Flame detection system and method based on imaging

Abstract

The invention discloses a flame detection system based on imaging. The imaging-based flame detection system includes at least one image capture device to capture one or more images in a field of view (FOV). Each of the one or more images includes an array of pixels. Further, one or more sensors are communicatively coupled to the at least one image capture device and configured to analyze the FOV of the captured one or more images. In addition, the one or more processors are communicatively coupled to the at least one image capture device and the one or more sensors. The one or more processors are configured to receive one or more captured images; associating at least a portion of the array of pixels with the corresponding one or more regions; the corresponding one or more zones are associated with a critical level, and a state is determined based at least on the analyzed FOV and the critical level.

Description

Technical Field

[0001] Example embodiments generally relate to flame detection systems, and more particularly, to imaging-based flame detection systems and methods. 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 to identify flames in the presence of false alarms. However, in industrial environments, there are often essential flames such as flares, so care must be taken during actual installation to prevent flares from entering the FOV. In addition, for flame detection, some regions within the FOV are more important than others. Some regions require highly accurate flame detection, while in some regions, flame detection is not as critical. Due to the non-imaging nature of the system, current flame detection systems lack the ability to assign or fine-tune priority weights to different FOV regions. Such systems are not easy to install and reduce the accuracy of flame classification, and lack the ability to reduce false alarms or enhance flame detection. Therefore, there is still a need for an imaging-based flame detection system that can facilitate simplified installation procedures, improve flame classification, and more effectively reduce false alarms, ultimately resulting in enhanced flame detection capabilities.

[0003] The applicant has 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 summary of the invention is not an exhaustive review and is neither intended to identify key 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 herein, and some of these embodiments will be further described in the detailed description presented later.

[0005] In an example implementation, an imaging-based flame detection system is disclosed. The imaging-based flame detection system includes at least one image capture device configured to capture one or more images in a field of view (FOV). Each of the one or more images includes a pixel array. Additionally, the imaging-based flame detection system includes one or more sensors communicatively coupled to the at least one image capture device. The one or more sensors are configured to analyze the FOV of the one or more captured images. The imaging-based flame detection system further includes one or more processors communicatively coupled to the at least one image capture device and the one or more sensors. The one or more processors are configured to receive the one or more captured images; associate at least a portion of the pixel array with corresponding one or more zones; and associate the corresponding one or more zones with criticality levels. Then, the one or more processors are configured to determine a status based at least on the analyzed FOV of the one or more captured images and the criticality levels of the corresponding one or more zones.

[0006] In some implementations, the one or more sensors are one or more infrared (IR) sensors, flame sensors, or photodiodes.

[0007] In some implementations, the criticality level of each respective zone of the one or more zones is non-critical, critical, or highly critical.

[0008] In some implementations, the status indicates the presence of flame or smoke in the corresponding one or more zones. Additionally, the non-critical zones correspond to zones where expected flames are present, the critical zones correspond to zones where possible non-critical flames are present, and the highly critical zones correspond to zones where possible unexpected flames are present.

[0009] In some implementations, the one or more processors are configured to generate a first signal when an unexpected flame is detected in a highly critical zone and send the first signal to a communication device. In some implementations, the communication device is configured to generate an audible message for a user indicating the presence of an unexpected flame in the highly critical zone.

[0010] In some implementations, the one or more processors are configured to generate a second signal when a non-critical flame is detected in a critical zone and send the second signal to the communication device. In some implementations, the communication device generates a notification for the user indicating the presence of a non-critical flame in the critical zone.

[0011] In some embodiments, one or more processors are configured to generate a third signal when smoke is detected in a non-critical area and send the third signal to a communication device. In some embodiments, the communication device generates an audible message for the user indicating the presence of smoke in the non-critical area.

[0012] In some embodiments, one or more processors are configured to analyze the FOV to determine a status by evaluating the pixel array of at least one image capture device and one or more sensors.

[0013] In some embodiments, at least one image capture device and one or more sensors are spatially calibrated to analyze flames within the FOV of one or more captured images.

[0014] In some embodiments, one or more processors are configured to reassign different critical levels to one or more areas during operation of the imaging-based flame detection system.

