors 106 may receive one or more captured real-time images. Additionally, one or more processors 106 may be configured to compare the one or more real-time images with at least one reference image. In some embodiments, the at least one reference image may be obtained by comparing at least two consecutive real-time images from the one or more real-time images based at least on one or more coordinates of each of the one or more real-time images. In an example embodiment, the one or more coordinates may include at least an x coordinate, a y coordinate, and a z coordinate. Additionally, one or more processors 106 may be configured to determine misalignment information, obstacle information, or misalignment information and obstacle information within the FOV based at least on the comparison result. Note that the one or more sensors 102 and the at least one image capture device 104 may be collectively referred to as a "flame detector".

[0045] In some embodiments, system 100 may include at least one accelerometer (not shown) to determine changes in one or more coordinates of the one or more sensors 102 within a set time delay specified by the user based at least on the comparison result, thereby determining misalignment information. As described above, the one or more real-time images may be divided into a pixel array. Each pixel of the pixel array may be masked with one or more regions. Additionally, each of the corresponding one or more regions may be defined with a criticality level. The criticality level of each corresponding region may be one of non-critical, critical, or very critical. The non-critical region may correspond to a region where misalignment and / or an obstacle is not detected. The very critical region may correspond to a region where misalignment and / or an obstacle is detected. The critical region may correspond to a region where misalignment or an obstacle may be detected. Note that at least a portion of the pixel array may be associated with the corresponding one or more regions using artificial intelligence (AI), machine learning (ML), video analysis, or historical data. Additionally, one or more processors 106 may be configured to segment the one or more real-time images into multiple infrared (IR) channels. At least one filter (not shown) may be used to mask the multiple IR channels with the one or more regions defined by the criticality level. Additionally, one or more processors 106 may be configured to identify multiple key points. The multiple key points may include distinct contrast edges, curve coordinate points, or distinct contrast edges and curve coordinate points on the masked multiple IR channels.

[0046] Reference Figure 3A , at least one imaging device 104 may display overlapping circles 300 relative to distance based on the identified key points to indicate the FOV 114. In an example embodiment, the one or more real-time images with the overlapping circles 300 may indicate the distance of one or more targets in the overlapping circles 300 from the at least one imaging device 104. Reference Figure 3B, once the FOV 114 can be confirmed, one or more regions can be defined within the FOV 114. For example, the overlapping circles 300 can indicate non-critical regions, and the overlapping squares 302 can indicate highly critical regions. Additionally, once the FOV 114 and one or more regions within the FOV 114 can be defined, the user can set a time delay in seconds. Note that, in order to determine misalignment information, multiple IR channels can be masked based on the identified key points. Additionally, note that, in order to determine obstacle information, multiple IR channels can be masked based on the criticality level.

[0047] In some example embodiments, one or more processors 106 may include suitable logic components, circuits, and / or interfaces that are capable of operating to execute one or more instructions stored in a memory (not shown) to perform a predetermined operation. In some embodiments, one or more processors 106 may store one or more real-time images in the non-volatile memory of one or more processors 106. In some embodiments, one or more processors 106 may be configured to decode and execute any instructions received from one or more other electronic devices or servers. One or more processors 106 may be configured to execute one or more computer-readable program instructions, such as program instructions for performing any function described in this specification. Additionally, one or more processor technologies known in the art may be utilized to implement one or more processors 106. Examples of processors include, but are not limited to, one or more general-purpose processors (e.g., or Advanced Micro (AMD) microprocessors) and / or one or more dedicated processors (e.g., digital signal processors or system-on-chip (SOC) field-programmable gate array (FPGA) processors).

[0048] Furthermore, the memory may store a set of instructions and data. In some embodiments, the memory may include one or more instructions executable by the processor to perform a specific operation. It is apparent to those skilled in the art that the one or more instructions stored in the memory enable the hardware of the system to perform a predetermined operation. Some well-known memory implementations include, but are not limited to, fixed (hard) drives, magnetic tapes, floppy disks, optical disks, compact disc read-only memory (CD-ROM) and magneto-optical disks, semiconductor memories (such as ROM), random access memory (RAM), programmable read-only memory (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), flash memory, magnetic or optical cards, or other types of media / machine-readable media suitable for storing electronic instructions.

