Method, device, apparatus, readable medium and program product for identifying flame

Abstract

The invention discloses a method, device and equipment for identifying flame, a readable medium and a program product, and belongs to the technical field of computers. The method for identifying the flame comprises the following steps: acquiring a target image frame; in response to determining that the target image is detected in the target image frame, determining a target bounding box with the target image from the target image frame; determining a target trajectory corresponding to the target bounding box; and determining a flame identification result of the target trajectory according to the position information and the time sequence information of the bounding box in the target trajectory. According to the invention, the problem of false detection in flame detection is reduced, and high-precision and high-accuracy flame detection in a monitoring scene is realized.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a method, apparatus, device, computer-readable medium, and program product for identifying flames. Background Art

[0002] To improve the accuracy of flame recognition, existing image-based flame detection algorithms typically adopt the following methods: specifically training a new classification network to distinguish between flames and false detections; using color feature models or traditional algorithms to extract the color features of the detected objects to determine whether they are flames; and using thermal imagers to locate the flame position.

[0003] However, the above methods all have various shortcomings: adding a new model will increase the time consumption during application; when using color features, when encountering objects similar to flames, it is still difficult to distinguish whether they are real flames; thermal imagers will increase equipment costs. Summary of the Invention

[0004] The content of this disclosure is used to briefly introduce concepts that will be described in detail in the detailed description section below. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] Some embodiments of the present disclosure provide a method, apparatus, device, computer-readable medium, and program product for identifying flames to at least partially solve the technical problems mentioned in the above background technology section.

[0006] In a first aspect, some embodiments of the present disclosure provide a method for identifying flames, the method comprising: acquiring a target image frame; in response to determining that a target image is detected in the target image frame, determining a target bounding box with the target image from the target image frame; determining a target trajectory corresponding to the target bounding box; and determining a flame recognition result of the target trajectory based on position information and timing information of the bounding box in the target trajectory.

[0007] In a second aspect, some embodiments of the present disclosure provide a device for identifying flames, the device comprising: an acquisition unit configured to acquire a target image frame; a first determination unit configured to determine a target bounding box with the target image from the target image frame in response to determining that a target image is detected in the target image frame; a second determination unit configured to determine a target trajectory corresponding to the target bounding box; and a third determination unit configured to determine a flame recognition result of the target trajectory based on position information and timing information of the bounding box in the target trajectory.

[0008] In a third aspect, an embodiment of the present application provides an electronic device comprising: one or more processors; a storage device for storing one or more programs; and when the one or more programs are executed by one or more processors, the one or more processors implement a method as described in any implementation method in the first aspect.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any implementation manner in the first aspect.

[0010] In a fifth aspect, some embodiments of the present disclosure provide a computer program product, including a computer program, which implements the method described in any implementation manner in the first aspect when executed by a processor.

[0011] One of the above-mentioned embodiments of the present disclosure has the following beneficial effects: analyzing the causes of false detection and flame characteristics in various scenarios, detecting flames in a time-series-based manner, and caching bounding box information of multiple frames of the detected target image. By determining the mean intersection-and-union ratio between the target bounding box in the target trajectory and other bounding boxes in the target trajectory, it is determined whether the target trajectory meets the motion characteristics of the flame, and thereby further distinguishing whether it is a static false detection or a motion false detection, thereby solving the problem of false detection in flame detection in the prior art and achieving high-precision and high-accuracy flame detection in monitoring scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0013] Figure 1 is a flow chart of some embodiments of a method for identifying a flame according to the present disclosure;

[0014] Figure 2 is a schematic structural diagram of some embodiments of a device for identifying flames according to the present disclosure;

[0015] Figure 3 It is a structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0016] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0017] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0018] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0019] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0020] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0021] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0022] refer to Figure 1 , shows a process 100 of some embodiments of a method for identifying flames according to the present disclosure. The method for identifying flames includes the following steps:

[0023] Step 101: Acquire a target image frame.

[0024] In some embodiments, an executing entity (eg, an electronic device) of the method for identifying flames may acquire a target image frame.

[0025] Here, the target image frame generally refers to an image frame that needs to be used for flame recognition. The image frame may be from a surveillance video or image, and the target image frame may be a plurality of continuous or discontinuous image frames, or a single image frame.