[0015] In another exemplary embodiment, an imaging-based flame detection method is disclosed. The imaging-based flame detection method includes the steps of: capturing one or more images in a field of view (FOV) via at least one image capture device. Each of the one or more images includes a pixel array. Additionally, the imaging-based flame detection method includes the steps of: analyzing the FOV of the one or more captured images via one or more sensors; receiving the one or more captured images via one or more processors; associating at least a portion of the pixel array with corresponding one or more areas via one or more processors; associating the corresponding one or more areas with critical levels via one or more processors; and determining a status via one or more processors based at least on the analyzed FOV of the one or more captured images and the critical levels of the corresponding one or more areas.

[0016] The above Summary is provided merely for the purpose of summarizing some example embodiments in order 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 in any way narrowing the scope or essence of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Accordingly, certain example embodiments of the present disclosure have been generally described above. The following will refer to the accompanying drawings, which are not necessarily drawn to scale, and in which:

[0018] Figure 1 Exemplary embodiments of an imaging-based flame detection system in accordance with example embodiments of the present disclosure are illustrated;

[0019] Figure 2Illustrates one or more regions of one or more captured images according to example embodiments of the present disclosure;

[0020] Figure 3 Illustrates simulation results of an imaging-based flame detection system according to example embodiments of the present disclosure;

[0021] Figure 4 Illustrates a flowchart showing steps of a method of an imaging-based flame detection system according to example embodiments of the present disclosure;

[0022] Figure 5 Illustrates a flowchart showing steps of a method of generating a first signal when an unexpected flame is detected in a highly critical area according to example embodiments of the present disclosure;

[0023] Figure 6 Illustrates a flowchart showing steps of a method of generating a second signal when a non-critical flame is detected in a critical area according to example embodiments of the present disclosure; and

[0024] Figure 7 Illustrates a flowchart showing steps of a method of generating a third signal when smoke is detected in a non-critical area according to example embodiments of the present disclosure. Detailed Description

[0025] 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.

[0026] The components illustrated in the drawings represent components that may or may not be present in various embodiments of the disclosure described herein, such that an embodiment may include fewer or more components than those shown in the drawings without departing from the scope of the disclosure. Some components may be omitted from one or more of the drawings or shown in dashed lines to make the components below visible.

[0027] As used herein, the term "comprising" means including but not limited to and should be construed 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".

[0028] 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).

[0029] As used herein, the word "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.

[0030] 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, the particular component or feature does not need to be included or have the characteristic. Such a component or feature may optionally be included in some embodiments, or it may be excluded.

[0031] The present disclosure provides various embodiments of systems and methods for imaging-based flame detection. The embodiments may be configured to detect flames based on different sensitivities assigned to different zones of a field of view. The embodiments may provide high-resolution thermal imaging to enable precise and early identification of flames. The embodiments may detect subtle temperature changes and spatial variations to allow for rapid and accurate flame localization, thereby reducing false alarms and enhancing safety in critical environments. The embodiments may provide real-time monitoring capabilities to ensure immediate response to flame outbreaks, thereby facilitating rapid intervention and minimizing potential damage. Additionally, the embodiments may be integrated into various settings ranging 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.

[0032] Figure 1 An example embodiment of an imaging-based flame detection system 100 according to an example embodiment of the present disclosure is illustrated. The imaging-based flame detection system 100 may include at least one image capture device 102, one or more sensors 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.

[0033] In some embodiments, at least one image capture device 102 may capture one or more images in a field of view (FOV) 114. The one or more images may include an exact record of a scene or subject in the FOV 114. Notably, the FOV 114 may correspond to the observable area that an individual may view via at least one image capture device 102. In some embodiments, at least one image capture device 102 may include at least one of a multi-pixel digital camera or a dual infrared (IR) camera. At least one image capture device 102 may include various capture modes and storage options. At least one image capture device 102 may enable sharing of visual data in the form of the one or more captured images. Additionally, each of the one or more images 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 images.

[0034] As discussed above, the imaging-based flame detection system 100 may include one or more sensors 104. The one or more sensors 104 may be communicatively coupled to at least one image capture device 102. In some embodiments, the one or more sensors 104 may include one or more infrared (IR) sensors, flame sensors, or photodiodes. The one or more sensors 104 may be configured to analyze the FOV 114 of the one or more captured images. The one or more sensors 104 may detect and measure thermal radiation or infrared (IR) emissions from the FOV 114.

