A target recognition and tracking method, device, equipment and storage medium

Abstract

The application discloses a target identification and tracking method, device and equipment and a storage medium, and is applied to a radar-optical linkage system. The method comprises the following steps: determining a current working mode; if the working mode is a first working mode, when a target intrusion event is monitored by the radar, state information of the intrusion target is acquired, and whether the intrusion target is a preset key control target is determined by using optical image identification; if the intrusion target is the preset key control target, the number of the preset key control targets is determined; if the number is one, the preset key control target is tracked and recorded by using the state information of the preset key control target; and if the number is multiple, the preset key control targets are screened by using a preset screening rule and tracked and recorded by using optical image identification. By using the technical scheme, the detection accuracy of the system can be improved, and problems such as limited detection area, discontinuous linkage, strong dependence between devices and instability can be solved.

Description

Technical Field

[0001] This invention relates to the field of radar detection technology, and in particular to a target identification and tracking method, apparatus, device, and storage medium. Background Technology

[0002] With the increasing demand for security protection, various security measures are widely used in perimeter security, security facilities, prisons, coastlines, and border control. Common security measures include human area patrols, photoelectric automatic patrols, electronic fences, and radar area detection. These measures can basically meet the needs of security area early warning, target intrusion tracking, and threat target handling. However, due to their low response efficiency, lack of visual display, high deployment costs, and inherent performance limitations, operators are unable to control the scene and situation development in a real-time, accurate, and effective manner.

[0003] Radar-electro-optical linkage systems can effectively compensate for and improve the above-mentioned problems. They operate through a combination of active radar detection, radar-electro-optical parameter calculation guidance, and photoelectric-assisted tracking, using a combination of radar parameter display and video display to perform diversified detection and tracking of specific areas. Currently, there are two main implementation schemes: Scheme 1: Electronic radar detects and discovers targets, guiding photoelectric linkage tracking. However, this system relies solely on radar guidance and is easily affected by the radar's own hardware performance parameters. In complex background environments, the radar is susceptible to clutter interference, leading to noise, false targets, and other target feedback information, resulting in a high false alarm rate and reducing the overall system reliability and stability. Furthermore, when the electronic radar detects targets moving at low speeds or tangentially, the target detection capability is limited by the mechanism, easily resulting in situations such as no target detection or discontinuous target trajectory information, affecting the system's perception performance. Scheme 2: Electronic radar detection and positioning, photoelectric identification and linkage tracking. While this scheme has a wide detection range, it cannot effectively and accurately identify and guide the target in harsh environments and weather conditions. The system has low environmental adaptability and cannot achieve all-day, all-weather application.

[0004] In summary, how to solve the aforementioned limitations, reduce the false alarm rate of the system, and make the linkage tracking more reliable, stable, and adaptable to the environment are problems that need to be solved. Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide a target recognition and tracking method, apparatus, device, and storage medium that can reduce the false alarm rate of the system and make the linkage tracking more reliable, stable, and adaptable to the environment. The specific solution is as follows:

[0006] In a first aspect, this application discloses a target recognition and tracking method applied to a radar-electro-optical linkage system, comprising:

[0007] Determine the current working mode of the radar-photoelectric linkage system. If the current working mode is the first working mode, when the radar detects a target intrusion event, obtain the status information of the intrusion target, and use photoelectric image recognition to determine whether the intrusion target is a preset key control target. The first working mode is a working mode of dual-mechanism linkage between radar and photoelectric image recognition.

[0008] If the intrusion target is a preset key control target, then determine the number of preset key control targets;

[0009] If the number of preset key control targets is 1, then based on the status information of the preset key control target, the preset key control target is guided, tracked and recorded. If the number of preset key control targets is multiple, then the preset key control targets are filtered by preset filtering rules, and guided, tracked and recorded using photoelectric image recognition.

[0010] Optionally, after determining the current operating mode of the radar-photoelectric linkage system, the method further includes:

[0011] If the current working mode is the second working mode, then the target intrusion event is monitored by radar. The second working mode is the working mode linked to the radar master command.

[0012] When the radar detects the target intrusion event, the status information of the intrusion target is obtained, and it is determined whether the status information of the intrusion target meets the preset conditions.

[0013] If the status information of the intrusion target meets the preset conditions, then the intrusion target will be guided, tracked, and recorded.

[0014] Optionally, the process of detecting a target intrusion event by the radar, obtaining the status information of the intrusion target, and using photoelectric image recognition to determine whether the intrusion target is a preset key control target further includes:

[0015] When the radar detects a target intrusion event, it determines whether the optoelectronic equipment has detected the intruding target;

[0016] If the photoelectric device does not detect the intrusion target, the photoelectric recognition area is expanded, and it is determined whether the photoelectric device after the expanded area detects the intrusion target. If the photoelectric device after the expanded area does not detect the intrusion target, the intrusion target is determined to be an invalid target.

[0017] If the optoelectronic device detects an intrusion target, and the intrusion target is not a preset key control target, then the intrusion target is determined to be an invalid target.

