Target trajectory correlation processing method and device applied to infrared search equipment
By using the sliding window and critical region association method, the problem of high complexity in target detection and tracking algorithms in infrared search equipment is solved, and efficient target trajectory association processing is achieved, improving the utilization rate and hit rate of target information.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING INST OF ENVIRONMENTAL FEATURES
- Filing Date
- 2024-01-04
- Publication Date
- 2026-06-12
AI Technical Summary
Infrared search equipment has high algorithm complexity in target detection and tracking, which cannot meet the needs of application scenarios, especially due to the low update frequency, few morphological features, and a large number of targets in the area of interest, which leads to a geometric increase in complexity.
A sliding window processing and critical region association method is adopted. Duplicate targets are eliminated through IOU processing. Multiple frames of image information are stored within the sliding window. The target trajectory association is combined with the Hungarian algorithm to improve the utilization rate of target information in the feature domain and the hit rate in the time domain.
It improves the accuracy and detection efficiency of target trajectories, reduces algorithm complexity, and achieves efficient target trajectory association processing for infrared search devices.
Smart Images
Figure CN117853528B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of target detection technology, and in particular to a target trajectory association processing method and apparatus applied to infrared search equipment. Background Technology
[0002] Infrared search and track equipment (ISS) is based on staring-field infrared (SNIR) and generates continuous circumferential images using specific optical imaging techniques through rapid, continuous servo scanning. Targets detected by ISS are characterized by low update frequency, few morphological features, and a large number of targets within the area of interest.
[0003] Based on the above characteristics, the complexity of the algorithm increases exponentially when performing target detection and tracking, making it unable to meet the application requirements of the scenario.
[0004] Therefore, there is an urgent need for a target trajectory association processing method and device applied to infrared search equipment to solve the above-mentioned technical problems. Summary of the Invention
[0005] This invention provides a target trajectory association processing method and apparatus for use on infrared search devices, which can accurately determine the target trajectory based on image data acquired by the infrared search device.
[0006] In a first aspect, embodiments of the present invention provide a target trajectory association processing method applied to an infrared search device, comprising:
[0007] In response to the infrared search device performing a circumferential scan of the target area, the following is executed for each scan cycle:
[0008] S1, perform IOU processing on the current original image acquired by the infrared search device to remove duplicate targets in the current original image, obtain the current first image, and then execute S2;
[0009] S2, compare the current first image with the current sliding window, remove the targets that overlap with the current first image in the current sliding window based on the comparison result, and add the target information in the current first image to the sliding window that has removed the overlapping targets to obtain a new sliding window, and then execute S3; the current sliding window stores the target information of multiple frames of first images, and the multiple frames of first images are the first images that are continuous with the current first image and precede the current first image;
[0010] S3, determine whether the angle of the area covered by the new sliding window is greater than the preset angle; if not, continue to execute S3; if yes, take the left boundary angle of the new sliding window as the starting point, extract the target data within the preset area, remove the extracted target data from the new sliding window, and execute S4.
[0011] S4. The retrieved target data is correlated with the established current target track in the critical region to obtain a new target track.
[0012] Repeat steps S1 to S4 until the infrared search device has scanned the target area once, and obtain the target trajectory of the current scan.
[0013] Secondly, embodiments of the present invention also provide a target trajectory association processing apparatus applied to an infrared search device, comprising:
[0014] The IOU processing module is used to perform IOU processing on the current original image acquired by the infrared search device to remove duplicate targets in the current original image and obtain the current first image.
[0015] The filtering module is used to compare the current first image with the current sliding window, remove targets that overlap with the current first image in the current sliding window based on the comparison result, and add the target information in the current first image to the sliding window that has been removed of overlapping targets to obtain a new sliding window; the current sliding window stores target information of multiple frames of first images, and the multiple frames of first images are first images that are continuous with the current first image and precede the current first image;
[0016] The judgment module is used to determine whether the angle of the area covered by the new sliding window is greater than a preset angle; if not, the filtering module continues to be executed; if so, the target data within the preset area is extracted starting from the left boundary angle of the new sliding window, and the extracted target data is removed from the new sliding window.
[0017] The critical region association module is used to associate the retrieved target data with the established current target track in the critical region to obtain a new target track.
[0018] Thirdly, embodiments of the present invention also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the method described in any embodiment of this specification.
[0019] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the methods described in any embodiment of this specification.