[0026] It should be noted that the electronic device described above can be either hardware or software. When the electronic device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the electronic device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, or as a single software or software module. No specific limitations are given here.

[0027] Step 102 : In response to determining that a target image is detected in the target image frame, a target bounding box containing the target image is determined from the target image frame.

[0028] In some embodiments, in response to determining that a target image is detected in the target image frame, the execution entity (eg, electronic device) may determine a target bounding box with the target image from the target image frame.

[0029] Specifically, the target image generally refers to an image suspected to be a flame. The execution subject may detect the target image in the target image frame in a variety of ways, which will not be described in detail here.

[0030] The target bounding box (Bbox) generally refers to the bounding box of the target image, used to indicate the location of the target. For example, the Bbox can be determined by performing an image stroke on the target image. As another example, the Bbox can be a bounding box of a predetermined shape encompassing the target image.

[0031] In some optional implementations of some embodiments, the above-mentioned target image frame uses a pre-trained flame detection model to detect whether the target image exists in the above-mentioned target image frame, wherein the above-mentioned flame detection model is obtained by training the above-mentioned initial model with the yolov5 model as the initial model, the sample target image frame as the input of the above-mentioned initial model, and the sample detection result corresponding to the sample target image frame as the expected output of the above-mentioned initial model.

[0032] Step 103: Determine the target trajectory corresponding to the target bounding box.

[0033] In some embodiments, the execution entity may determine a target trajectory corresponding to the target bounding box.

[0034] Specifically, the target trajectory generally refers to a motion trajectory of the target image. As an example, the trajectory may refer to a position change trajectory of the target image in different image frames.

[0035] In some optional implementations of some embodiments, the execution entity may match the target bounding box with a track in a track set; in response to determining that the target bounding box does not match a track in the track set, generate a target track based on the target bounding box; in response to determining that a corresponding track matching the target bounding box exists in the track set, add the target bounding box to the corresponding track and use the corresponding track as the target track.

[0036] Here, the trajectories in the above trajectory set can be preset trajectories or trajectories generated by historical target image bounding boxes.

[0037] The above trajectory generally refers to: in a video sequence, all detection results of an object in consecutive video frames can be considered as the object's trajectory in the video sequence. An object appears from frame ti to frame t, and the Bbox of the object's position in each of these i frames is known. Combining these results is the object's trajectory from frame ti to frame t. All Bboxes in the trajectory represent historical information. Here, the above target generally refers to the target image for which the trajectory is to be determined.

[0038] In some optional implementations of some embodiments, a distance intersection-and-union (IoU) matrix between the trajectory set and the target bounding box is determined; rows and columns in the distance intersection-and-union (IoU) matrix are matched to obtain a first matching result; the distance intersection-and-union matrix is ​​matrix-transposed to obtain a transposed distance intersection-and-union (IoU) matrix, and rows and columns in the transposed distance intersection-and-union (IoU) matrix are matched to obtain a second matching result; in response to determining that the first matching result and the second matching result are the same matching trajectory in the trajectory set that matches the target bounding box, the matching trajectory is determined to be the corresponding trajectory of the target bounding box.

[0039] Specifically, the method used to match the target bounding box and the trajectory is to calculate the distance intersection over union (DIOU) between the trajectory and the target bounding box. If the calculated DIOU value is greater than the preset matching threshold MATCH_IOU_THR, the target bounding box and the trajectory are considered to match, otherwise they are considered not to match.

[0040] Here, the above distance intersection-over-union ratio DIOU refers to the intersection-over-union ratio (IoU) with distance, which represents the ratio of the intersection to the union of two bounding boxes. The larger the value of the IoU, the higher the degree of overlap of the two bounding boxes.

[0041] Specifically, since there can be one or more target bounding boxes, and there can also be one or more tracks in the track set that match the target bounding box, when calculating the distance intersection and union ratio matrix, the target bounding box can be used as the row of the distance intersection and union ratio matrix, and the track can be used as the column of the distance intersection and union ratio. The distance intersection and union ratio of the target bounding box and the track is determined to form the value in the distance intersection and union ratio matrix.