[0035] In some embodiments, at least one image capture device 102 and the one or more sensors 104 may be spatially calibrated to analyze a flame within the FOV 114 of the one or more captured images. Such spatial calibration may ensure that each pixel in the pixel array may have the same or nearly the same FOV 114. In some embodiments, a flame may be detected by analyzing the pixels in the pixel array one by one. It will be apparent to those skilled in the art that at least one image capture device 102 and the one or more sensors 104 may be spatially calibrated by correlating the one or more stored images with known values and then applying the calibration results to uncalibrated one or more real-time images. In some embodiments, the FOV 114 of the pixel array may be ensured to be the same by eliminating the parallax and different orientations of the one or more captured images. Notably, the one or more images may be captured in real time.

[0036] In some embodiments, spatial calibration may include the process of aligning and synchronizing data from at least one image capture device 102 and one or more sensors 104 to accurately study the flame characteristics within the FOV 114. In one example, spatial calibration may be performed on dual IR cameras and IR sensors to precisely locate and measure the temperature of the flame within the FOV 114. Additionally, spatial calibration may ensure that one or more images captured by at least one image capture device 102 and the thermal radiation or infrared (IR) emissions detected and measured from the data of one or more sensors 104 correspond to the same region of interest, and thus allow for accurate flame detection.

[0037] The imaging-based flame detection system 100 may further include one or more processors 106. The one or more processors 106 may be communicatively coupled to at least one image capture device 102 and one or more sensors 104. Additionally, the one or more processors 106 may receive one or more captured images. Further, the one or more processors 106 may be configured to associate at least a portion of the pixel array with corresponding one or more zones. The one or more zones may include zones within the FOV 114 where expected flame / smoke is present, zones where possible non-critical flames are present, or zones where possible unexpected flames are present. The one or more zones may be assigned to at least a portion of the pixel array based at least on a criticality level. In some embodiments, the criticality level of each respective zone in the one or more zones may include non-critical, critical, or highly critical. Thus, the one or more zones may be classified as highly critical zones (not shown), critical zones (not shown), and non-critical zones (not shown). It is noted that at least a portion of the pixel array may be associated with the corresponding one or more zones using artificial intelligence (AI), machine learning (ML), or historical data. This will be described in more detail in a later part of the detailed description in conjunction with Figure 2 the one or more zones.

[0038] In some embodiments, the one or more processors 106 may be configured to determine a status based at least on the analyzed FOV 114 of the one or more captured images and the criticality level of the one or more zones. In some embodiments, the status may indicate the presence of flame or smoke in the one or more zones. Additionally, the one or more processors 106 may be configured to analyze the FOV 114 to determine the status by evaluating the pixel array of at least one image capture device 102 and the one or more sensors 104.

[0039] In various examples, one or more processors 106 may include suitable logic components, circuitry, and / or interfaces that are operable 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 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 of the functions 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 special-purpose processors (e.g., digital signal processors or system-on-a-chip (SOC) field-programmable gate array (FPGA) processors).

[0040] Additionally, 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 particular operation. It will be 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 disk 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.

[0041] The imaging-based flame detection system 100 may also 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 may 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. Additionally, the at least one digital output 108 may be integrated with the flame and gas unit 116.

[0042] The imaging-based flame detection 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 integral with the flame and gas unit 116.

[0043] The imaging-based flame detection 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 imaging-based flame detection 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).

[0044] In an example embodiment, HART provides a hybrid analog and digital signal to allow 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 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 local networks to enable remote monitoring and control of the imaging-based flame detection system 100. In some embodiments, the at least one communication output 112 may be integral with the flame and gas unit 116.

[0045] In various examples, the imaging-based flame detection system 100 may be installed near an environment 118. In some embodiments, the environment 118 may be an area prone to fire and / or an area where fire is used in the manufacture or processing of a product or substance, such as a chemical processing plant or an industrial oil site. It will be apparent to those skilled in the art that an area prone to fire is an area where a fire is most likely to occur or has a higher tendency to occur.

[0046] Figure 2 One or more regions of one or more captured images according to example embodiments of the present disclosure are illustrated. Figure 3 Illustrated is the simulation result 300 of the imaging-based flame detection system 100 according to example embodiments of the present disclosure. In combinationFigure 1 Pair Figure 3 And Figure 2 Are described.