[0018] Optionally, after determining that the intrusion target is an invalid target, the method further includes:

[0019] The invalid targets are suppressed and filtered, and it is determined whether the invalid targets have disappeared. If the invalid targets have disappeared, the suppression and filtering of the invalid targets is canceled. If the invalid targets have not disappeared, the suppression and filtering of the invalid targets is performed until the invalid targets disappear.

[0020] Optionally, if the number of preset key control targets is one, after guiding and tracking the preset key control target based on its status information, the method further includes:

[0021] Real-time determination of whether the preset key control target has disappeared;

[0022] If the currently preset key control target disappears, the radar will be used to monitor other intrusion targets.

[0023] Optionally, if the number of preset key control targets is multiple, the preset key control targets are filtered according to preset filtering rules, and photoelectric image recognition is used for guidance, tracking, and recording, including:

[0024] If there are multiple key control targets, then the center coordinate values ​​of multiple preset key control targets are determined;

[0025] Based on the center coordinates of the preset key control targets, the preset key control targets that are closest to the preset threshold are selected, and photoelectric image recognition is used for guidance, tracking and recording.

[0026] Optionally, if the number of preset key control targets is one, then based on the status information of the preset key control target, guidance tracking and recording are performed on the preset key control target, including:

[0027] If the number of preset key control targets is 1, then the preset key control target is marked with a level. If the level is marked as high, then the preset key control target is captured on a screenshot and recorded.

[0028] Image recognition is used to determine the type of the preset key control target, and the status information of the preset key control target is updated. Based on the updated status information of the preset key control target, the preset key control target is guided, tracked, and recorded.

[0029] Secondly, this application discloses a target recognition and tracking device applied to a radar-electro-optical linkage system, the device comprising:

[0030] The mode determination module is used to determine the current working mode of the radar-photoelectric linkage system;

[0031] The target acquisition and processing module is used when the current working mode is the first working mode. When the radar detects a target intrusion event, it acquires the status information of the intrusion target and uses photoelectric image recognition to determine whether the intrusion target is a preset key control target. The first working mode is a working mode in which radar and photoelectric image recognition are linked by a dual mechanism.

[0032] The quantity determination module is used to determine the quantity of the preset key control targets if the intrusion target is a preset key control target;

[0033] The tracking and recording module is used to guide and track the preset key control target based on its status information if the number of preset key control targets is 1; if the number of preset key control targets is multiple, the preset key control targets are filtered according to preset filtering rules, and guided and tracked using photoelectric image recognition.

[0034] Thirdly, this application discloses an electronic device, including:

[0035] Memory is used to protect computer programs;

[0036] A processor is used to execute the computer program to implement the aforementioned target recognition and tracking method.

[0037] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the target recognition and tracking method as described above.

[0038] In this application, applied to a radar-electro-optical linkage system, the current operating mode of the radar-electro-optical linkage system is first determined. If the current operating mode is the first operating mode, when the radar detects a target intrusion event, the status information of the intruding target is obtained, and photoelectric image recognition is used to determine whether the intruding target is a preset key control target. The first operating mode is a dual-mechanism linkage mode of radar and photoelectric image recognition. If the intruding target is a preset key control target, the number of preset key control targets is determined. If the number of preset key control targets is one, the preset key control target is guided, tracked, and recorded based on its status information. If the number of preset key control targets is multiple, the preset key control targets are filtered according to preset filtering rules, and guided, tracked, and recorded using photoelectric image recognition. As can be seen, in a radar-electro-optical linkage system, the first step is to determine the system's operating mode and then perform linked tracking according to the set mode. Based on this, photoelectric image recognition is integrated to identify and judge intrusion targets, assisting in filtering invalid alarms. This can filter out targets other than preset key control targets, effectively identifying and screening detected targets and assisting in judgment, minimizing false alarm rates, reducing system false alarm rates, and minimizing interference from false points and noisy targets. This achieves fully automatic system perception and improves user experience. Simultaneously, in complex application scenarios, image recognition optimizes the performance of the radar-electro-optical linkage system, enabling interactive guided tracking. This solves problems such as radar guidance deviations due to uneven terrain, lack of target elevation information in two-dimensional electronic radar detection feedback, inaccurate positioning and adjustment of photoelectric elevation in complex terrain scenarios, failure to detect intruding targets within the field of view, and inaccurate target capture by linked video imaging. This gives the system stronger autonomous judgment capabilities and makes linked tracking more reliable, traceable, stable, and environmentally adaptable. Attached Figure Description

[0039] 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 only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0040] Figure 1 This is a flowchart of a target recognition and tracking method disclosed in this application;

[0041] Figure 2 This is a block diagram illustrating the principle of a specific target recognition and tracking method disclosed in this application;

[0042] Figure 3This is a flowchart of a specific target recognition and tracking method disclosed in this application;

[0043] Figure 4 This is a flowchart illustrating the logic of a specific target recognition and tracking method disclosed in this application.

[0044] Figure 5 This is a flowchart illustrating the logic of a specific target recognition and tracking method disclosed in this application.

[0045] Figure 6 This is a schematic diagram of the structure of a target recognition and tracking device disclosed in this application;

[0046] Figure 7 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0047] 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 only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] Currently, in various security application scenarios, the use of radar-electro-optical linkage systems to detect and track specific areas is often affected by its own hardware performance parameters, mechanism limitations, and environmental influences, resulting in problems such as low target detection capability, reduced system reliability and stability, and low scenario applicability.