[0020] This invention provides a target trajectory association processing method and apparatus applied to infrared search equipment. Through sliding window processing, the confidence level of target information in the feature domain is improved, while erroneous information in the time domain is removed. Through critical region association, the utilization rate of target information in the feature domain is improved, while the range of target information in the time domain is reduced, thereby increasing the hit rate. Therefore, this application can accurately determine the target trajectory based on image data acquired by the infrared search equipment. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This is a flowchart of a target trajectory association processing method applied to an infrared search device, provided by an embodiment of the present invention;
[0023] Figure 2 This is a hardware architecture diagram of an electronic device provided in an embodiment of the present invention;
[0024] Figure 3 This is a structural diagram of a target trajectory association processing device applied to an infrared search device, provided by an embodiment of the present invention. Detailed Implementation
[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.
[0026] Please refer to Figure 1 This invention provides a target trajectory association processing method applied to infrared search equipment, comprising:
[0027] In response to the infrared search device performing a circumferential scan of the target area, the following is executed for each scan cycle:
[0028] S1, perform IOU processing on the current original image acquired by the infrared search device to remove duplicate targets in the current original image, obtain the current first image, and then execute S2;
[0029] S2, compare the current first image with the current sliding window, remove the targets that overlap with the current first image in the current sliding window based on the comparison result, and add the target information in the current first image to the sliding window that has removed the overlapping targets to obtain a new sliding window, and then execute S3; the current sliding window stores the target information of multiple frames of first images, and the multiple frames of first images are the first images that are continuous with the current first image and precede the current first image;
[0030] S3, determine whether the angle of the area covered by the new sliding window is greater than the preset angle; if not, continue to execute S3; if yes, take the left boundary angle of the new sliding window as the starting point, extract the target data within the preset area, remove the extracted target data from the new sliding window, and execute S4.
[0031] S4. The retrieved target data is correlated with the established current target track in the critical region to obtain a new target track.
[0032] Repeat steps S1 to S4 until the infrared search device has scanned the target area once, and obtain the target trajectory of the current scan.
[0033] In this embodiment, by using a sliding window, the confidence level of target information in the feature domain is improved, while erroneous information in the time domain is removed. Through critical region association, the utilization rate of target information in the feature domain is improved, while the range of target information in the time domain is reduced, thereby increasing the hit rate. Therefore, this application can accurately determine the target trajectory based on image data acquired by an infrared search device.
[0034] It should be noted that each scan circle is 360°, meaning that the infrared images obtained by the infrared search device after each scan can be stitched together to form a 360° circular image.
[0035] The following description Figure 1 The execution method for each step is shown.
[0036] First, in step S1, the current original image acquired by the infrared search device is subjected to IOU processing to remove duplicate targets in the current original image and obtain the current first image.
[0037] In this step, to meet the algorithm's requirements, the target information data in the original image needs to be processed. If there is a possibility of overlapping targets, for example, one target in the original image is an airplane, but because the temperature at the wing is different from other parts, the wing is considered another target, then the airplane and the wing are duplicate targets. This step, by performing IOU processing on the original image, can ensure the uniqueness of the target. In addition, the processed target needs to have the following field information: the target's spatial azimuth angle, the target's spatial pitch angle, the frame number of the target's source image, the target's pixel width, the target's pixel height, and the target's relative brightness. The above target information can form a target description, denoted as (f, a, e, w, h, l).
[0038] The spatial azimuth of the target (a): with true north as the azimuth of 0°, it increases clockwise;
[0039] The target's pitch angle (e): with the horizontal direction as the position of 0° pitch angle, upward is a positive value that increases, and downward is a negative value that decreases;
[0040] Frame number (f) of the target source image: This identifies the image from which the monitored target comes, and has a uniqueness that lasts for one cycle.
[0041] Target pixel width (w): morphological feature of the target, identifying the number of pixels that the target is imaged in the width direction of the image;
[0042] Target pixel height (h): Target morphological feature, identifying the number of pixels of the target image in the height direction;
[0043] Relative brightness of the target (l): The difference between the average brightness of the target and the average brightness of the non-target area within a region centered on the target and with a length and width equal to the target's own.
[0044] Then, for step S2, the current first image is compared with the current sliding window. Based on the comparison result, the targets that overlap with the current first image in the current sliding window are removed, and the target information in the current first image is added to the sliding window that has removed the overlapping targets to obtain a new sliding window. Then, S3 is executed. The current sliding window stores the target information of multiple frames of first images. The multiple frames of first images are the first images that are continuous with the current first image and precede the current first image.
[0045] Based on the imaging characteristics of infrared search equipment, for a single frame image, the multiple target information obtained after processing it must be different targets; however, for consecutive images, there are overlapping areas, so the same target may be detected continuously. This embodiment can remove overlapping areas by designing a sliding window.