[0047] As discussed above, one or more processors 106 may be configured to associate one or more zones with critical levels. Additionally, the critical level of each respective zone in the one or more zones may include highly critical, critical, or non - critical. Thus, one or more zones may be classified as highly critical zone 202, critical zone 204, and non - critical zone 206. Additionally, at least a portion of the pixel array may be associated with a corresponding one or more zones. The pixel array may include pixels 208, 210, 212, and so on.

[0048] In some embodiments, the highly critical zone 202 may correspond to a zone where there may be an unexpected flame. In other words, the highly critical zone 202 may correspond to a zone where a flame is not desired or expected. In some embodiments, the highly critical zone 202 may include important infrastructure in one or more of the captured images in the FOV 114 where a flame may not be expected to occur. For example, one or more processors 106 associate a portion N11 to N12 by M11 to M12 of the pixel array of one or more of the captured images as the highly critical zone 202.

[0049] Furthermore, one or more processors 106 may be configured to generate a first signal when an unexpected flame is detected within the highly critical zone 202. Additionally, the first signal may be sent to a communication device (not shown). In some example embodiments, the communication device may include an electronic device or an electromechanical device that may automatically activate upon receiving a signal from one or more processors 106. In some embodiments, the communication device may have a wireless or wired connection to one or more processors 106.

[0050] In some embodiments, the critical zone 204 may correspond to a zone where there may be a non - critical flame. In other words, the critical zone 204 may correspond to a zone where a flame is not expected, but the presence of the flame is not critical (e.g., hazardous) for a particular area of the environment 118. In some embodiments, the critical zone 204 may include an area in one or more of the captured images in the FOV 114 where there is a non - critical flame. For example, one or more processors 106 associate a portion N21 to N22 by M21 to M22 of the pixel array of one or more of the captured images as the critical zone 204, as an area within the associated portion where there may be a flame and the flame is non - critical for that area.

[0051] In addition, one or more processors 106 may be configured to generate a second signal when a non-critical flame is detected within the critical area 204. Additionally, the second signal may be sent to a communication device.

[0052] In some embodiments, the non-critical area 206 may correspond to an area where a flame is expected to be present. In other words, the non-critical area 206 may correspond to an area where a flame is expected to be present and is desired to be present. For example, the flame may be necessary for the operation of the environment 118. In some embodiments, the non-critical area 206 may include an area where an expected flame is present in one or more captured images within the FOV 114. In some embodiments, the non-critical area 206 may also include an area where smoke is present in one or more captured images within the FOV 114. For example, one or more processors 106 associate a portion N31 to N32 by M31 to M32 of the pixel array of one or more captured images as the non-critical area 206, as an area within the associated portion where an expected flame may be present or smoke is detected.

[0053] In addition, one or more processors 106 may be configured to generate a third signal when an expected flame or smoke is detected within the non-critical area 206. Additionally, the third signal may be sent to a communication device. In some examples, the third signal indicates the flare stack status (i.e., the flare stack is operating normally).

[0054] In some embodiments, one or more processors 106 may be configured to reassign different critical levels to one or more areas during the operation of the imaging-based flame detection system 100. In some embodiments, during the operation of the imaging-based flame detection system 100, one or more processors 106 may intelligently and dynamically modify the different critical levels of one or more areas. The modification may be based on real-time data or changing conditions. Basically, one or more processors 106 may allow the imaging-based flame detection system 100 to make different adjustments to resources, attention, or responses as needed and allocate them to one or more areas, thereby improving the overall flexibility and effectiveness of the heat detection and response tasks. In some embodiments, the communication device may generate an audible message or notification (e.g., a visual indication) for the user indicating the presence of a flame or smoke in one or more areas based on the received first signal, second signal, or third signal.

[0055] In some embodiments, the simulation results 300 may provide the presence of a flame or smoke in one or more zones. The simulation results 300 may include columns characterizing the respective zones. These zones include the highly critical zone 202, the critical zone 204, and the non-critical zone 206. Additionally, the simulation results 300 may include columns characterizing the status. The status may include a trip alarm (i.e., the alarm requires stopping safety-critical operations), an alarm (i.e., a low-level warning for notification only and only operative when necessary, not implying stopping operations), and the flare stack status. Additionally, the simulation results 300 may provide the results of a simulation of the imaging-based flame detection system 100 under controlled conditions. In some embodiments, the simulation results 300 may include the flames detected by the imaging-based flame detection system 100 in one or more zones. Additionally, the simulation results 300 may include signals generated based on the flames or smoke detected in one or more zones.