[0049] Referring backFigure 1 The system 100 may further include at least one digital output 108. The at least one digital output 108 may be coupled to one or more processors 106. The at least one digital output 108 may generate temperature-related information in a discrete digital format. In some embodiments, the at least one digital output 108 may be in binary form, characterizing the temperature state as 1 and 0. The temperature state can be easily processed and interpreted by digital devices such as microcontrollers, computers, or data acquisition systems. In some embodiments, the at least one digital output 108 may include a relay (not shown). Additionally, the at least one digital output 108 may allow for precise temperature monitoring, triggering of alarms, and data storage. Further, the at least one digital output 108 may be integrated with the flame and gas unit 116.

[0050] The system 100 may further include at least one analog output 110. The at least one analog output 110 may be coupled to one or more processors 106. The at least one analog output 110 may be in the form of a voltage or a current. The at least one analog output 110 may provide a continuous temperature characterization to enable real-time monitoring and analysis. In some embodiments, the level of the at least one analog output 110 may correspond to the detected temperature. Additionally, the at least one analog output 110 may be integrated with the flame and gas unit 116.

[0051] The system 100 may further include at least one communication output 112. The at least one communication output 112 may be coupled to one or more processors 106. The at least one communication output 112 may facilitate data transmission. In some embodiments, the at least one communication output 112 may include High-Speed Addressable Remote Transducer (HART), Modbus, TCP / IP. Additionally, the at least one communication output 112 may enable seamless connection between the system 100 and other monitoring and control devices. In some embodiments, the other monitoring and control devices may include a Supervisory Control and Data Acquisition (SCADA) system, a Programmable Logic Controller (PLC).

[0052] In some example embodiments, HART may provide a hybrid analog and digital signal to allow for real-time measurement data and device diagnostics on a single pair of wires. In another example embodiment, Modbus is a widely adopted serial communication protocol that allows for easy data exchange between multiple devices, making it suitable for industrial applications. In another example embodiment, TCP / IP is a standard Internet protocol suite that extends connectivity beyond the local network to enable remote monitoring and control of the system. In some embodiments, the at least one communication output 112 may be integrated with the flame and gas unit 116.

[0053] In some embodiments, the system may be installed near the environment 118. In some embodiments, the environment 118 may be a fire-prone area, such as an industrial oil site. It will be apparent to those skilled in the art that a fire-prone area is an area where a fire is most likely to occur or has a higher tendency to occur.

[0054] In some embodiments, the system 100 may include a communication device 120. One or more processors 106 may be configured to send one or more notifications to a user or a remote server via the communication device 120 based at least on the determined misalignment and / or obstacle information. The communication device 120 may be a smart phone, a tablet computer, a personal computer, or any other communication device known in the art.

[0055] It will be apparent to those skilled in the art that the above components of the system 100 are provided for illustrative purposes only. In some embodiments, the system 100 may further include some other components without departing from the scope of the present disclosure.

[0056] Figure 4A Illustrates one or more real-time images segmented into multiple IR channels according to an example embodiment of the present disclosure. Figure 4B Illustrates one or more real-time images with misalignment information determined by the system 100 according to an example embodiment of the present disclosure. In combination Figures 1 to 3B to describe Figures 4A to 4B .

[0057] In some embodiments, one or more processors may be configured to segment an image 400 of one or more real-time images into multiple infrared (IR) channels, as Figure 4A shown. At least one filter may be used to mask the multiple IR channels using one or more regions defined by a criticality level. To determine the misalignment information, the multiple IR channels may be masked based on the identified key points. As Figure 4A shown, the multiple IR channels may include an R_channel (red channel) 402, a G_channel (green channel) 404, and a B_channel (blue channel) 406.

[0058] Reference Figure 4B, at least one reference image can be obtained by comparing at least two consecutive real-time images from one or more real-time images based at least on one or more coordinates of each of the one or more real-time images. In some embodiments, consecutive frames of one or more real-time images can be taken at multiple times including T, T + 1, ..., T + n, T + (n + 1), T + (n + 2), etc. Consecutive frames of one or more real-time images can at least include the frame 408 at T, the frame 410 at T + 1, the frame 412 at T + n, the frame 414 at T + (n + 1), and the frame 416 at T + (n + 2). Additionally, misalignment information can be determined at T + (n + 1) after the difference between T + (n + 1) and T + n with reference to the previous frame T + n. Additionally, misalignment information can be determined based at least on a threshold limit set by the user. Misalignment information can be determined when the difference of the identified multiple key points or consecutive frames may exceed the threshold limit. Thus, (T + 1) can be stored as at least one reference image.