[0046] It should be noted that the maximum size of the sliding window is nR. p ;R p R represents the coverage area corresponding to a single first image; n is the number of first images; in this invention, n of the sliding window is 3, and R p The angle is 2.2°, and the sliding window describes the target in the three frames that are closest to the current first image.
[0047] In some implementations, comparing the current first image with the current sliding window, and removing targets in the current sliding window that overlap with the current first image based on the comparison result, includes:
[0048] For each target in the current first image, perform the following:
[0049] Determine whether the spatial angular distance between the target and each target in the current sliding window is less than the angular distance threshold;
[0050] If yes, the two targets are considered to be the same target, and the target corresponding to that target in the current sliding window is removed from the current sliding window; otherwise, no action is taken.
[0051] In some implementations, determining whether the spatial angular distance between the target and each target in the current sliding window is less than an angular distance threshold is calculated using the following formula:
[0052] d < d max |t old ∈∑ old , t c ∈∑ c
[0053] In the formula, d is the spatial angular distance between the two targets; ∑ old The set of target information in the current sliding window; ∑ c t is the set of target information in the current first image; old For belonging to ∑ old Target information; t c For belonging to ∑ c Target information; d max The angular distance threshold is the maximum allowed spatial angular distance between two targets when they are the same target. In this invention, the angular distance threshold d... max Take 0.01°.
[0054] Through the above steps, when t is considered old and t c When the targets are the same, filtering can be performed to retain only one target's information. In this invention, because the spatial mapping of the infrared imaging has been overcalibrated, the spatial angle confidence of the target is high; therefore, only the most recent target description is retained.c , will ∑ old Delete the corresponding target from ∑. c Add to ∑ old In the middle, a new sliding window is formed, denoted as ∑ new This will be used as the current sliding window for the next sliding window filtering.
[0055] Next, regarding step S3:
[0056] The preset angle is the sum of the angle coverage area corresponding to a single first image and the preset region range, and the preset region range is determined based on the velocity threshold of the target to be detected.
[0057] Let the preset angle be R. p +R a , where R p R represents the angular coverage area corresponding to a single first image. a The preset region range refers to the sample region range selected for critical region association. In this invention, the preset region range is 3.6°, meaning that updating one lap of data requires 100 critical region association processes. In the new sliding window ∑ new In the middle, starting from the left boundary angle, extract the coverage R. a The target information data is denoted as ∑ O Then remove it from the sliding window. After removal, the remaining angle range of the sliding window will decrease. The sum of the remaining angle range and the angle range corresponding to the first image added after the next sliding window filtering will be used as the angle of the area covered by the sliding window in the next S3.
[0058] Finally, for step S4, the retrieved target data is correlated with the established current target track in a critical region to obtain a new target track, including:
[0059] Let the set of extracted target data be denoted as ∑ O The established current target track is denoted as ∑ T , t o For belonging to ∑ O The goal, t t For belonging to ∑ T The goal;
[0060] Calculate each t o With each t t The cosine distance between them;
[0061] Based on each calculated cosine distance, the Hungarian algorithm is used to process ∑ O and ∑ T Perform matching to obtain successfully matched targets and unmatched targets;
[0062] For a successfully matched target, update its target information to ∑ T In the related terms, and ∑ T The data in the table is marked as updated, and ∑ is updated accordingly. T The motion characteristics; for targets that are not successfully matched, their target information is added as new targets to ∑. T In the process, a new target trajectory was obtained.
[0063] In this step, the motion features include: changes in velocity and direction in the spatial domain, and changes in the size and brightness of the feature domain.
[0064] Through steps S1-S4, after each loop, the infrared search device scans the target area once, and the aforementioned processing is performed on the infrared images of that loop, thus obtaining the target trajectory for the current scan loop. For target data in the current target trajectory that has not been marked for updating, its motion characteristics are used to predict the target's spatial domain and feature domain, providing more reliable information for the next processing. If a target is not marked as an associated target for three consecutive loops, it is considered to have disappeared and does not need to be maintained; it can be removed from the target maintenance information.
[0065] It should be noted that since each pairing is calculated using the target description, i.e. (a, e, w, h, l), each feature is normalized before use to ensure that the influencing factors of each feature are the same, so as to ensure that the weights are consistent during the calculation.
