Light-thunder integrated system three-dimensional target identification method, device, equipment and medium
By combining radar with optoelectronic equipment and using GIS maps for regional division and target type weighting, the shortcomings of the integrated optical radar system in terms of environmental factors and anti-interference are solved, and higher target recognition accuracy and robustness are achieved.
Patent Information
- Application Number
- CN202510881736.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-27
- Publication Date
- 2025-10-17
AI Technical Summary
The existing integrated optical-threat system is affected by environmental factors, lacks anti-interference and countermeasure capabilities, and lacks target identification capabilities, resulting in insufficient target identification accuracy and robustness.
Target information is acquired through radar equipment, image recognition is performed in combination with optoelectronic equipment, and regional division and target type weighting are performed using GIS maps. The final target type is comprehensively determined, and intelligent judgment is performed using the three-dimensional information of the map.
It improves the target recognition accuracy and robustness of the integrated optical mine system in complex environments, and enhances the system's anti-interference ability and adaptability.
Smart Images
Figure CN120802232A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of target detection and identification, and in particular to a three-dimensional target identification method, device, equipment and medium of a radar-optical integrated system. BACKGROUND
[0002] In a radar-optical integrated system (referred to as "radar-optical integrated system" for short), the advantages of radar (radio detection and ranging) and optical equipment (such as visible light cameras, infrared thermal imagers) are fully utilized: Radar: has all-weather, large-range, long-distance continuous monitoring capability, and can accurately detect the distance, direction, speed and other parameters of the target; Optical equipment: can provide high-resolution optical or thermal imaging information of the target, including rich detailed features such as shape, texture, color, and thermal radiation characteristics.
[0003] In related technologies, a typical application is that radar first performs large-scale scanning detection, and after discovering a potential target, the rough position information (direction, distance) of the target is used to guide the optical equipment to accurately point, track and identify details. Through information fusion technology, the position / motion data of the radar and the visual / thermal feature data of the optical equipment are associated and integrated, which can achieve more comprehensive and accurate target detection and identification. However, it has the following limitations: 1. Influence of environmental factors. The visible light of the optical equipment is greatly affected by light conditions and weather fog and rain. The infrared equipment is sensitive to temperature and may be disturbed by hot smoke and high-temperature background. The radar is disturbed by ground clutter and is difficult to distinguish stationary targets.
[0004] 2. Insufficient anti-interference and countermeasure capability. The optical equipment will be weakened by strong light sources. The radar will be suppressed by noise and deceptive jamming, resulting in false alarm or failure.
[0005] 3. Insufficient target identification capability. For targets with similar shapes but different properties, the radar may not be able to distinguish them, and the optical system may also misjudge if the resolution is insufficient. In a multi-target scene, in a dense environment, the cross-movement of multiple targets may cause the optical and radar data to be associated incorrectly.
[0006] The above limitations result in a certain degree of deficiency in the accuracy and robustness of the target identification of the existing radar-optical integrated system. SUMMARY
[0007] The present application provides a radar-optical integrated system three-dimensional target identification method, device, equipment and medium, which solves the problem of how to improve the accuracy and robustness of the target identification of the radar-optical integrated system.
[0008] To achieve the above purpose, the following technical solutions are adopted in the present application: In a first aspect, a three-dimensional target identification method of an optical radar integrated system is provided, comprising: scanning and searching a target based on a radar device to obtain target information, wherein the target information comprises distance, azimuth, pitch, speed information and a first target type; receiving the target information, and controlling a photoelectric device turntable to turn to a target direction and perform image identification on a target area according to corresponding information to obtain a second target type of photoelectric target identification; mapping the target information to a preset GIS map to obtain position information of the target, wherein the GIS map is configured to divide regions according to detailed information of the map, and each region is preconfigured with a weight value of different target types; comprehensively determining a final target type according to the first target type, the second target type and the position information.
[0009] In a second aspect, a three-dimensional target identification device of an optical radar integrated system is provided, comprising: a radar module configured to scan and search a target based on a radar device to obtain target information, wherein the target information comprises distance, azimuth, pitch, speed information and a first target type; a photoelectric module configured to receive the target information, and control a photoelectric device turntable to turn to a target direction and perform image identification on a target area according to corresponding information to obtain a second target type of photoelectric target identification; a GIS map module configured to map the target information to a preset GIS map to obtain position information of the target, wherein the GIS map is configured to divide regions according to detailed information of the map, and each region is preconfigured with a weight value of different target types.