[0059] Additionally, consecutive frames of T + (n + 1) and T + (n + 2) can be compared with the at least one reference image. The difference between the at least one reference image and these consecutive frames can be greater than the threshold limit, such that at least one reference image - T + (n + 1) is greater than the threshold limit, at least one reference image - T + (n + 2) is greater than the threshold limit, and so on. Thus, the misalignment information can be consistent for a time delay set by the user, such as 30 frames per second (fps) for 5 seconds, which is 5 * 30 fps. Thus, in order to determine the misalignment information, at least one accelerometer can be utilized for an additional secondary check.

[0060] Figure 5A Illustrates one or more real-time images segmented into multiple IR channels according to an example embodiment of the present disclosure. Figure 5B Illustrates one or more real-time images with obstacle information determined by the system 100 according to an example embodiment of the present disclosure. In combination Figures 1 to 3B to describe Figures 5A to 5B .

[0061] As described above in Figure 1 , one or more processors can be configured to segment an image 500 of one or more real-time images into multiple infrared (IR) channels. Multiple IR channels can be masked using at least one filter with one or more regions defined by a criticality level. In order to determine obstacle information, multiple IR channels can be masked based on the criticality level. Additionally, as Figure 5A shown, the multiple IR channels can include an R_channel (red channel) 502, a G_channel (green channel) 504, and a B_channel (blue channel) 506.

[0062] ReferenceFigure 5B At least one reference image can be obtained by comparing at least two consecutive real-time images from one or more real-time images based at least on one or more coordinates of each image in the one or more real-time images. In some embodiments, consecutive frames of the one or more real-time images can be taken at multiple times including T, T+1, ..., T+n, T+(n+1), T+(n+2), etc. Consecutive frames of the one or more real-time images can at least include the frame 508 at T, the frame 510 at T+1, the frame 512 at T+n, the frame 514 at T+(n+1), and the frame 516 at T+(n+2). In addition, obstacle information can be determined at T+(n+1) with reference to the previous frame T+n after the difference between T+(n+1) and T+n. Obstacle information can be determined based at least on a threshold limit set by the user. Obstacle information can be determined when the difference of the identified multiple key points or consecutive frames may exceed the threshold limit. Thus, (T+n) can be stored as at least one reference image.

[0063] In addition, consecutive frames of T+(n+1) and T+(n+2) can be compared with the at least one reference image. Additionally, the difference between the at least one reference image and these consecutive frames can be greater than the threshold limit, such that at least one reference image - T+(n+1) is greater than the threshold limit, at least one reference image - T+(n+2) is greater than the threshold limit, and so on. Thus, the obstacle information can be consistent for a time delay set by the user, such as 32fps for 6 seconds, which is 6 * 32fps, and then the obstacle information can be reported to the user.

[0064] Figure 6 An exemplary scenario 600 of the installation of the system 100 according to an exemplary embodiment of the present disclosure is illustrated. In conjunction with Figures 1 to 5B is described Figure 6 .

[0065] As described above in Figure 1 , one or more sensors 102 and at least one imaging device 104 can be spatially calibrated to maintain the same or similar FOV 114. The FOV 114 can be viewed on the user interface 602 of the communication device 120. In addition, an Android application or an IOS application can be used to view the FOV 114. In addition, the system 100 can communicate with the communication device 120 via Wi-Fi or any other network interface known in the art. In addition, the FOV 114 can include one or more regions.

[0066] In one example implementation, one or more areas may be marked with different circles to indicate criticality levels. A very critical area may be marked with a circle 604 at a distance of 200 feet (ft) (preferably a red circle). A non-critical area may be marked with a circle 606 at a distance of 150 ft (preferably an orange circle). A non-critical area may be marked with a circle 608 at a distance of 100 ft (preferably a green circle). One or more areas may be marked to indicate which are the FOVs 114 at different distances from the system 100.

[0067] Figure 7 An exemplary scenario 700 for determining misalignment information according to an example implementation of the present disclosure is illustrated. In conjunction with Figures 1 to 6 to Figure 7 is described.