[0049] Therefore, this application provides a target recognition and tracking scheme that can reduce the false alarm rate of the system and make the linkage tracking more reliable, stable and environmentally adaptable.

[0050] This invention discloses a target recognition and tracking method, see [link to relevant documentation]. Figure 1 As shown, the method includes:

[0051] Step S11: Determine the current working mode of the radar-photoelectric linkage system. If the current working mode is the first working mode, when the radar detects a target intrusion event, it obtains the status information of the intrusion target and uses photoelectric image recognition to determine whether the intrusion target is a preset key control target. The first working mode is a working mode of dual-mechanism linkage between radar and photoelectric image recognition.

[0052] In this embodiment, the radar-electro-optical linkage system is applied. The operating mode of the radar-electro-optical linkage system is mainly determined by environmental weather factors. The system mainly includes a first operating mode and a second operating mode. The first operating mode is a dual-mechanism linkage mode of radar and electro-optical image recognition. Specifically, the radar feeds back information such as the target's azimuth, distance, and speed. Based on this information, the electro-optical device is guided to track the target. This mode is selected for use in non-severe weather conditions. Under these environmental conditions, the electro-optical device has high imaging quality, and the electro-optical recognition of the target is good, accurate, and stable. Therefore, image recognition can be used for auxiliary judgment support to achieve dual-mechanism linkage control of radar detection and image recognition. The second operating mode is a radar main guidance linkage mode. Specifically, it judges and links based on the target's angle, distance, and speed returned by the radar, performs electro-optical assisted tracking, video imaging, and completes subsequent functional processes. This mode is selected under severe environmental conditions, such as sandstorms, heavy fog, and strong winds and rainstorms. Under such conditions, the electro-optical imaging quality and image recognition effect are poor, and effective target recognition cannot be performed. Therefore, the radar main guidance linkage mode is selected.

[0053] In this embodiment, if the current operating mode is the first operating mode, the target is detected by radar and preliminary guidance is provided to the target. Specifically, when the radar detects a target intrusion event, it obtains the status information of the intruding target and uses photoelectric image recognition to determine whether the intruding target is a preset key control target.

[0054] Understandably, radar acquires the status information of intruding targets within the detection area. By processing this information, it can obtain the target's number, speed, latitude and longitude coordinates, distance, and azimuth angle, thus possessing multi-target processing capabilities. Through radar's physical detection, intelligent optimization of target parameters, and real-time feedback of target parameters, it can perform large-scale target detection and early warning within a specific distance range of the detection area, as well as map the trajectory of intruding targets.

[0055] In this embodiment of the application, if the current working mode is the second working mode, the target intrusion event is monitored by radar. When the target intrusion event is detected by the radar, the status information of the intrusion target is obtained, and it is determined whether the status information of the intrusion target meets the preset conditions.

[0056] It should be noted that when the radar detects an intruding target, it feeds back the calculated status information of the intruding target to the optoelectronic gimbal device, guiding the device to perform coordinated tracking. The optoelectronic device can integrate adaptive payloads to meet different operating conditions based on varying application requirements and distances, and can perform visualization and video acquisition. Combined with the target position information fed back by the radar, it enables coordinated optoelectronic tracking of the intruding target, continuous day and night video information acquisition, and time-series data feedback. Upon detecting an intruding target, the optoelectronic gimbal, during its rotation, determines the azimuth angle between the optoelectronic device and the radar feedback. If both meet a set threshold condition, the target number can be determined, and the intruding target can be guided and tracked.

[0057] Step S12: If the intrusion target is a preset key control target, then determine the number of preset key control targets.

[0058] In this embodiment, when the current working mode is the first working mode, radar is used to monitor the intrusion target for preliminary guidance, and the photoelectric device rotates and uses image recognition in real time to determine whether the intrusion target is a preset key control target. It can be understood that since the security control mainly targets people (walking, riding in vehicles or boats), people, vehicles and boats can be set as key control target categories.

[0059] It should be noted that most ground-based detection radars on the market are two-dimensional planar radars, lacking elevation information feedback for target points. Three-dimensional radars, which can provide elevation information, are dozens of times more expensive than the two-dimensional radars commonly used in perimeter security systems, making them unsuitable for widespread application. Therefore, currently, using two-dimensional planar radar in complex terrain with radar-guided electro-optical linkage may result in situations where there are no targets in the field of view or the detected targets are unstable, with intermittent trajectories. For example, if the terrain in the detection area has undulating slopes, the lack of elevation information feedback from the radar means that the electro-optical elevation cannot be accurately adjusted, potentially leading to situations where targets cannot be detected in the field of view. Therefore, in the first operating mode, when the radar detects a target intrusion event, it is necessary to determine whether the electro-optical equipment has detected the intruding target.