[0066] like Figure 2 , Figure 3 As shown, this embodiment of the invention provides a target trajectory association processing device applied to infrared search equipment. The device embodiment can be implemented through software, hardware, or a combination of both. From a hardware perspective, as... Figure 2 The diagram shown is a hardware architecture diagram of an electronic device for a target trajectory association processing device applied to an infrared search device, provided by an embodiment of the present invention. Except for... Figure 2 In addition to the processor, memory, network interface, and non-volatile memory shown, the electronic device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing packets. Taking software implementation as an example, such as... Figure 3 As shown, as a logical device, it is formed by the CPU of its electronic device reading the corresponding computer program from the non-volatile memory into memory and running it. This embodiment provides a target trajectory association processing device applied to infrared search equipment, comprising:
[0067] The IOU processing module 300 is used to perform IOU processing on the current original image acquired by the infrared search device to remove duplicate targets in the current original image and obtain the current first image.
[0068] The filtering module 302 is used to compare the current first image with the current sliding window, remove targets that overlap with the current first image in the current sliding window based on the comparison result, and add the target information in the current first image to the sliding window that has removed the overlapping targets to obtain a new sliding window; the current sliding window stores target information of multiple frames of first images, and the multiple frames of first images are first images that are continuous with the current first image and precede the current first image;
[0069] The judgment module 304 is used to determine whether the angle of the area covered by the new sliding window is greater than a preset angle; if not, the filtering module continues to be executed; if so, the target data within the preset area is extracted starting from the left boundary angle of the new sliding window, and the extracted target data is removed from the new sliding window.
[0070] The critical region association module 306 is used to associate the retrieved target data with the established current target track in a critical region to obtain a new target track.
[0071] In some implementations, the target information includes:
[0072] The target's spatial azimuth, spatial pitch, frame number of the source image, pixel width, pixel height, and relative brightness.
[0073] In some implementations, when the filtering module 302 compares the current first image with the current sliding window and removes targets in the current sliding window that overlap with the current first image based on the comparison result, it performs the following operations:
[0074] For each target in the current first image, perform the following:
[0075] Determine whether the spatial angular distance between the target and each target in the current sliding window is less than the angular distance threshold;
[0076] If yes, the two targets are considered to be the same target, and the target corresponding to that target in the current sliding window is removed from the current sliding window; otherwise, no action is taken.
[0077] In some implementations, determining whether the spatial angular distance between the target and each target in the current sliding window is less than an angular distance threshold is calculated using the following formula:
[0078] d < d max |told ∈∑ old , t c ∈∑ c
[0079] In the formula, d is the spatial angular distance between the two targets; ∑ old The set of target information in the current sliding window; ∑ c t is the set of target information in the current first image; old For belonging to ∑ old Target information; t c For belonging to ∑ c Target information; d max The angular distance threshold is the maximum allowed spatial angular distance between two targets when they are the same target.
[0080] In some implementations, the preset angle is the sum of the angle coverage area corresponding to a single first image and the preset region range, wherein the preset region range is determined based on the velocity threshold of the target to be detected.
[0081] In some implementations, the critical region association module 306 is used to perform the following operations:
[0082] Let the set of extracted target data be denoted as ∑ O The established current target track is denoted as ∑ T , t o For belonging to ∑ O The goal, t t For belonging to ∑ T The goal;
[0083] Calculate each t o With each t t The cosine distance between them;
[0084] Based on each calculated cosine distance, the Hungarian algorithm is used to process ∑ O and ∑ T Perform matching to obtain successfully matched targets and unmatched targets;
[0085] For a successfully matched target, update its target information to ∑ T In the related terms, and ∑ T The data in the table is marked as updated, and ∑ is updated accordingly. T The motion characteristics; for targets that are not successfully matched, their target information is added as new targets to ∑. T In the process, a new target trajectory was obtained.
[0086] The motion characteristics include: changes in velocity and direction in the spatial domain, and changes in the size and brightness of the characteristic domain.
[0087] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on a target trajectory association processing device applied to an infrared search device. In other embodiments of the present invention, a target trajectory association processing device applied to an infrared search device may include more or fewer components than illustrated, or combine some components, or split some components, or arrange different components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
[0088] The information interaction and execution process between the modules in the above-mentioned device are based on the same concept as the method embodiment of the present invention, and the specific details can be found in the description of the method embodiment of the present invention, and will not be repeated here.
[0089] This invention also provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a target trajectory association processing method applied to an infrared search device according to any embodiment of this invention.
[0090] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program causes the processor to perform a target trajectory association processing method applied to an infrared search device according to any embodiment of this invention.
[0091] Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer (or CPU or MPU) of the system or apparatus may read and execute the program code stored in the storage medium.
[0092] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.
[0093] Examples of storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.
[0094] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.