[0010] a target type determination module configured to comprehensively determine a final target type according to the first target type, the second target type and the position information.
[0011] In a third aspect, an electronic device is provided, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is executed by the processor to implement the steps of the three-dimensional target identification method of the optical radar integrated system according to the first aspect.
[0012] In a fourth aspect, a readable storage medium is provided, which stores a program or instructions, and the program or instructions are executed by a processor to implement the steps of the three-dimensional target identification method of the optical radar integrated system according to the first aspect.
[0013] The three-dimensional target identification method of the optical radar integrated system has the following advantages: The three-dimensional target identification method of the light and radar integrated system of the application effectively utilizes the three-dimensional information of the map, intelligently judges the target type, makes up for the deficiencies of the light and radar integrated system affected by weather and other factors, and thus improves the accuracy and robustness of the system linkage target identification. Meanwhile, the accuracy, adaptability and anti-interference ability of the system in complex environments are improved.
[0014] The device, electronic equipment and readable storage medium corresponding to the three-dimensional target identification method of the light and radar integrated system of the application can achieve the same technical effects. To avoid repetition, they will not be described here. BRIEF DESCRIPTION OF DRAWINGS
[0015] Figure 1 A schematic flowchart of a three-dimensional target identification method of a light and radar integrated system provided for an embodiment of the application is provided. Figure 2 A schematic flowchart of another three-dimensional target identification method of a light and radar integrated system provided for an embodiment of the application is provided. Figure 3 A structural schematic diagram of a three-dimensional target identification device of a light and radar integrated system provided for an embodiment of the application is provided. Figure 4 A structural schematic diagram of an electronic equipment provided for an embodiment of the application is provided. DETAILED DESCRIPTION
[0016] To further illustrate the technical means and effects taken by the application to achieve the predetermined purpose, the technical solutions in the embodiments of the application are described clearly. Obviously, the described embodiments are part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art belong to the scope of protection of the application.
[0017] The terms "first", "second", etc. in the specification and claims of the application are used to distinguish similar objects, not to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are usually a class, not limited to the number of objects, for example, the first object can be one or more. In addition, "and / or" in the specification means at least one of the connected objects, and the character " / ", generally represents that the front and rear associated objects are in an "or" relationship.
[0018] The description of the method flow in the specification and the steps of the flowchart in the drawings of the application do not necessarily strictly execute the step labels, and the method steps can change the execution order. Moreover, certain steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be divided into multiple steps for execution.
[0019] The three-dimensional target identification method, device, equipment and medium of the light-radar integrated system provided by the embodiments of the present application are described in detail as follows in combination with the drawings and preferred embodiments.
[0020] The light-radar integrated system can be widely applied to situational awareness scenes such as security monitoring. As a large-scale continuous monitoring device, the radar guides the photoelectric device to perform high-precision confirmation and detailed identification after discovering a target, and realizes all-weather target tracking and identification. The light-radar integrated system improves the accuracy of target classification and identity determination by combining photoelectric and radar data. At the same time, the photoelectric sensor independently verifies and distinguishes real targets from false targets, thereby improving the anti-interference ability of the system. The position data information of the radar is fused with the image data of the photoelectric device through an algorithm, and a more complete target information model is constructed. The accuracy of target identification in the system directly determines the effectiveness of the system linkage function.
[0021] In view of the limitations of related technologies in environmental factors, insufficient anti-interference and countermeasure ability, and insufficient target identification ability, in order to improve the accuracy and robustness of target identification of the light-radar integrated system, an improved light-radar integrated system is provided. The target position information is mapped on a map, the region is divided according to the detailed information of the map, and the target type weighting value of each region is different. According to the position of the target on the map, the target type is further intelligently judged.
[0022] Referring to Figures 1-2 , the embodiments of the present application provide a three-dimensional target identification method of a light-radar integrated system, as Figures 1-2 shown, comprising: Step S1, scanning and searching a target based on a radar device to obtain target information; the target information includes distance, azimuth, pitch, speed information and target type.
[0023] In this step, the radar device scans and searches a target to obtain the distance, azimuth, pitch, speed information of the target and the first target type determined by the radar.
[0024] Step S2, receiving the target information; controlling a photoelectric device turntable to turn to the target direction according to the corresponding information and performing image recognition on the target region to obtain a second target type of photoelectric target identification.