[0068] As described above in Figure 6 the FOV 114 may be viewed on the user interface 602 of the communication device 120. Additionally, an Android application or an IOS application may be used to view the FOV 114. In some implementations, during the installation of the system 100, at least one reference image may be stored in the memory of one or more processors 106. Additionally, the user interface 602 may display information storing at least one reference image. In one example, the information may include "Store the image below as a reference for occlusion and misalignment". Additionally, the user interface 602 may include a button 702 to request the user to confirm at least one reference image. In one example, the button 702 may include "Confirm and agree to continue".

[0069] Furthermore, the identified key points may be marked on at least one of the stored reference images. Then, the identified key points may be compared with one or more other real-time images. Additionally, based on the comparison results, misalignment information may be determined. When determining the misalignment information, a warning may be indicated on the system 100. Additionally, the misaligned image 704 may be viewed on the user interface 602 of the communication device 120. In some implementations, the user may navigate back to view at least one of the stored reference images, as indicated by the arrow 706.

[0070] Figure 8 An exemplary scenario 800 for determining obstacle information according to an example implementation of the present disclosure is illustrated. In conjunction with Figures 1 to 7 to Figure 8 is described.

[0071] As described above in Figures 6 to 7As described, the FOV 114 can be viewed on the user interface 602 of the communication device 120. Additionally, an Android application or an IOS application can be used to view the FOV 114. In some embodiments, during the installation of the system 100, at least one reference image can be stored in the memory of one or more processors 106. Further, the user interface 602 can display information storing at least one reference image. In one example, the information can include "Store the image below as a reference for occlusion and misalignment". Additionally, the user interface 602 can include a button 802 to request the user to confirm at least one reference image. In one example, the button 802 can include "Confirm to agree to continue".

[0072] Furthermore, the identified key points can be marked on at least one of the stored reference images. Then, the identified key points can be compared with one or more other real-time images. Based on the comparison result, the system 100 can determine obstacle information. The obstacle information can include a moving object or an occluding object that occludes the FOV 114. When determining the obstacle information, a warning can be indicated on the system 100. Additionally, the occluded image 804 can be viewed on the user interface 602 of the communication device 120. In some embodiments, the user can navigate back to view at least one of the stored reference images, as indicated by the arrow 806.

[0073] It will be apparent to those skilled in the art that, without departing from the scope of the present disclosure, the detection of one or more regions and the execution of further processing steps can be performed by one or more processors 106 of the system 100 using at least one imaging device 104 and one or more sensors 102.

[0074] In various embodiments, the corresponding one or more regions can be any arbitrary shape selected by the user using a graphical user interface (GUI) (not shown). The arbitrary shape can include a circular shape, a cloud-like shape, a triangular shape, or any other shape that does not conform to a typical geometric pattern.

[0075] In the embodiments disclosed by the present invention, the system 100 can adopt various image processing techniques known in the art to analyze the FOV 114 of one or more captured images.

[0076] Obviously, the above components of the system 100 are provided only for illustrative purposes. In another embodiment, without departing from the scope of the present disclosure, the system 100 can include other components, such as a controller unit, a microprocessor unit (MPU), a microcontroller unit (MCU), etc.

[0077] Figure 9A flowchart illustrating the steps of a method 900 for determining misalignment information and obstacle information according to an example implementation of the present disclosure is presented. In conjunction with Figures 1 to 8 pair Figure 9 is described.

[0078] First, method 900 includes detecting one or more targets within the FOV 114 of one or more sensors 102 at step 902 via one or more sensors 102. In some implementations, the one or more sensors 102 may include one or more infrared (IR) sensors, flame sensors, or photodiodes. Additionally, the FOV 114 may include a pixel array. For example, the one or more sensors 102 may detect one or more targets in an industrial area within the FOV 114 of the one or more sensors 102 by analyzing the FOV 114.

[0079] Subsequently, method 900 includes capturing one or more real-time images of the one or more targets within the FOV 114 at step 904 via at least one imaging device 104. Further, each pixel of the pixel array may be associated with a corresponding one or more regions defined by the user. For example, an IR camera may capture one or more real-time images of an industrial area within the FOV 114, and each of the one or more captured real-time images may include a pixel array that represents the details and information captured by the IR camera.