[0042] In order to match more accurately, the rows of the distance intersection and union ratio matrix represent the target bounding box in the first calculation, and the columns represent the tracks in the track set. Each bounding box can match one track, but a track can match multiple bounding boxes. Therefore, the calculated distance intersection and union ratio matrix is ​​transposed in the second calculation, and the rows represent the tracks in the track set, and the columns represent the target bounding box. Each track matches one bounding box, and each bounding box can match multiple tracks. Only tracks and bounding boxes that can be correctly matched together twice are considered to be correctly matched, and the rest are considered to have failed matches.

[0043] As an example, the above-mentioned target bounding boxes can be target bounding boxes b1, target bounding boxes b2 and target bounding boxes b3, and the tracks matched with the target bounding boxes can be tracks t1 and tracks t2. The distance intersection and union ratio of the target bounding box b1 and track t1 is diou1, the distance intersection and union ratio of the target bounding box b1 and track t2 is diou4, the distance intersection and union ratio of the target bounding box b2 and track t1 is diou2, the distance intersection and union ratio of the target bounding box b2 and track t2 is diou5, the distance intersection and union ratio of the target bounding box b3 and track t1 is diou3, and the distance intersection and union ratio of the target bounding box b3 and track t2 is diou6. The distance intersection and union ratio matrix obtained by the first calculation is: Afterwards, the distance intersection-and-union ratio matrix obtained by the first calculation can be transposed to obtain the transposed distance intersection-and-union ratio matrix: The results of both matches are that the target bounding box b3 and the trajectory t2 are matched successfully, so the trajectory t2 is the corresponding trajectory of the target bounding box b3.

[0044] In this process, if there are fast-moving false detection tracks, they can also be filtered out because the fast-moving false detection tracks cannot match the target bounding box.

[0045] DIoU can consider the overlap, distance, and scale information between two bounding boxes to more accurately match targets and trajectories; the formula is as follows:

[0046]

[0047] Among them, IoU is the intersection-over-union ratio of bounding box box1 and bounding box box2, d = ρ 2(b1, b2) represents the distance between the center point b1 of the bounding box box1 and the center point b2 of the bounding box box2, which is determined by the Euclidean distance; C represents the length of the diagonal of the minimum circumscribed rectangle of the two boxes.

[0048] Step 104 : determining a flame recognition result of the target trajectory according to the position information and time sequence information of the bounding box in the target trajectory.

[0049] In some embodiments, the execution entity may determine the flame recognition result of the target trajectory based on the position information and timing information of the bounding box in the target trajectory.

[0050] Here, the flame recognition result generally refers to whether the target image is a flame.

[0051] In some optional implementations of some embodiments, the execution entity may determine the intersection-and-union (IoU) of the target bounding box in the target trajectory and other bounding boxes in the target trajectory based on the position information and timing information of the bounding box in the target trajectory to obtain an IoU set; determine an IoU mean in the IoU set; in response to determining that the IoU mean exceeds a maximum value of a preset interval, determine the flame recognition result of the target trajectory as a static false detection; in response to determining that the IoU mean is lower than a minimum value of a preset interval, determine the flame recognition result of the target trajectory as a motion false detection; in response to determining that the IoU mean is within the preset interval, determine the flame recognition result of the target trajectory as a detected flame.

[0052] As an example, the above execution entity can determine whether the target is a flame by following the steps below:

[0053] Step 1: Determine a target bounding box with a target image from a target image frame;

[0054] Step 2: Determine the trajectory corresponding to the target bounding box:

[0055] Match the target trajectory corresponding to the target bounding box by the intersection of the target bounding box and the trajectory;

[0056] If the corresponding target track is matched, the target bounding box is updated to the target track;

[0057] If no target track is matched, the target bounding box is used as the first frame in the track to generate the target track (the target track includes at least two bounding boxes, so the subsequent steps are started after the next frame of the target image is included in the target track);

[0058] Step 3: Determine the flame recognition result of the target trajectory by the intersection and union ratio of the target bounding box and other bounding boxes in the target trajectory.