[0025] Specifically, in this step, the distance, azimuth, pitch and speed information of the target obtained by the radar is used to control the photoelectric device turntable to turn to the target direction; then the target region is identified by collecting and analyzing image information. At the same time, the target distance information provided by the radar is mapped to a geographic information system (GIS) map, so as to determine the actual position of the target in the three-dimensional space.
[0026] In the implementation, if the photoelectric device fails to find the target, the method returns to step S1, and the target is searched again by the radar scanning to obtain the latest information of the target, and then the parameters of the photoelectric device are adjusted to identify the target again.
[0027] In step S3, the target information is mapped to a preset GIS map to obtain the position information of the target, and the GIS map is configured to divide regions according to detailed information of the map, and each region is preset with a weight value of different target types.
[0028] In this step, the target position information is mapped on the map, and each region is weighted according to the detailed information of the map.
[0029] In step S4, the final target type is determined according to the first target type, the second target type, and the position information. In step S41, if the first target type is consistent with the second target type, the type is confirmed as the final target type. In step S42, if the first target type is inconsistent with the second target type, the target type is determined according to the weight value of the target type corresponding to the region of the position information on the map. In step S43, if the target type cannot be determined according to the weight value of the target type corresponding to the region of the position information on the GIS map, a comprehensive confidence is calculated based on the first target type, the second target type, and the weight value of different target types in the region, and the type exceeding the set threshold is taken as the final target type.
[0030] The final target type is determined according to the above logical sequence. That is, if the target type determined by the radar is consistent with the target type of the photoelectric identification result, the type is directly confirmed as the final target type; if the target types are inconsistent, the target type is determined according to the weight value of the target type corresponding to the region of the position information on the GIS map; if the target type cannot be determined according to the weight value of the target type corresponding to the region of the position information on the GIS map, a comprehensive confidence is calculated by a preset weighting algorithm combined with the target type determined by the radar, the target type of the photoelectric identification result, and the weight value of the region, and the type exceeding the set threshold is taken as the final target type.
[0031] Further, in step S3, the GIS map is configured to divide regions according to detailed information of the map, and each region is preset with a weight value of different target types. Specifically: If the target is located in a highway region, the weight value of the vehicle and pedestrian category is higher than that of the animal or static object; If the target is located in a wilderness region, the weight value of the animal category is higher than that of the vehicle, pedestrian, or static object; If the target is located in a mountainous region, the weight value of the static object category is higher than that of the vehicle, pedestrian, or animal.
[0032] The light and radar integrated system is different from the single photoelectric device in that the distance, position and radar determined target category information of the radar detected target are added, the photoelectric image information and the position information of the map are combined to form a three-dimensional spatial recognition scheme.
[0033] In a specific implementation, after the radar searches for a target, the distance information, azimuth and pitch information, target speed information and radar target category of the target are sent to an information processor of the system. The processor controls a photoelectric device turntable to turn according to the azimuth and pitch information provided by the radar. After the turntable stops turning, the target is observed and target recognition is performed through image information. Meanwhile, intelligent comprehensive judgment is performed according to the position of the target mapped on the map. If the target is on a road on the map, the target is more likely to be a vehicle or a person. If the target is in a wilderness, the target is more likely to be an animal such as a cow or a horse. If the target is in a mountainous area, the target is more likely to be a false target such as a rock. The position on the map is divided into regions, the target type weight values of different regions are different, and the target type is comprehensively judged according to the radar information, photoelectric information and map region information, so that the recognition is more accurate.
[0034] The logical sequence of target category judgment is as follows. First, the radar target type is compared with the photoelectric target type. If they are consistent, the target type judgment is completed. If the result is inconsistent, the target type judgment of the map is introduced. If the result is still inconsistent, a weighted algorithm is used for judgment, and finally the target type is determined.
[0035] Based on the above technical scheme, the light and radar integrated system three-dimensional target recognition method effectively utilizes the three-dimensional information of the map, intelligently judges the target type, makes up for the deficiencies of the light and radar integrated system affected by weather and other factors, and thus improves the accuracy and robustness of the system in target recognition. At the same time, the accuracy, adaptability and anti-interference ability of the system in complex environments are improved.