[0060] In one implementation, when the terrain of the detection area is complex, such as with a certain degree of undulation and slope, the intrusion target may not appear in the field of view due to the influence of terrain, radar detection azimuth angle error, and optical field angle, causing the optoelectronic device to fail to detect the intrusion target. In this case, the optoelectronic identification area is expanded, and the optoelectronic pan-tilt unit scans the surrounding area to reduce the impact of errors. It then determines whether the optoelectronic device in the expanded area has detected the intrusion target. If the optoelectronic device in the expanded area has detected the intrusion target, it continues to determine whether the intrusion target is a preset key control target; if the optoelectronic device in the expanded area still has not detected the intrusion target, the intrusion target is determined to be an invalid target.

[0061] In another implementation, if the photoelectric device detects an intrusion target, it determines whether the intrusion target is a preset key control target. If it is not a preset key control target, the intrusion target is determined to be an invalid target.

[0062] It is understandable that in complex background application environments, radar detection may produce certain noise and false targets, such as waves on a turbulent water surface, branches and weeds swaying in the wind, or small animals that are not monitored targets. Detecting such targets will generate alarm information and cause certain false alarms, so such targets are regarded as invalid targets.

[0063] In this embodiment, when an intrusion target is determined to be an invalid target, it is necessary to suppress and filter the invalid target, stop guiding and tracking that target, and re-evaluate and guide and track other targets. Invalid targets that have been suppressed and filtered remain in a state of exclusion until they disappear. The suppression and filtering of the invalid target is cancelled once it disappears, restoring normal, linked tracking. If the invalid target does not disappear, suppression and filtering are continued until it disappears.

[0064] Step S13: If the number of preset key control targets is 1, then guide and track the preset key control target based on its status information.

[0065] In this embodiment, the current working mode is the first working mode. When image recognition determines that the intrusion target is a preset key control target, it is further necessary to determine the number of preset key control targets. If the number of preset key control targets is one, i.e., a single target, the status information is calculated, the obtained intrusion target number is marked with a level, and the number is marked as high-level. A screenshot is taken and recording begins to achieve guidance, tracking, and recording of the preset key control target.

[0066] Step S14: If there are multiple preset key control targets, the preset key control targets are filtered by preset filtering rules, and photoelectric image recognition is used for guidance, tracking and recording.

[0067] In this embodiment, the current working mode is the first working mode. If there are multiple preset key control targets, the preset key control targets are filtered according to preset filtering rules. In this working mode, the integrated algorithm will automatically determine and track the most threatening target based on preset rules, such as selecting the closest or fastest intrusion target. For example, there are currently five intrusion targets, numbered 1 to 5, with distances from the control area of ​​100m, 200m, 300m, 400m, and 500m respectively, and movement speeds of 20m / s, 30m / s, 40m / s, and 50m / s respectively. If distance is set as the first filtering condition and speed as the second filtering condition, then among targets 1 to 5, target 1 is the closest and therefore the most threatening intrusion target. Target 1 will be selected and tracked using photoelectric image recognition. If target 1 disappears, targets 2 and 3 will be at the same distance and become the most threatening targets. In this case, target 3 will be selected as the most threatening target based on the second filtering condition, and tracked using photoelectric image recognition. The filtering conditions can be set according to the actual situation and are not specifically limited here.

[0068] In this embodiment of the application, when using photoelectric image recognition to guide and track intrusion targets, it is necessary to determine in real time whether the preset key control target has disappeared.

[0069] In one implementation, if the currently preset key control target disappears, it is necessary to use the radar to re-monitor other intrusion targets.

[0070] In another implementation, if the currently preset key control target does not disappear, but a higher threat level intrusion target appears, such as a target that is closer, then the most threatening target will be transferred.

[0071] like Figure 2 The diagram shown is a basic principle block diagram of a radar-photoelectric linkage system optimized using image recognition, provided in an embodiment of this application. The radar detection area is set according to the scenario and application requirements, and the working mode is selected based on environmental and weather factors: First working mode: dual-mechanism linkage of radar and photoelectric image recognition; Second working mode: radar main guidance linkage. When a target enters the detection area, the radar detects the intruding target and transmits the target's position and status information back to the target information analysis module of the platform system software. The radar data is analyzed to obtain information such as the target's number, azimuth angle, distance, and speed. Based on the analyzed information, the platform software controls the photoelectric system to rotate to a designated position to perform video imaging of the target and performs linkage tracking according to the set mode.

[0072] As can be seen, this application provides a target identification and tracking method applied to a radar-electro-optical linkage system. First, the current operating mode of the radar-electro-optical linkage system is determined. If the current operating mode is a first operating mode, when the radar detects a target intrusion event, the status information of the intruding target is obtained, and photoelectric image recognition is used to determine whether the intruding target is a preset key control target. The first operating mode is a dual-mechanism linkage mode of radar and photoelectric image recognition. If the intruding target is a preset key control target, the number of preset key control targets is determined. If the number of preset key control targets is one, guidance tracking and recording are performed on the preset key control target based on its status information. If the number of preset key control targets is multiple, the preset key control targets are filtered according to preset filtering rules, and guidance tracking and recording are performed using photoelectric image recognition. As can be seen, in a radar-electro-optical linkage system, the first step is to determine the system's operating mode and then perform linked tracking according to the set mode. Based on this, photoelectric image recognition is integrated to identify and judge intrusion targets, assisting in filtering invalid alarms. This can filter out targets other than preset key control targets, effectively identifying and screening detected targets and assisting in judgment, minimizing false alarm rates, reducing system false alarm rates, and minimizing interference from false points and noisy targets. This achieves fully automatic system perception and improves user experience. Simultaneously, in complex application scenarios, image recognition optimizes the performance of the radar-electro-optical linkage system, enabling interactive guided tracking. This solves problems such as radar guidance deviations due to uneven terrain, lack of target elevation information in two-dimensional electronic radar detection feedback, inaccurate positioning and adjustment of photoelectric elevation in complex terrain scenarios, failure to detect intruding targets within the field of view, and inaccurate target capture by linked video imaging. This gives the system stronger autonomous judgment capabilities and makes linked tracking more reliable, traceable, stable, and environmentally adaptable.