[0056] In one exemplary embodiment, when a flame is detected only in the non-critical zone 206, a third signal may be generated and sent to the communication device. The communication device may generate an audible message or notification for the user indicating the presence of a flame within the non-critical zone 206, which will be characterized under the flare stack status. Since the presence of a flame in the non-critical zone 206 may be expected, the audible message or notification may include information about the flame and may provide the user with an instruction to take no action. In some embodiments, the audible message or notification may include a siren / buzzer or a voice message. In various examples, when a flame is detected only in the non-critical zone 206, the communication device does not generate an audible message for the user. Additionally, when a flame is detected only in the non-critical zone 206, an indication of the flare stack status (i.e., the flare stack is operating normally) may be provided.

[0057] In another exemplary embodiment, when flames are detected in the critical zone 204 and the non-critical zone 206, a second signal and a third signal may be generated and sent to the communication device, which will be characterized under the alarm (LA) and the flare stack status. The communication device may generate a notification for the user indicating the presence of a flame within the critical zone 204 based on the second signal. Since the flame is not critical and may be present in the critical zone 204, the notification may provide the user with an instruction to take measures based on the flame. In some embodiments, the notification may include a text message or a voice message. Additionally, the communication device may generate an audible message or notification for the user indicating the presence of a flame within the non-critical zone 206 based on the third signal. Since the presence of a flame in the non-critical zone 206 is expected, the audible message or notification may provide the user with an instruction to take no action.

[0058] In another example implementation, when flames are detected in the highly critical area 202, the critical area 204, and the non-critical area 206, a first signal, a second signal, and a third signal may be generated and sent to a communication device, which will be characterized under the flare stack status, alarm (LA), and trip alarm (HH). The communication device may generate an audible message or notification for the user based on the first signal indicating the presence of a flame within the highly critical area 206. Since the detected flame in the highly critical area 202 is not expected, the audible message or notification may provide the user with an instruction to take immediate action. Similarly, the communication device may generate a notification for the user based on the second signal indicating the presence of a flame within the critical area 204. Since the flame is not critical and may be present in the critical area 204, the notification may provide the user with an instruction to take action based on the flame. As discussed above, the communication device may generate an audible message or notification for the user based on the third signal indicating the presence of a flame within the non-critical area 206. Since the presence of a flame in the non-critical area 206 is expected, the audible message or notification may provide the user with an instruction not to take any action.

[0059] In another example implementation, when flames are detected in the highly critical area 202 and the non-critical area 206, a first signal and a third signal may be generated and sent to a communication device, which will be characterized under the flare stack status and trip alarm (HH). The communication device may generate an audible message or notification for the user based on the first signal indicating the presence of a flame within the highly critical area 206. Since the detected flame in the highly critical area 202 is not expected, the audible message or notification may provide the user with an instruction to take immediate action. Additionally, the communication device may generate an audible message or notification for the user based on the third signal indicating the presence of a flame within the non-critical area 206. Since the presence of a flame in the non-critical area 206 is expected, the audible message or notification may provide the user with an instruction not to take any action.

[0060] In another example implementation, when a flame is detected in the critical area 204, such as when a flame is detected only in the critical area 204, a second signal may be generated and sent to a communication device, which will be characterized under the alarm (LA). The communication device may generate a notification for the user based on the second signal indicating the presence of a flame within the critical area 204. Since the flame is not critical and may be present in the critical area 204, the notification may provide the user with an instruction to take action based on the flame.

[0061] In another example implementation, when flames are detected in the highly critical area 202 and the critical area 204, a first signal and a second signal can be generated and sent to a communication device, which will be characterized in the alarm (LA) and trip alarm (HH) tables below. The communication device can generate an audible message or notification for the user based on the first signal indicating the presence of flames within the highly critical area 206. Since the detected flames in the highly critical area 202 are not expected, the audible message or notification can provide instructions for the user to take immediate action. Additionally, the communication device can generate a notification for the user based on the second signal indicating the presence of flames within the critical area 204. Since the flames are not critical and may be present in the critical area 204, the notification can provide instructions for the user to take measures based on the flames.