[0036] Reference Figure 3 Corresponding to the light and radar integrated system three-dimensional target recognition method embodiment, an embodiment of the present application provides a light and radar integrated system three-dimensional target recognition device, which comprises: A radar module 1001 is configured to search for a target based on a radar device and acquire target information. The target information includes distance, azimuth, pitch and speed information and a first target type. A photoelectric module 1002 is configured to receive the target information, control a photoelectric device turntable to turn to the target direction according to the corresponding information, perform image recognition on the target region, and obtain a second target type of photoelectric target recognition. A GIS map module 1003 is configured to map the target information to a preset GIS map and obtain the position information of the target. The GIS map is configured to divide regions according to detailed information of the map, and different target types are preset with different weight values in each region. The target type determination module 1004 is configured to determine a final target type based on the first target type, the second target type and the position information.
[0037] Further, the target type determination module 1004 is specifically configured to: If the first target type is consistent with the second target type, the type is confirmed as the final target type; If the first target type is inconsistent with the second target type, the target type is determined according to a weight value of a target type corresponding to a map region of the position information; If the target type cannot be determined according to the weight value of the target type corresponding to the GIS map region, a comprehensive confidence is calculated based on the first target type, the second target type and the weight value of different target types in the region, and a type exceeding a set threshold is taken as the final target type.
[0038] Further, the GIS map is configured to be divided into regions according to detailed information of the map, and each region is preconfigured with weight values of different target types, including: If the target is located in a highway region, the weight values of the vehicle and pedestrian categories are higher than those of the animal or static object; If the target is located in a wilderness region, the weight value of the animal category is higher than those of the vehicle, pedestrian or static object; If the target is located in a mountain region, the weight value of the static object category is higher than those of the vehicle, pedestrian or animal.
[0039] Further, before the second target type obtained by the photoelectric target recognition is obtained, if the photoelectric device fails to find the target, the step of obtaining the target information based on the radar device scanning and searching is returned.
[0040] The above-mentioned optical-radar integrated system three-dimensional target recognition device realizes the steps and each process of the above-mentioned optical-radar integrated system three-dimensional target recognition method embodiments, and can achieve the same technical effects. To avoid repetition, details are not repeated here.
[0041] Referring to Figure 4 Corresponding to the above-mentioned optical-radar integrated system three-dimensional target recognition method embodiments, the embodiments of the present application provide an electronic device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor. The computer program is executed by the processor to realize the steps and each process of the above-mentioned optical-radar integrated system three-dimensional target recognition method embodiments, and can achieve the same technical effects. To avoid repetition, details are not repeated here.
[0042] The memory 1009 can be used to store software programs and various data. The memory 1009 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), etc. In addition, the memory 1009 can include a volatile memory or a non-volatile memory, or the memory 1009 can include both volatile and non-volatile memories. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable Programmable ROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synchlink DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 1009 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.
[0043] The processor 1010 can include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 1010.
[0044] Corresponding to the above-mentioned embodiments of the three-dimensional target recognition method of the light and radar integrated system, the embodiments of the present application also provide a readable storage medium, the readable storage medium stores programs or instructions, the programs or instructions are executed by a processor to realize the steps and various processes of the above-mentioned embodiments of the three-dimensional target recognition method of the light and radar integrated system, and the same technical effects can be achieved. To avoid repetition, details are not repeated here.
[0045] The processor is the processor in the electronic device described in the embodiments of the present application. The readable storage medium includes a computer readable storage medium, such as a computer readable only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0046] It should be noted that, in this document, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that includes the element. In addition, it should be noted that the scope of the methods and apparatus of the present embodiments are not limited by the order of the steps or the sequences for performing the steps, and can include performing the steps in different order, or substantially concurrently, or in reverse order, or omitting, adding to, or combining steps, such as described with respect to the examples. Furthermore, features described with respect to certain examples can be combined in other examples.
[0047] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and necessary general hardware platforms, of course, they can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a plurality of instructions for making a terminal (which can be a mobile phone, computer, server, or network device, etc.) execute the methods described in the embodiments of the present application.
[0048] It can be understood that the embodiments of the present application are described above in conjunction with the drawings, but the present application is not limited to the above specific embodiments, and the above specific embodiments are only illustrative, not restrictive. Those skilled in the art know that various changes or equivalent replacements can be made to the features and embodiments without departing from the spirit and scope of the present application. In addition, those skilled in the art can modify the features and embodiments to adapt to specific conditions and materials under the inspiration or guidance of the present application without departing from the spirit and scope of the present application. Therefore, the present application is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of the present application are within the scope of the present application.