[0073] This application discloses a specific target recognition and tracking method. See [link to relevant documentation] Figure 3 As shown, the method includes:

[0074] Step S21: Determine the current working mode of the radar-photoelectric linkage system. If the current working mode is the first working mode, when the radar detects a target intrusion event, it obtains the status information of the intrusion target and uses photoelectric image recognition to determine whether the intrusion target is a preset key control target. The first working mode is a working mode of dual-mechanism linkage between radar and photoelectric image recognition.

[0075] Step S22: If the intrusion target is a preset key control target, then determine the number of preset key control targets.

[0076] For more detailed processing procedures regarding steps S21 and S22, please refer to the relevant content disclosed in the foregoing embodiments, which will not be repeated here.

[0077] Step S23: If the number of preset key control targets is 1, then the preset key control target is marked with a level. If the level is marked as high, then the preset key control target is captured on a screenshot and recorded.

[0078] In this embodiment of the application, the current working mode is the first working mode. When the target of the intrusion is determined to be a preset key control target by image recognition, and the number of preset key control targets is determined to be 1, that is, a single target, the status information is calculated, the number of the obtained intrusion target is marked with a level, and the number is marked as high level. A screenshot is taken and recording begins, so as to realize the guidance, tracking and recording of the preset key control target.

[0079] Step S24: Use image recognition to determine the type of the preset key control target, update the status information of the preset key control target, and guide and track the preset key control target based on the updated status information of the preset key control target.

[0080] In this embodiment of the application, if the number of preset key control targets is 1, a screenshot is taken of the intrusion target and video recording is started. At the same time, the type of the preset key control target can be determined by image recognition, and the determined type information of the preset key control target is assigned to the corresponding number in the calculated status information, the number information of the preset key control target is updated, and the preset key control target is guided and tracked.

[0081] Step S25: If there are multiple key control targets, determine the center coordinates of multiple preset key control targets; based on the center coordinates of the preset key control targets, select the preset key control targets that are closest to the preset threshold, and use photoelectric image recognition for guidance, tracking and recording.

[0082] In this embodiment of the application, the current working mode is the first working mode. When the target of the intrusion is determined to be a preset key control target by image recognition, the number of preset key control targets is determined to be multiple. At this time, the photoelectric linkage will determine the coordinate values ​​of multiple targets under the reference of the video window and calculate the center coordinate values ​​of multiple targets. The targets around the center coordinate values ​​are filtered. Based on the center coordinate values ​​of multiple targets, the azimuth angle of the photoelectric pan-tilt unit, the radar return target angle and other information, the azimuth threshold of the target is judged. According to the threshold judgment, the number of the closest target is recorded. The alarm record level of this target is recorded as high, and alarm screenshots and video recordings are stored.

[0083] like Figure 4 , Figure 5 The diagram shows a logical flowchart of a specific target recognition and tracking method. The automatic linkage tracking mode is applied in unattended operation. In this mode, the platform software's target information calculation module calculates the radar-transmitted data, including target number, velocity, latitude and longitude coordinates, distance, and azimuth angle. Based on the parameter information of each target object determined by the calculation module, the system autonomously determines its operating mode and guides tracking using a dual-mechanism linkage control method that optimizes the linkage system's performance through image recognition, achieving fully automatic application in unattended mode.

[0084] like Figure 4 As shown, the automatic linkage tracking mode is divided into two categories based on environmental and weather conditions. The first is a radar-guided linkage mode. In this mode, the radar identifies and filters targets, sets a detection area, and issues a real-time alarm when a target enters the detection area. Feedback analysis of the target's specific positional status information guides the photoelectric device for linkage tracking. During this process, the photoelectric pan-tilt unit rotates, judging the target's azimuth angle value fed back by the radar. If both meet a threshold, an alarm screenshot and alarm video are recorded and stored, and the alarm level for this number is recorded as high. For other targets with corresponding numbers, the alarm level is recorded as low, without needing screenshots or video recording. If the threshold is not met, the alarm level remains low, and the above guidance, linkage, and tracking judgment process is repeated. The second is a dual-mechanism linkage mode combining radar and photoelectric image recognition. The initial logic of this mode is basically similar to the radar-guided linkage mode. The radar detects the target and provides initial guidance. At this time, all initial alarm level information is recorded as low, and screenshots and video recordings are not stored. The photoelectric device rotates and performs real-time image recognition and judgment. This mechanism primarily uses photoelectric image recognition for guidance and tracking, with interactive judgment, making the linkage tracking more reliable and stable. Based on the photoelectric image recognition of the detected intruder, photoelectric equipment is used to determine whether there is a target to be identified. Specifically, it is divided into two categories: one is the state of no target to be identified, and the other is the state of a target to be identified.