[0062] In another example implementation, when smoke can only be detected in the non-critical area 206, a third signal can be generated and sent to the communication device. Additionally, the communication device can generate an audible message or notification for the user indicating the presence of smoke within the non-critical area 206. Since smoke may be expected in the non-critical area 206, the audible message or notification can include information about the smoke and can provide instructions for the user not to take any action.

[0063] It is obvious that, without departing from the scope of the present disclosure, the detection of one or more areas and the execution of further processing steps can be performed by one or more processors 106 of the imaging-based flame detection system 100 using at least one image capture device 102 and one or more sensors 104.

[0064] In various implementations, the corresponding one or more areas can be any shape selected by the user using a graphical user interface (GUI) (not shown) or any other input device. The shape can include a rectangular shape, a square shape, a circular shape, a cloud-like shape, a triangular shape, or any other shape that does not conform to a typical geometric pattern. In various examples, the user can select the shape of the area based on the knowledge of the infrastructure of the environment 118. For example, if the environment 118 is an industrial oil site, the user can identify a flare tower used to process oil in one or more images in the FOV 114. When the industrial oil site is processing oil, the user also knows that fires will frequently and expectedly appear at the flare tower. Therefore, the user can draw a shape around the flare tower and then designate this area as a non-critical area because flames are expected to be present in this area.

[0065] In the implementations disclosed in the present invention, the imaging-based flame detection system 100 can employ various image processing techniques known in the art to analyze the FOV 114 of the captured one or more images.

[0066] It is obvious that the above components of the imaging-based flame detection system 100 are for illustrative purposes only. In another embodiment, without departing from the scope of the present disclosure, the imaging-based flame detection system 100 may include other components, such as a controller unit, a microprocessor unit (MPU), a microcontroller unit (MCU), etc.

[0067] Figure 4 FIG. 400 is a flowchart of a method 400 of an imaging-based flame detection system 100 according to an exemplary embodiment of the present disclosure. It is described in conjunction with Figures 1 to 3 to Figure 4 be described.

[0068] First, at step 402, the method includes capturing one or more images in a field of view (FOV) 114 via at least one image capture device 102. As discussed, each of the one or more images includes a pixel array. In some embodiments, each pixel in the pixel array is a single picture element that constitutes the visual content of the captured one or more images. For example, a dual IR camera may capture one or more images of an industrial area within the FOV 114, and each of the captured one or more images may include a pixel array that characterizes the details and information captured by the dual IR camera.

[0069] Subsequently, at step 404, the FOV 114 of the captured one or more images is analyzed via one or more sensors 104. In some embodiments, the one or more sensors 104 may include one or more infrared (IR) sensors, flame sensors, or photodiodes. The one or more sensors 104 may capture and measure thermal radiation or infrared (IR) emissions to detect flames in the captured one or more images. It should be noted that the at least one image capture device 102 and the one or more sensors 104 may be spatially calibrated to analyze flames within the FOV 114 of the captured one or more images. Additionally, the spatial calibration may ensure that each pixel in the pixel array has the same or nearly the same FOV 114. For example, after capturing one or more images of an industrial area, one or more flame sensors may detect the presence of flames within the FOV 114 by analyzing each pixel in the pixel array.

[0070] Subsequently, at step 406, one or more captured images are received via one or more processors 106. For example, the one or more processors 106 may perform tasks such as object detection or image enhancement on the captured one or more images to detect objects, track movement, or enhance image quality, so as to accurately identify flames or smoke in the captured one or more images of the industrial area.

[0071] Subsequently, at step 408, at least a portion of the pixel array is associated with a corresponding one or more zones via one or more processors 106. In an example implementation, the corresponding zones can include, for example, critical infrastructure of the environment 118. In another example implementation, the corresponding zones can include areas where a flame may be present, areas where a flame is expected to be present, areas where a flame is not critical for the area. In another example implementation, the zones can include areas where a flame is expected to be present, such as a flame necessary for the operation of the environment, such as a flare tower. Additionally, the area can include smoke. For example, in one or more captured images of an industrial area, one or more processors 106 can associate a zone with critical infrastructure present, another zone with a possible non-critical flame present, and yet another zone with an expected flame or smoke present.