[0059] According to the characteristics of false flame detection and the characteristics of flames, it is found that burning flames are basically in a jumping state, some false detections are basically stationary, and some false detections move faster than the jumping of flames. Therefore, the intersection over union (IoU) is calculated using the bounding box of the last frame (the target bounding box) and the bounding boxes of all previous frames, and the mean value of the IoU (IoU_mean) is obtained after subtracting the maximum and minimum values. If IoU_mean is greater than the set DET_IOU_THR_MAX (the maximum value of the preset interval), it is considered a basically stationary target, that is, a false detection. If IoU_mean is less than the set DET_IOU_THR_MIN (the minimum value of the preset interval), it is considered a fast-moving false detection. Only the trajectories with DET_IOU_THR_MIN < IoU_mean < DET_IOU_THR_MAX (the IoU_mean is within the preset interval) will be considered as flames. Specifically, the number of cached bounding boxes in the trajectory is set to CACHE_LEN. If the number of cached bounding boxes in the trajectory is less than CACHE_LEN, the mean value will be calculated based on the actual number of cached bounding boxes to determine the flame recognition result. If there are only two cached bounding boxes, the IoU between the two bounding boxes is used to determine the flame recognition result. If there is only one cached bounding box, the IoU_mean will not be calculated.

[0060] Specifically, if the target bounding box does not match the corresponding trajectory, a trajectory is generated with the target bounding box as the first frame. If subsequent bounding boxes match this trajectory, the subsequent process continues. If no bounding box matches this trajectory after a preset number of frames, the trajectory is deleted. In some optional implementation manners of some embodiments, in response to determining that the flame recognition result of the above target trajectory is that a flame is detected, the above execution entity may send the last frame image in the above target trajectory and the above flame recognition result to the target device.

[0061] Specifically, the above target device may be a preset device that needs to give an early warning.

[0062] One embodiment of the above various embodiments of the present disclosure has the following beneficial effects: Analyze the reasons for false detections and the characteristics of flames in various scenarios, adopt a time-series-based method to detect flames, and cache the bounding box information of multiple frames for the detected targets. By determining the IoU_mean between the last bounding box of each trajectory and all previous cached bounding boxes, it is judged whether it conforms to the motion characteristics of flames, so as to screen out false detections with too fast moving speeds through the matching between the target and the trajectory; Calculate the IoU_mean through the cached bounding boxes in the trajectory to judge whether it conforms to the motion characteristics of flames to further distinguish static false detections or motion false detections, so as to solve the problem of false detections in flame detection in the prior art and achieve high-precision and high-accuracy flame detection in the monitoring scenario.

[0063] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a device for identifying flames. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0064] like Figure 2 As shown, some embodiments of the apparatus 200 for identifying flames include: an acquisition unit 201, a first determination unit 202, a second determination unit 203, and a third determination unit 204. The acquisition unit 201 is configured to acquire a target image frame; the first determination unit 202 is configured to, in response to determining that a target image is detected in the target image frame, determine a target bounding box containing the target image from the target image frame; the second determination unit 203 is configured to determine a target trajectory corresponding to the target bounding box; and the third determination unit 204 is configured to determine a flame recognition result for the target trajectory based on position information and timing information of the bounding box in the target trajectory.

[0065] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units included therein, and will not be repeated here.

[0066] One of the above-mentioned embodiments of the present disclosure has the following beneficial effects: analyzing the causes of false detection and flame characteristics in various scenarios, detecting flames in a time-series-based manner, and caching box information of the detected target in multiple frames. By determining the iou_mean between the last box of each trajectory and all previously cached boxes, it is determined whether it meets the motion characteristics of the flame, thereby filtering out false detections caused by excessive movement speed by matching the target and the trajectory; by calculating the iou_mean of the boxes cached in the trajectory, it is determined whether it meets the motion characteristics of the flame to further distinguish whether it is a static false detection or a motion false detection, thereby solving the problem of false detection in flame detection in the prior art and achieving high-precision and high-accuracy flame detection in monitoring scenarios.

[0067] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure (for example, an electronic device that executes the method for identifying flames). Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0068] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. Various programs and data required for the operation of the electronic device 300 are also stored in the RAM 303. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0069] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0070] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network via the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are performed.

[0071] It should be noted that the computer-readable medium described above in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0072] In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Furthermore, in some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.