[0085] When no target is identified, the photoelectric pan-tilt unit scans the surrounding area (up, down, left, right) to expand the photoelectric recognition area and reduce the impact of errors. If a target is detected during the scan, it is determined whether the target is a person, vehicle, or vessel. If no target is detected, the target is considered a false alarm or noise point, and its alarm level is set to low. No linkage tracking is required for this target, thus reducing the overall false alarm rate for intrusion targets. Simultaneously, this target is suppressed and filtered, and linkage tracking for it is stopped. The remaining target numbers are re-evaluated and linked, repeating the above logic process. Target numbers that have been suppressed and filtered remain excluded until the target disappears. Once the target disappears, the filtering for that number is canceled, restoring normal linkage tracking capability, and the target is reintroduced into the above logic process.

[0086] When there is target recognition, the target in the image needs to be classified to determine whether it is a key control target such as a person, vehicle, or ship. If it is not, but an animal or other target type, no linkage tracking is performed, and the subsequent logic process continues the process described above when there is no target recognition. If the target is one or more of the following: a person, a vehicle, or a ship, then proceed to process 2.

[0087] like Figure 5 As shown, the judgment process in step 2 begins. The photoelectric identification targets are people, vehicles, and ships. The number of identified targets in the field of view is determined. If there are multiple photoelectric identification targets in the field of view, the centers of multiple targets are tracked. After photoelectric identification, the position information of each identified target, i.e., the miss distance, is fed back. When multiple targets appear simultaneously in the field of view, the photoelectric linkage reference selects the coordinate values ​​of multiple target centers. Linked tracking is performed using the coordinate values ​​of multiple miss distance centers. Based on the target feedback miss distance, the azimuth angle of the photoelectric pan-tilt unit, and the radar return target angle, the target's azimuth threshold is determined. The closest radar target point number is recorded according to the threshold. This target number is recorded as having a high alarm level, and an alarm screenshot and video recording are stored. Other radar targets remain at a low alarm level, with no screenshot or video recording.

[0088] If the number of targets identified in the field of view is a single one, an alarm screenshot and video recording are performed for that intrusion target. The alarm information record for this target is updated to high, a screenshot is taken, and video recording begins. The alarm records for other targets remain low, with no screenshots or recordings. Simultaneously, the target type information is assigned to the corresponding radar number based on the target's photoelectric image recognition effect, and the target number information is updated. The photoelectric linkage tracking is guided by the target miss distance calculated based on the image recognition feedback. In automatic tracking mode, the integrated algorithm automatically determines and tracks the most threatening target based on preset parameters. During the linkage tracking process, it continuously checks whether the most threatening target has changed. If it has not changed, the photoelectric linkage tracking continues based on the miss distance. If the target has changed, the process proceeds to the next logical step.

[0089] There are two scenarios when the most threatening target changes. Scenario 1: The current target number remains, but a target with a higher threat level appears, and the most threatening target shifts. In this case, photoelectric image recognition guidance is stopped, and the system switches to... Figure 4 The process of the dual-mechanism linkage between radar and image recognition is described, and the operation of the process is repeated. The second is that the target with the current number disappears. After the target disappears, there are two situations: Situation 1: There are other radar target points. At this time, the logic process is the same as that of the first situation, and the subsequent judgment operation of the first situation is executed. Situation 2: There are no other radar target points. At this time, the photoelectric image recognition guidance linkage continues until the target disappears, and a complete autonomous linkage tracking is completed.

[0090] As can be seen, this application provides a target identification and tracking method applied to a radar-electro-optical linkage system. First, the current operating mode of the radar-electro-optical linkage system is determined. If the current operating mode is a first operating mode, when the radar detects a target intrusion event, the status information of the intruding target is obtained, and photoelectric image recognition is used to determine whether the intruding target is a preset key control target. The first operating mode is a dual-mechanism linkage mode of radar and photoelectric image recognition. If the intruding target is a preset key control target, the number of preset key control targets is determined. If the number of preset key control targets is one, then the preset key control target... A level label is applied. If the level label is high, a screenshot and video recording are taken of the preset key control target. Image recognition is used to determine the type of the preset key control target, and the status information of the preset key control target is updated. Based on the updated status information of the preset key control target, guidance and tracking are performed on the preset key control target. If there are multiple key control targets, the center coordinates of multiple preset key control targets are determined. Based on the center coordinates of the preset key control targets, the preset key control target that is closest to a preset threshold is selected, and guidance and tracking are performed using photoelectric image recognition. As can be seen, in a radar-electro-optical linkage system, the first step is to determine the system's operating mode and then perform linked tracking according to the set mode. Based on this, photoelectric image recognition is integrated to identify and judge intrusion targets, assisting in filtering invalid alarms. This can filter out targets other than preset key control targets, effectively identifying and screening detected targets and assisting in judgment, minimizing false alarm rates, reducing system false alarm rates, and minimizing interference from false points and noisy targets. This achieves fully automatic system perception and improves user experience. Simultaneously, in complex application scenarios, image recognition optimizes the performance of the radar-electro-optical linkage system, enabling interactive guided tracking. This solves problems such as radar guidance deviations due to uneven terrain, lack of target elevation information in two-dimensional electronic radar detection feedback, inaccurate positioning and adjustment of photoelectric elevation in complex terrain scenarios, failure to detect intruding targets within the field of view, and inaccurate target capture by linked video imaging. This gives the system stronger autonomous judgment capabilities and makes linked tracking more reliable, traceable, stable, and environmentally adaptable.