[0095] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion module connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion module execute some and all of the actual operations, thereby realizing the function of any of the above embodiments.
[0096] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0097] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.
[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A target trajectory association processing method applied to infrared search equipment, characterized in that, include: In response to the infrared search device performing a circumferential scan of the target area, the following is executed for each scan cycle: S1, perform IOU processing on the current original image acquired by the infrared search device to remove duplicate targets in the current original image, obtain the current first image, and then execute S2; S2, compare the current first image with the current sliding window, remove the targets that overlap with the current first image in the current sliding window based on the comparison result, and add the target information in the current first image to the sliding window that has removed the overlapping targets to obtain a new sliding window, and then execute S3; the current sliding window stores the target information of multiple frames of first images, and the multiple frames of first images are the first images that are continuous with the current first image and precede the current first image; S3, determine whether the angle of the area covered by the new sliding window is greater than the preset angle; if not, continue to execute S3; if yes, take the left boundary angle of the new sliding window as the starting point, extract the target data within the preset area, remove the extracted target data from the new sliding window, and execute S4. S4. The retrieved target data is correlated with the established current target track in the critical region to obtain a new target track. Repeat steps S1 to S4 until the infrared search device has scanned the target area once, and obtain the target trajectory of the current scan.
2. The method according to claim 1, characterized in that, The target information includes: The target's spatial azimuth, spatial pitch, frame number of the source image, pixel width, pixel height, and relative brightness.
3. The method according to claim 1, characterized in that, The step of comparing the current first image with the current sliding window, and removing targets in the current sliding window that overlap with the current first image based on the comparison result, includes: For each target in the current first image, perform the following: Determine whether the spatial angular distance between the target and each target in the current sliding window is less than the angular distance threshold; If yes, the two targets are considered to be the same target, and the target corresponding to that target in the current sliding window is removed from the current sliding window; otherwise, no action is taken.
4. The method according to claim 3, characterized in that, The determination of whether the spatial angular distance between the target and each target in the current sliding window is less than the angular distance threshold is calculated using the following formula: d < d max |t old ∈∑ old ,t c ∈∑ c where d is the spatial angular distance of two targets; ∑ old is the set of target information in the current sliding window; ∑ c is the set of target information in the current first image; t old For belonging to ∑ old Target information; t c For belonging to ∑ c Target information; d max The angular distance threshold is the maximum allowed spatial angular distance between two targets when they are the same target.
5. The method according to claim 1, characterized in that, The preset angle is the sum of the angle coverage area corresponding to a single first image and the preset region range, and the preset region range is determined based on the velocity threshold of the target to be detected.
6. The method according to claim 1, characterized in that, The step of associating the retrieved target data with the established current target track within a critical region to obtain a new target track includes: Let the set of extracted target data be denoted as ∑ O The established current target track is denoted as ∑ T , t o For belonging to ∑ O The goal, t t For belonging to ∑ T The goal; Calculate each t o With each t t The cosine distance between them; Based on each calculated cosine distance, the Hungarian algorithm is used to process ∑ O and ∑ T Perform matching to obtain successfully matched targets and unmatched targets; For a successfully matched target, update its target information to ∑ T In the related terms, and ∑ T The data in the table is marked as updated, and ∑ is updated accordingly. T The motion characteristics; for targets that are not successfully matched, their target information is added as new targets to ∑. T In the process, a new target trajectory was obtained.
7. The method according to claim 6, characterized in that, The motion characteristics include: Changes in velocity and direction in the spatial domain, and variations in size and brightness in the characteristic domain.
8. A target trajectory association processing device applied to infrared search equipment, characterized in that, include: The IOU processing module is used to perform IOU processing on the current original image acquired by the infrared search device to remove duplicate targets in the current original image and obtain the current first image. The filtering module is used to compare the current first image with the current sliding window, remove targets that overlap with the current first image in the current sliding window based on the comparison result, and add the target information in the current first image to the sliding window that has been removed of overlapping targets to obtain a new sliding window; the current sliding window stores target information of multiple frames of first images, and the multiple frames of first images are first images that are continuous with the current first image and precede the current first image; The judgment module is used to determine whether the angle of the area covered by the new sliding window is greater than a preset angle; if not, the filtering module continues to be executed; if so, the target data within the preset area is extracted starting from the left boundary angle of the new sliding window, and the extracted target data is removed from the new sliding window. The critical region association module is used to associate the retrieved target data with the established current target track in the critical region to obtain a new target track.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-7.
10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed in the computer, it causes the computer to perform the method of any one of claims 1-7.