[0073] A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0074] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0075] The computer-readable medium may be included in the electronic device, or may exist independently and not incorporated into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire a target image frame; in response to determining that a target image is detected in the target image frame, determine a target bounding box containing the target image from the target image frame; determine a target trajectory corresponding to the target bounding box; and determine a flame recognition result for the target trajectory based on the position information and timing information of the bounding box in the target trajectory.

[0076] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0077] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0078] The units described in some embodiments of the present disclosure may be implemented in software or hardware. The units described may also be provided in a processor. For example, they may be described as follows: a processor includes an acquisition unit, a first determination unit, a second determination unit, and a third determination unit. The names of these units do not, in some cases, limit the units themselves. For example, the acquisition unit may also be described as a "unit for acquiring a target image frame."

[0079] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0080] Some embodiments of the present disclosure further provide a computer program product, including a computer program, which implements any of the above methods for identifying flames when executed by a processor.

[0081] The above description is only an illustration of some preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for identifying a flame, comprising: Get the target image frame; In response to determining that a target image is detected in the target image frame, determining a target bounding box with the target image from the target image frame; Determining a target trajectory corresponding to the target bounding box; A flame recognition result of the target trajectory is determined according to the position information and the timing information of the bounding box in the target trajectory.

2. The method according to claim 1, wherein Determining the target trajectory corresponding to the target bounding box includes: Matching the target bounding box with the tracklets in the tracklet set; In response to determining that there is a corresponding track in the track set that matches the target bounding box, the target bounding box is added to the corresponding track and the corresponding track is used as the target track.

3. The method according to claim 2, wherein: Matching the target bounding box with the track in the track set includes: Determining a distance intersection-over-union matrix between the trajectories in the trajectory set and the target bounding box; Matching the rows and columns in the distance intersection and union ratio matrix to obtain a first matching result; Performing a matrix transposition on the distance intersection-and-union ratio matrix to obtain a transposed distance intersection-and-union ratio matrix, and matching rows and columns in the transposed distance intersection-and-union ratio matrix to obtain a second matching result; In response to determining that the first matching result and the second matching result are tracks in the track set that match the target bounding box are the same matching track, the matching track is determined to be a corresponding track of the target bounding box.

4. The method according to claim 1, wherein The target trajectory includes at least two bounding boxes, and determining the flame recognition result of the target trajectory according to the position information and timing information of the bounding boxes in the target trajectory includes: determining, based on position information and timing information of the bounding box in the target trajectory, an intersection-and-union ratio (IOR) of the target bounding box in the target trajectory and other bounding boxes in the target trajectory to obtain an IOR set; Determining a mean of the intersection-and-union ratios in the intersection-and-union ratio set; In response to determining that the mean of the intersection-over-union ratio exceeds a maximum value of a preset interval, determining the flame recognition result of the target trajectory as a static false detection; In response to determining that the mean of the intersection-over-union ratio is lower than a minimum value of a preset interval, determining the flame recognition result of the target trajectory as a motion false detection; In response to determining that the mean of the intersection-over-union ratio is within the preset interval, the flame recognition result of the target trajectory is determined as flame detection.

5. The method according to claim 1, wherein The target image frame is detected by using a pre-trained flame detection model to determine whether a target image exists in the target image frame, wherein the flame detection model is obtained by training the initial model using the yolov5 model as the initial model, the sample target image frame as the input of the initial model, and the sample detection result corresponding to the sample target image frame as the expected output of the initial model.

6. The method according to claim 1, wherein The method further comprises: In response to determining that the flame recognition result of the target trajectory is flame detection, the last frame image in the target trajectory and the flame recognition result are sent to the target device.

7. A device for identifying flames, comprising: an acquisition unit configured to acquire a target image frame; a first determining unit configured to determine, in response to determining that a target image is detected in the target image frame, a target bounding box with the target image from the target image frame; a second determining unit, configured to determine a target trajectory corresponding to the target bounding box; The third determining unit is configured to determine a flame recognition result of the target trajectory according to the position information and the time sequence information of the bounding box in the target trajectory.

8. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to implement the method for identifying flames according to any one of claims 1 to 6.

9. A computer-readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method for identifying flames according to any one of claims 1 to 6 can be implemented.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program is capable of implementing the method for identifying flames according to any one of claims 1 to 6.

Images