[0091] Accordingly, this application also discloses a target recognition and tracking device, see [link to relevant documentation]. Figure 6 As shown, the device includes:

[0092] The mode determination module 11 is used to determine the current working mode of the radar-photoelectric linkage system;

[0093] The target acquisition and processing module 12 is used when the current working mode is the first working mode. When the radar detects a target intrusion event, it acquires the status information of the intrusion target and uses photoelectric image recognition to determine whether the intrusion target is a preset key control target. The first working mode is a working mode in which radar and photoelectric image recognition are linked by a dual mechanism.

[0094] The quantity determination module 13 is used to determine the quantity of the preset key control targets if the intrusion target is a preset key control target;

[0095] The tracking and recording module 14 is used to guide and track the preset key control target based on its status information if the number of preset key control targets is 1; if the number of preset key control targets is multiple, the preset key control targets are filtered by preset filtering rules and guided and tracked using photoelectric image recognition.

[0096] For more detailed information on the working process of each of the above modules, please refer to the relevant content disclosed in the foregoing embodiments, which will not be repeated here.

[0097] Therefore, the above-described scheme of this embodiment, applied to a radar-optical-electric linkage system, firstly determines the current working mode of the radar-optical-electric linkage system. If the current working mode is the first working mode, when the radar detects a target intrusion event, it obtains the status information of the intruding target and uses photoelectric image recognition to determine whether the intruding target is a preset key control target. Here, the first working mode is a working mode of dual-mechanism linkage between radar and photoelectric image recognition. If the intruding target is a preset key control target, the number of preset key control targets is determined. If the number of preset key control targets is one, the preset key control target is guided, tracked, and recorded based on its status information. If the number of preset key control targets is multiple, the preset key control targets are filtered according to preset filtering rules, and guided, tracked, and recorded using photoelectric image recognition. As can be seen, in a radar-electro-optical linkage system, the first step is to determine the system's operating mode and then perform linked tracking according to the set mode. Based on this, photoelectric image recognition is integrated to identify and judge intrusion targets, assisting in filtering invalid alarms. This can filter out targets other than preset key control targets, effectively identifying and screening detected targets and assisting in judgment, minimizing false alarm rates, reducing system false alarm rates, and minimizing interference from false points and noisy targets. This achieves fully automatic system perception and improves user experience. Simultaneously, in complex application scenarios, image recognition optimizes the performance of the radar-electro-optical linkage system, enabling interactive guided tracking. This solves problems such as radar guidance deviations due to uneven terrain, lack of target elevation information in two-dimensional electronic radar detection feedback, inaccurate positioning and adjustment of photoelectric elevation in complex terrain scenarios, failure to detect intruding targets within the field of view, and inaccurate target capture by linked video imaging. This gives the system stronger autonomous judgment capabilities and makes linked tracking more reliable, traceable, stable, and environmentally adaptable.

[0098] Furthermore, embodiments of this application also disclose an electronic device, Figure 7 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0099] Figure 7 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the target recognition and tracking method disclosed in any of the foregoing embodiments. Furthermore, the electronic device 20 in this embodiment may specifically be a radar-photoelectric linkage system.

[0100] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0101] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk, or optical disk, etc. The resources stored on it can include an operating system 221, computer programs 222, and data 223, etc. The data 223 can include various types of data. The storage method can be temporary storage or permanent storage.

[0102] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including computer programs capable of performing the target recognition and tracking method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0103] Furthermore, this application also discloses a computer-readable storage medium, which includes random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, magnetic disks, optical disks, or any other form of storage medium known in the art. The computer program, when executed by a processor, implements the aforementioned target recognition and tracking method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0104] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0105] The steps of the target recognition and tracking or algorithm described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0106] Finally, 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.