[0080] Subsequently, method 900 includes receiving the one or more real-time images from at least one imaging device 104 at step 906 via one or more processors 106. In some implementations, each of the corresponding one or more regions may be defined with a criticality level. The criticality level of each respective region may be one of non-critical, critical, or very critical. For example, the one or more processors 106 may receive the one or more captured real-time images of the industrial area.

[0081] Subsequently, method 900 includes comparing the one or more real-time images with at least one reference image at step 908 via one or more processors 106. Additionally, the at least one reference image may be obtained by comparing at least two consecutive real-time images from the one or more real-time images based at least on one or more coordinates of each image of the one or more real-time images. In an example implementation, the one or more coordinates may include at least an x coordinate, a y coordinate, and a z coordinate. In some implementations, the one or more processors 106 may be configured to segment the one or more real-time images into multiple IR channels. Further, the one or more processors 106 may mask the multiple IR channels with the one or more regions having criticality levels.

[0082] In some embodiments, one or more processors 106 may identify multiple key points. The multiple key points may include distinct contrast edges, curve coordinate points, or distinct contrast edges and curve coordinate points on multiple masked IR channels. For example, one or more processors 106 may compare one or more real-time images of an industrial area with at least one reference image to determine misalignment information and / or obstacle information.

[0083] Subsequently, method 900 includes determining, at step 910, misalignment information, obstacle information, or misalignment information and obstacle information within FOV 114 via one or more processors 106 based at least on the comparison result. In some embodiments, one or more processors 106 may be configured to determine changes in the coordinates of one or more sensors 102 within a set time delay specified by the user based at least on the comparison result, thereby determining misalignment information. Additionally, to determine misalignment information, multiple IR channels may be masked based on the identified key points. Additionally, to determine obstacle information, multiple IR channels may be masked based on a criticality level.

[0084] For example, based on the comparison result, misalignment in one or more of the captured real-time images may be determined, or an obstacle obscuring FOV 114 may be determined in order to correctly install system 100 near the industrial area.

[0085] Figure 10 A flowchart illustrating steps of a method 1000 for determining misalignment information according to an example embodiment of the present disclosure is exemplified. In conjunction with Figure 9 to Figure 10 is described.

[0086] First, at step 1002, at least one imaging device 104 displays overlapping circles 300 relative to distance to indicate FOV 114. Subsequently, at step 1004, FOV 114 is confirmed. Subsequently, at step 1006, one or more regions are defined within FOV 114. Additionally, one or more sensors 102 may detect one or more targets within the FOV 114 of one or more sensors 102, as explained in step 902.

[0087] Subsequently, at step 1008, the user sets the time delay(s). In an example embodiment, the time delay set by the user may include 30 frames per second (fps) for 5 seconds, i.e., 5 * 30 fps. Subsequently, at step 1010, monitoring is enabled / started. In some embodiments, one or more sensors 102 and at least one image capture device 104 may monitor one or more targets within FOV114. In some embodiments, steps 1002 - 1010 may form a configuration for determining misalignment information.

[0088] Subsequently, at step 1012, an image T is captured. At least one imaging device 104 may capture an image T of one or more targets within the FOV 114 at T seconds, as explained in step 904. Additionally, one or more processors 106 may receive the captured image T, as explained in step 906. Subsequently, at step 1014, it is separated into multiple IR channels. In some embodiments, the captured image T may be separated into multiple IR channels. Subsequently, at step 1016, masking is performed using at least one filter. One or more processors 106 may mask the multiple IR channels via at least one filter using one or more regions with a criticality level.

[0089] Subsequently, at step 1018, multiple key points are identified based on picking distinct contrast edges, curve coordinate points on the masked image T of the multiple IR channels. In one example embodiment, the multiple key points may include one or more coordinates of the captured image T. In an exemplary embodiment, one or more coordinates may include at least an x coordinate, a y coordinate, and a z coordinate. Subsequently, at step 1020, the images T and T + 1 are compared to check for any differences in one or more coordinates. In one case, if there are no differences in one or more coordinates, proceed to step 1012 to capture another image.