Claims
1. A three-dimensional target recognition method for an integrated optical-mining system, characterized in that: include: Scan and search targets based on radar equipment to obtain target information; The target information includes: distance, azimuth, pitch and speed information and the first target type; Receive the target information; control the photoelectric device turntable to turn to the target direction according to the corresponding information and perform image recognition on the target area to obtain a second target type for photoelectric target recognition; Mapping the target information to a pre-set GIS map to obtain the target's location information; wherein the GIS map is configured to divide the area according to the detailed information of the map, and each area has a preset weight value for different target types; A final target type is comprehensively determined based on the first target type, the second target type and the location information.
2. The three-dimensional target recognition method of the integrated light-thunder system according to claim 1, characterized in that: The comprehensively determining the final target type according to the first target type, the second target type and the location information includes: If the first target type is consistent with the second target type, confirming the type as the final target type; If they are inconsistent, the target type is determined according to the weight value of the target type corresponding to the map area where the location information is located; If the target type cannot be determined based on the weight value of the target type corresponding to the target in the GIS map area, the comprehensive confidence is calculated based on the weight values of the first target type, the second target type and the different target types in the area, and the type that exceeds the set threshold is used as the final target type.
3. The three-dimensional target recognition method of the integrated light-thunder system according to claim 1, characterized in that: The GIS map is configured to divide regions according to detailed information on the map, and each region is preset with weight values for different target types, including: If the target is located in a road area, the weight of vehicles and pedestrians is higher than that of animals or static objects; If the target is located in a wilderness area, the weight of the animal category is higher than that of vehicles, pedestrians, or static objects; If the target is located in a mountainous area, the static object category is given a higher weight than vehicles, pedestrians, or animals.
4. The three-dimensional target recognition method of the integrated light-thunder system according to claim 1, characterized in that: Before obtaining the second target type for optoelectronic target identification, if the optoelectronic device fails to find the target, the process returns to the step of scanning and searching for the target based on the radar device to obtain target information.
5. A three-dimensional target recognition device for a light-thunder integrated system, characterized in that: include: Radar module, used to scan and search for targets based on radar equipment and obtain target information; The target information includes: distance, azimuth, pitch and speed information and the first target type; The optoelectronic module is configured to receive the target information; control the optoelectronic device turntable to rotate to the target direction according to the corresponding information and perform image recognition on the target area to obtain a second target type for optoelectronic target recognition; A GIS map module is used to map target information to a pre-set GIS map to obtain the target's location information; wherein the GIS map is configured to divide the area according to the detailed information of the map, and each area is preset with a weight value for different target types; The target type determination module is used to comprehensively determine the final target type based on the first target type, the second target type and the position information.
6. The three-dimensional target recognition device of the integrated light-thunder system according to claim 5, characterized in that: The target type determination module is specifically used to: If the first target type is consistent with the second target type, confirming the type as the final target type; If they are inconsistent, the target type is determined according to the weight value of the target type corresponding to the map area where the location information is located; If the target type cannot be determined based on the weight value of the target type corresponding to the target in the GIS map area, the comprehensive confidence is calculated based on the weight values of the first target type, the second target type and the different target types in the area, and the type that exceeds the set threshold is used as the final target type.
7. The three-dimensional target recognition device of the integrated light-thunder system according to claim 5, characterized in that: The GIS map is configured to divide regions according to detailed information on the map, and each region is preset with weight values for different target types, including: If the target is located in a road area, the weight of vehicles and pedestrians is higher than that of animals or static objects; If the target is located in a wilderness area, the weight of the animal category is higher than that of vehicles, pedestrians, or static objects; If the target is located in a mountainous area, the static object category is given a higher weight than vehicles, pedestrians, or animals.
8. The three-dimensional target recognition device of the integrated light-thunder system according to claim 5, characterized in that: Before obtaining the second target type for optoelectronic target identification, if the optoelectronic device fails to find the target, the process returns to the step of scanning and searching for the target based on the radar device to obtain target information.
9. An electronic device, characterized in that: The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the three-dimensional target recognition method of the integrated optical-radar system as claimed in any one of claims 1 to 4 are implemented.
10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the three-dimensional target recognition method of the integrated optical-radar system as claimed in any one of claims 1 to 4 are implemented.