[0107] The above provides a detailed description of the target recognition and tracking method, apparatus, device, and storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A target recognition and tracking method, characterized in that, Applications include radar-electro-optical linkage systems, including: The system determines the current operating mode of the radar-photoelectric linkage system. If the current operating mode is the first operating mode, when the radar detects a target intrusion event, it acquires the status information of the intruding target and uses photoelectric image recognition to determine whether the intruding target is a preset key control target. The first operating mode is a dual-mechanism linkage mode of radar and photoelectric image recognition, which guides the photoelectric equipment to track the target based on the target information fed back by the radar. This mode is selected in non-severe weather conditions. The preset key control target is a target that has been filtered out from other targets that have been invalidated by the intruding target. If the intrusion target is a preset key control target, then determine the number of preset key control targets; If the number of preset key control targets is 1, then based on the status information of the preset key control target, the preset key control target is guided, tracked and recorded. If the number of preset key control targets is multiple, then the preset key control targets are filtered by preset filtering rules, and guided, tracked and recorded using photoelectric image recognition. The target recognition and tracking method further includes: If the current operating mode is the second operating mode, then target intrusion events are monitored via radar. The second operating mode is a radar-guided linkage mode with photoelectric assisted tracking. Adaptive payloads are integrated into the photoelectric equipment to meet the needs of different operating conditions, and visualization and video acquisition are performed. This is combined with radar feedback of target location information, and selection is made under harsh environmental conditions. When the radar detects a target intrusion event, the status information of the intruding target is acquired, and it is determined whether the status information of the intruding target meets preset conditions. If the status information of the intruding target meets the preset conditions, the intruding target is guided, tracked, and recorded. When the radar detects a target intrusion event, it determines whether the optoelectronic device has detected the intruding target. If the optoelectronic device has not detected the intruding target, the optoelectronic identification area is expanded, and it is determined whether the optoelectronic device after the expanded area has detected the intruding target. If the optoelectronic device after the expanded area has not detected the intruding target, the intruding target is determined to be an invalid target. If the optoelectronic device detects the intruding target, and the intruding target is not a preset key control target, the intruding target is determined to be an invalid target.

2. The target recognition and tracking method according to claim 1, characterized in that, After determining that the intrusion target is an invalid target, the method further includes: The invalid targets are suppressed and filtered, and it is determined whether the invalid targets have disappeared. If the invalid targets have disappeared, the suppression and filtering of the invalid targets is canceled. If the invalid targets have not disappeared, the suppression and filtering of the invalid targets is performed until the invalid targets disappear.

3. The target recognition and tracking method according to claim 1, characterized in that, If the number of preset key control targets is 1, then after guiding and tracking the preset key control target based on its status information, the method further includes: Real-time determination of whether the preset key control target has disappeared; If the currently preset key control target disappears, the radar will be used to monitor other intrusion targets.

4. The target recognition and tracking method according to claim 1, characterized in that, If there are multiple preset key control targets, then the preset key control targets are filtered according to preset screening rules, and photoelectric image recognition is used for guidance, tracking, and recording, including: If there are multiple key control targets, then the center coordinate values ​​of multiple preset key control targets are determined; Based on the center coordinates of the preset key control targets, the preset key control targets that are closest to the preset threshold are selected, and photoelectric image recognition is used for guidance, tracking and recording.

5. The target recognition and tracking method according to any one of claims 1 to 4, characterized in that, If the number of preset key control targets is one, then based on the status information of the preset key control target, guidance tracking and recording are performed on the preset key control target, including: If the number of preset key control targets is 1, then the preset key control target is marked with a level. If the level is marked as high, then the preset key control target is captured on a screenshot and recorded. Image recognition is used to determine the type of the preset key control target, and the status information of the preset key control target is updated. Based on the updated status information of the preset key control target, the preset key control target is guided, tracked, and recorded.

6. A target recognition and tracking device, characterized in that, Applications include radar-electro-optical linkage systems, including: The mode determination module is used to determine the current working mode of the radar-photoelectric linkage system; The target acquisition and processing module is used when the current working mode is the first working mode. When the radar detects a target intrusion event, it acquires the status information of the intrusion target and uses photoelectric image recognition to determine whether the intrusion target is a preset key control target. The first working mode is a working mode in which radar and photoelectric image recognition are linked by a dual mechanism. The preset key control target is the target after filtering out other targets that have made invalid alarms on the intrusion target. The quantity determination module is used to determine the quantity of the preset key control targets if the intrusion target is a preset key control target; The tracking and recording module is used to guide and track the preset key control target based on its status information if the number of preset key control targets is 1; if the number of preset key control targets is multiple, the preset key control targets are filtered according to preset filtering rules, and guided and tracked using photoelectric image recognition. The target recognition and tracking device is also used for: If the current operating mode is the second operating mode, then target intrusion events are monitored via radar. The second operating mode is a radar-guided linkage mode with photoelectric assisted tracking. Adaptive payloads are integrated into the photoelectric equipment to meet the needs of different operating conditions, and visualization and video acquisition are performed. This is combined with radar feedback of target location information, and selection is made under harsh environmental conditions. When the radar detects a target intrusion event, the status information of the intruding target is acquired, and it is determined whether the status information of the intruding target meets preset conditions. If the status information of the intruding target meets the preset conditions, the intruding target is guided, tracked, and recorded. When the radar detects a target intrusion event, it determines whether the optoelectronic device has detected the intruding target. If the optoelectronic device has not detected the intruding target, the optoelectronic identification area is expanded, and it is determined whether the optoelectronic device after the expanded area has detected the intruding target. If the optoelectronic device after the expanded area has not detected the intruding target, the intruding target is determined to be an invalid target. If the optoelectronic device detects the intruding target, and the intruding target is not a preset key control target, the intruding target is determined to be an invalid target.

7. An electronic device, characterized in that, include: Memory is used to protect computer programs; A processor for executing the computer program to implement the target recognition and tracking method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store computer programs; wherein the computer programs, when executed by a processor, implement the target recognition and tracking method as described in any one of claims 1 to 5.

Images