[0072] Subsequently, at step 410, a corresponding one or more zones are associated with a criticality level via one or more processors 106. As previously discussed, the criticality level of each respective zone among the one or more zones can include non-critical, critical, or highly critical. For example, one or more processors 106 can associate the zone with critical infrastructure with a criticality level of highly critical, and thus can identify this zone as the highly critical zone 202. Additionally, another zone with a possible non-critical flame present can be associated with a criticality level of critical, and thus can be identified as the critical zone 204. Additionally, yet another zone with an expected flame or smoke present can be associated with a criticality level of non-critical, and thus can be identified as the non-critical zone 206.

[0073] Subsequently, at step 412, a status is determined via one or more processors 106 based at least on the analyzed FOV 114 of the one or more captured images and the criticality levels of the corresponding one or more zones. In some implementations, the status can indicate the presence of a flame or smoke in the corresponding one or more zones. Additionally, one or more processors 106 can be configured to analyze the FOV to determine the status by evaluating the pixel array of at least one image capture device and one or more sensors. For example, based on the analyzed FOV 114 of one or more captured images of an industrial area and the highly critical zone 202 of the industrial area, one or more processors 106 can detect a flame and determine a status indicating the presence of a flame in the critical infrastructure of the highly critical zone 202.

[0074] It should be understood that method 400 can be implemented by one or more implementations disclosed herein, which can be combined or modified as desired or needed. Additionally, the steps in method 400 can be modified, the order changed, performed in a different manner, performed sequentially, performed in parallel or simultaneously, or otherwise modified as desired or needed.

[0075] Figure 5 A flowchart illustrating the steps of a method 500 for generating a first signal when an unexpected flame is detected within a highly critical area 202 in accordance with an example embodiment of the present disclosure.

[0076] First, at step 502, a first signal is generated when an unexpected flame is detected within the highly critical area 202 via one or more processors 106. In some embodiments, the first signal may be generated when a flame can be detected within the highly critical area 202. For example, the first signal may trigger a series of measures such as sounding an alarm or providing a visual indication of the first signal.

[0077] Subsequently, at step 504, the first signal is sent to a communication device via one or more processors 106. As previously described, the communication device generates an audible message or notification for the user indicating the presence of an unexpected flame within the highly critical area. In some embodiments, the generated first signal may be sent to the communication device to generate an audible message or notification indicating the presence of an unexpected flame. For example, since the detected flame is not expected to be present within the highly critical area 202, the audible message or notification may provide instructions to the user to take immediate action.

[0078] Figure 6 A flowchart illustrating the steps of a method 600 for generating a second signal when a non-critical flame is detected within a critical area 204 in accordance with an example embodiment of the present disclosure.

[0079] First, at step 602, a second signal is generated when a non-critical flame is detected within the critical area 204 via one or more processors 106. In some embodiments, the second signal may be generated when a flame can be detected within the critical area 204. For example, the second signal may trigger a series of measures such as warning an emergency response team.

[0080] Subsequently, at step 604, the second signal is sent to a communication device via one or more processors 106. As previously described, the communication device generates a notification for the user indicating the presence of a non-critical flame within the critical area 204. In some embodiments, the generated second signal may be sent to the communication device to generate a notification indicating the presence of a non-critical flame. For example, since the flame is not critical and may be present within the critical area 204, the notification may provide instructions to the user to take measures based on the flame.

[0081] Figure 7 A flowchart illustrating the steps of a method 700 for generating a third signal when smoke is detected within a non-critical area 206 in accordance with an example embodiment of the present disclosure.

[0082] First, at step 702, a third signal is generated when smoke is detected in the non-critical area via one or more processors. In some embodiments, the third signal may be generated when smoke can be detected in the non-critical area 206. For example, since the detected smoke is expected to be present in the non-critical area 206, the third signal may or may not trigger a series of measures.

[0083] Subsequently, at step 704, the third signal is sent to the communication device via one or more processors. As previously described, the communication device generates an audible message or notification for the user indicating the presence of smoke in the non-critical area. In some embodiments, the generated third signal may be sent to the communication device to generate an audible message or notification indicating the presence of smoke. For example, since the smoke is expected to be present in the non-critical area 206, the audible message or notification may include information about the smoke and may provide the user with an instruction not to take any measures.