[0090] Subsequently, at step 1022, the captured image T is taken as a reference. In another case, if there are differences in one or more coordinates, the captured image T can be stored as at least one reference image. Subsequently, at step 1024, the image T is compared with T+2 and T+3 within 30fps * user-set delay (in seconds). In some embodiments, the user-set delay in seconds can correspond to the user-set time delay in seconds. Additionally, one or more processors 106 can compare the images T+2 and T+3 with the reference image T, as explained in step 908. In one case, if there are no changes in one or more coordinates, proceed to step 1012 to capture another image. Subsequently, at step 1026, at least one accelerometer checks for changes in the x, y, and z coordinates within the user-set time delay (in seconds). In another case, if there are changes in one or more coordinates, at least one accelerometer can further check for any changes in one or more coordinates within the user-set time delay. In one case, if there are no changes in one or more coordinates, proceed to step 1012 to capture another image. Subsequently, at step 1028, misalignment information is reported. In another case, if there are changes in one or more coordinates, misalignment information can be reported. In some embodiments, one or more processors 106 can determine the misalignment information within the FOV 114, as explained in step 910.

[0091] In some embodiments, steps 1012 - 1028 can be performed by one or more processors 106 to determine the misalignment information within the FOV 114.

[0092] Figure 11 A flowchart illustrating the steps of a method 1100 for determining obstacle information according to an example embodiment of the present disclosure is presented. In conjunction with Figure 9 For Figure 11 description.

[0093] First, at step 1102, at least one imaging device 104 displays overlapping circles 300 relative to distance to indicate the FOV 114. Subsequently, at step 1104, the FOV 114 is confirmed. Subsequently, at step 1106, one or more regions are defined within the FOV 114. Additionally, one or more sensors 102 can detect one or more targets within the FOV 114 of one or more sensors 102, as explained in step 902.

[0094] Subsequently, at step 1108, the user sets a time delay (s). In one example implementation, the time delay set by the user may include 30 frames per second (fps) for 5 seconds, which is 5 * 30 fps. Subsequently, at step 1110, monitoring is enabled / started. In some implementations, one or more sensors 102 and at least one image capture device 104 may monitor one or more targets within the FOV 114. In some implementations, steps 1102 - 1110 may form a configuration for determining misalignment information.

[0095] Subsequently, at step 1112, an image T is captured. At least one imaging device 104 may capture an image T of one or more targets within the FOV 114 at T seconds, as explained in step 904. Additionally, one or more processors 106 may receive the captured image T, as explained in step 906. Subsequently, at step 1114, it is separated into multiple IR channels. In some implementations, the captured image T may be separated into multiple IR channels. Subsequently, at step 1116, at least one filter is used for masking. One or more processors 106 may mask the multiple IR channels via at least one filter using one or more regions with critical levels.

[0096] Subsequently, at step 1118, multiple key points are identified based on picking distinct contrast edges, curve coordinate points on the masked image T of the multiple IR channels. In one example implementation, the multiple key points may include one or more coordinates of the captured image T. The one or more coordinates may include at least an x - coordinate, a y - coordinate, and a z - coordinate. Subsequently, at step 1120, image T and T + 1 are compared to check if there are any differences in one or more coordinates. In one case, if there are no differences in one or more coordinates, proceed to step 1112 to capture another image.

[0097] Subsequently, at step 1122, the captured image T is captured as a reference. In another case, if there are differences in one or more coordinates, the captured image T can be stored as at least one reference image. Subsequently, at step 1124, the image T is compared with T+2 and T+3 within 30fps * user-set delay (in seconds). In some embodiments, the user-set delay in seconds can correspond to the user-set time delay in seconds. In one case, if there are no changes in one or more coordinates, proceed to step 1112 to capture another image. Additionally, one or more processors 106 can compare the images T+2 and T+3 with the reference image T, as explained in step 908. Subsequently, at step 1126, the obstacle information is reported. In another case, if there are changes in one or more coordinates, the obstacle information can be reported at least based on the comparison result. In some embodiments, one or more processors 106 can determine the obstacle information within the FOV 114, as explained in step 910.

[0098] In some embodiments, steps 1112-1126 can be performed by one or more processors 106 to determine the misalignment information within the FOV114.

[0099] It should be understood that methods 900, 1000, and 1100 can be implemented by one or more embodiments disclosed by the present invention, and these embodiments can be combined or modified according to expectations or needs. Additionally, the steps in methods 900, 1000, and 1100 can be modified, the order can be changed, they can be performed differently, sequentially, in parallel, or simultaneously, or modified in other ways according to expectations or needs.