[0084] In some alternative embodiments, flames may be detected in the non-critical area 206. Additionally, the generated third signal may be sent to the communication device to generate an audible message or notification indicating the presence of flames. For example, since flames may be expected to be present in the non-critical area 206, the audible message or notification may include information about the flames and may provide the user with an instruction not to take any measures. In some embodiments, since smoke or flames are expected to be present in the non-critical area 206, an audible message or notification may not be generated and no necessary measures need to be taken.

[0085] It will be apparent to those skilled in the art that, without departing from the scope of the present disclosure, the above-described embodiments of the present invention may be performed by one or more processors 106 of the imaging-based flame detection system 100 and methods 400, 500, 600, 700 using at least one image capture device 102 and one or more sensors 104.

[0086] In some embodiments, the imaging-based flame detection system 100 may prevent false alarms from occurring within a specific field of view. Additionally, the imaging-based flame detection system 100 can automatically assign a criticality level to each of one or more areas by using AI / ML and generate one or more alarms for the user accordingly. Further, the imaging-based flame detection system 100 can accurately determine the presence of flames and / or smoke within the field of view while excluding non-critical (required) flames or smoke.

[0087] Many modifications and other embodiments of the invention set forth herein will come to mind to those skilled in the art to which this invention pertains after benefiting from the foregoing description and the teachings presented in the related drawings. Accordingly, it is to be understood that the invention 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. In addition, although the exemplary embodiments have been described herein in the context of certain exemplary 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 specifically 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 generic and descriptive sense only and not for purposes of limitation.

Claims

1. An imaging-based flame detection system, the imaging-based flame detection system comprising: at least one image capture device configured to capture one or more images in a field of view (FOV), wherein each of the one or more images comprises an array of pixels; one or more sensors communicatively coupled to the at least one image capture device configured to analyze the FOV of the captured one or more images; and one or more processors, the one or more processors being communicatively coupled to the at least one image capture device and the one or more sensors, the one or more processors being configured to: receiving one or more captured images; associating at least a portion of the pixel array with a corresponding one or more regions; associating the corresponding one or more zones with a criticality level; and A status is determined based at least on the analyzed FOV of the captured image or images and the criticality level of the corresponding region or regions.

2. The imaging-based flame detection system of claim 1, wherein: The one or more sensors are one or more infrared (IR) sensors, flame sensors or photodiodes.

3. The imaging-based flame detection system of claim 1, wherein: The criticality level of each respective zone of the one or more zones is non-critical, critical, or highly critical.

4. The imaging-based flame detection system of claim 3, wherein: The status indicates the presence of fire or smoke in the corresponding one or more zones.

5. The imaging-based flame detection system of claim 4, wherein: The non-critical zone corresponds to a zone where an expected flame exists, the critical zone corresponds to a zone where a possible non-critical flame exists, and the highly critical zone corresponds to a zone where a possible unintended flame exists.

6. The imaging-based flame detection system of claim 5, wherein: The one or more processors are configured to: generating a first signal when an unexpected flame is detected within the highly critical region; and The first signal is transmitted to a communication device, wherein the communication device generates an audible message for a user indicating the presence of the unintended flame within the highly critical zone.

7. The imaging-based flame detection system of claim 5, wherein: The one or more processors are configured to: generating a second signal when a non-critical flame is detected within the critical zone; and The second signal is transmitted to a communication device, wherein the communication device generates a notification to a user indicating the presence of the non-critical flame within the critical zone.

8. The imaging-based flame detection system of claim 4, wherein: The one or more processors are configured to: generating a third signal when the smoke is detected within the non-critical area; and The third signal is sent to a communication device, wherein the communication device generates an audible message to a user indicating the presence of smoke within the non-critical zone.

9. The imaging-based flame detection system of claim 4, wherein: The one or more processors are configured to analyze the FOV by evaluating the pixel array of the at least one image capture device and the one or more sensors to determine the status.

10. The imaging-based flame detection system of claim 4, wherein: The at least one image capture device and the one or more sensors are spatially calibrated to analyze the flame within the FOV of the captured one or more images.

Images