[0100] Without departing from the scope of the present disclosure, the above embodiments of the present disclosure can be performed by one or more processors 106 of the system 100 and methods 900, 1000, and 1100 using one or more sensors 102 and at least one imaging device 104. In some embodiments, the system 100 and methods 900, 1000, and 1100 can provide accurate misalignment information and obstacle information within the FOV. The system 100 can be installed in high-risk environments such as manufacturing units, refineries, coal mines, etc., in order to immediately warn of any misalignment or obstacle that may interfere with flame detection within the FOV. The system 100 and methods 900, 1000, and 1100 can provide misalignment information and obstacle information without any human intervention.

[0101] Those skilled in the art to which the present disclosure pertains will, after benefiting from the foregoing description and the teachings presented in the related drawings, conceive of many modifications and other embodiments of the present disclosure set forth herein. Accordingly, it is to be understood that the present disclosure is not limited to the specific embodiments disclosed, and that modifications and other embodiments are intended to be included within the scope of the appended claims. Moreover, although the example embodiments have been described above in the context of certain example combinations of elements and / or functions, it should be understood that different combinations of elements and / or functions may be provided by alternative embodiments without departing from the scope of the appended claims. In this regard, for example, combinations of elements and / or functions different from those explicitly described above may also be contemplated, as may be set forth in some of the appended claims. Although specific terms are employed herein, they are used in a general and descriptive sense only and not for purposes of limitation.

Claims

1. A system, comprising: one or more sensors configured to detect one or more targets within a field of view (FOV) of the one or more sensors; at least one imaging device mounted based on a distance between the one or more sensors, the one or more targets, and the FOV of the one or more sensors, wherein the at least one imaging device is configured to capture one or more real-time images of the one or more targets within the FOV; as well as one or more processors communicatively coupled to the one or more sensors and the at least one imaging device, wherein the one or more processors are configured to: receiving the one or more real-time images from the at least one imaging device; comparing the one or more real-time images to at least one reference image; as well as Misalignment information, obstacle information, or misalignment information and obstacle information within the FOV are determined based at least on the comparison result.

2. The system of claim 1, wherein the FOV comprises a pixel array, wherein each pixel in the pixel array is associated with a corresponding one or more regions defined by a user. 3 . The system of claim 2 , wherein each of the corresponding one or more regions is further defined by a criticality level, wherein the criticality level of each respective region is one of non-critical, critical, or very critical.

4. The system of claim 3, wherein the one or more processors are further configured to segment the one or more real-time images into a plurality of infrared (IR) channels, and wherein the plurality of IR channels are masked using at least one filter with the one or more regions defined by the criticality level.

5. The system of claim 4, wherein the one or more processors are further configured to identify a plurality of key points, wherein the plurality of key points include sharp contrast edges, curvilinear coordinate points, or sharp contrast edges and curvilinear coordinate points on the masked plurality of IR channels.

6. A system according to claim 1, wherein the one or more processors are further configured to send one or more notifications to a user or a remote server via a communication device based at least on the determined misalignment information, obstacle information, or misalignment information and obstacle information within the FOV.

7. A method comprising: detecting, via one or more sensors, one or more targets within a field of view (FOV) of the one or more sensors; capturing, via at least one imaging device, one or more real-time images of the one or more targets within the FOV; receiving, via one or more processors, the one or more real-time images from the at least one imaging device; comparing, via the one or more processors, the one or more real-time images to at least one reference image; as well as Misalignment information, obstacle information, or misalignment information and obstacle information within the FOV are determined via the one or more processors based at least on the comparison result.

8. The method of claim 7, wherein the FOV comprises a pixel array, and wherein each pixel in the pixel array is associated with a corresponding one or more regions defined by a user.

9. The method of claim 8, wherein each of the corresponding one or more regions is further defined by a criticality level, wherein the criticality level of each respective region is one of non-critical, critical, or very critical.

10. The method according to claim 9, further comprising: splitting, via the one or more processors, the one or more real-time images into a plurality of IR channels; masking, via the one or more processors, the plurality of IR channels using the one or more regions having the criticality level; as well as A plurality of key points are identified via the one or more processors, wherein the plurality of key points include sharp contrast edges, curvilinear coordinate points, or sharp contrast edges and curvilinear coordinate points on the masked plurality of IR channels.

Images