Radar target detection method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose a radar target detection method and device, electronic equipment and storage medium. The radar target detection method comprises: determining whether at least two candidate objects exist in the collected radar data, the speed difference of the at least two candidate objects being less than a preset speed threshold, and the distance difference of the at least two candidate objects in the longitudinal direction being greater than a preset distance; if so, determining a candidate object image detection result of a corresponding position in image information collected by the image collection device according to candidate position information of the at least two candidate objects determined by the radar device; and determining a target object from the candidate objects according to the candidate object image detection result. The embodiments of the present application improve the accuracy of the radar detection result, and reduce the difficulty of processing the multipath effect problem on the radar algorithm side.

Description

Technical Field

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

[0002] When a radar emits electromagnetic waves for target detection, multiple reflections occur between the radar and the target, as well as between different targets. This results in a multipath effect during radar detection, causing anomalies in the actual echo frequency and phase, ultimately leading to inaccurate radar detection results.

[0003] For example, there are currently a large number of strong electromagnetic wave reflectors such as large metal billboards, traffic lights, streetlights, and metal guardrails on urban roads and highways. These strong reflectors are very likely to cause multipath effects. When the radar detects a target approaching these strong reflectors, multiple reflections will generate false targets behind the detected target, affecting the radar's detection performance. Moreover, the false targets generated by multipath effects often do not follow a direct pattern, increasing the difficulty for the radar algorithm to handle the multipath effect problem. Summary of the Invention

[0004] This invention provides a radar target detection method, apparatus, electronic device, and storage medium, which improves the accuracy of radar detection results and reduces the difficulty of handling multipath effects in radar algorithms.

[0005] In a first aspect, embodiments of the present invention provide a radar target detection method, executed by a radar device equipped with an image acquisition device, comprising:

[0006] Determine whether there are at least two candidate objects in the collected radar data whose velocity difference is less than a preset velocity threshold, and whether the longitudinal distance difference between at least two candidate objects is greater than a preset distance;

[0007] If they exist, the image detection result of the candidate object at the corresponding position in the image information acquired by the image acquisition device is determined based on the candidate position information of the at least two candidate objects determined by the radar device.

[0008] The target object is determined from the candidate objects based on the candidate object image detection results.

[0009] Secondly, embodiments of the present invention also provide a radar target detection device, executed by a radar device equipped with an image acquisition device, comprising:

[0010] The candidate object module is used to determine whether there are at least two candidate objects in the collected radar data whose velocity difference is less than a preset velocity threshold, and the longitudinal distance difference between at least two candidate objects is greater than a preset distance.

[0011] An image detection module is used to determine, if present, the image detection result of the candidate object at the corresponding position in the image information acquired by the image acquisition device, based on the candidate position information of the at least two candidate objects determined by the radar device.

[0012] The target object determination module is used to determine the target object from the candidate objects based on the candidate object image detection results.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, comprising:

[0014] One or more processors;

[0015] Storage device for storing one or more programs.

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the radar target detection method as described in any embodiment of the present invention.

[0017] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the radar target detection method as described in any embodiment of the present invention.

[0018] This invention determines whether there are at least two candidate objects in the collected radar data whose velocity difference is less than a preset velocity threshold, and at least two candidate objects whose longitudinal distance difference is greater than a preset distance. If so, based on the candidate position information of the at least two candidate objects determined by the radar device, the image detection result of the corresponding position in the image information collected by the image acquisition device is determined. The target object is then determined from the candidate objects based on the candidate object image detection result. This invention uses a combination of radar and image acquisition equipment to eliminate false targets caused by multipath effects, improving the accuracy of radar detection results and reducing the difficulty of handling multipath effects in the radar algorithm. It also leverages the advantages of both sensors to provide more comprehensive digital road information. Attached Figure Description

[0019] Figure 1 This is a flowchart of the radar target detection method in Embodiment 1 of the present invention;

[0020] Figure 2 This is a schematic diagram of the radar target detection device in Embodiment 2 of the present invention;

[0021] Figure 3 This is a schematic diagram of the electronic device in Embodiment 3 of the present invention. Detailed Implementation

[0022] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0023] Example 1

[0024] Figure 1 This is a flowchart of a radar target detection method according to Embodiment 1 of the present invention. This embodiment is applicable to the situation where false targets generated by multipath effects are eliminated during radar equipment detection. The method is executed by a radar device equipped with an image acquisition device. This method can be executed by a radar target detection device, which can be implemented in software and / or hardware, and can be configured in a radar device equipped with an image acquisition device. For example, the radar device can be a device with communication and computing capabilities.

[0025] Radar equipment and image acquisition devices each have their own advantages and disadvantages. Radar equipment can effectively measure the speed and distance of objects, while image acquisition devices do not have the same significant advantage in speed and distance measurement. However, image acquisition devices are more effective at determining the type and characteristics of objects, thus necessitating the use of radar equipment in certain scenarios. However, the use of radar equipment is accompanied by multipath effects. In this embodiment of the invention, the radar equipment with image acquisition devices is configured around the radar equipment's installation location. The installation positions of the image acquisition devices and the radar equipment should maximize the overlap between the image acquisition range of the image acquisition devices and the data acquisition range of the radar equipment.

[0026] like Figure 1 As shown, the method specifically includes:

[0027] Step 101: Determine whether there are at least two candidate objects in the collected radar data whose velocity difference is less than a preset velocity threshold, and whether the longitudinal distance difference between at least two candidate objects is greater than a preset distance.

[0028] In this embodiment of the invention, the advantages of using radar equipment for target object detection are more obvious. For example, it is necessary to collect data such as the speed and distance of the target object. Therefore, radar equipment is the main device for target object detection. However, due to multipath effects, the radar equipment may include false targets in the collected radar data when identifying the target object. That is, the radar data contains data of the false target, but the false target does not actually exist. Therefore, in this embodiment of the invention, an image acquisition device is used to assist in the removal of the radar data of the false target, thereby improving the accuracy of the radar equipment in detecting the target object and avoiding interference from the radar data of the false target. Therefore, the image acquisition device is an auxiliary device for target object detection. Simply relying on the image acquisition device to detect the target object does not meet the detection requirements.

[0029] Specifically, the radar data collected by the radar equipment is identified to obtain all included objects. If at least two objects have similar velocities (i.e., the velocity difference is less than a preset velocity threshold), and the longitudinal distance between these two or more objects is greater than a preset distance, then these objects are identified as candidate objects. Among the candidate objects, there may be spurious objects generated by multipath effects; that is, a candidate object located behind may be a spurious object generated by a candidate object located in front due to radar multipath effects. The preset velocity threshold and preset distance are set according to the actual situation. The preset velocity threshold indicates that the velocities of the two objects are close, and the velocity difference is within a certain tolerance range. The preset longitudinal distance indicates that the candidate object is in the front-back direction, not in the parallel direction, because spurious objects generated by multipath effects are generally located behind the real objects.

[0030] For example, identification is performed based on radar data collected by radar equipment. The target object is determined from the radar data based on the characteristics of the target to be identified. After the target object is determined, since the multipath effect mostly occurs behind the target object, the radar data is used to search for objects with similar speeds to the target object behind the determined target object. If such objects exist, they are identified as candidate objects. The objects behind the target object may be false targets.

[0031] In one feasible embodiment, prior to step 101, the method further includes:

[0032] Determine the detection results of high-energy reflectors on the tested road section;

[0033] If a high-energy reflector exists, then candidate objects are determined.

[0034] High-energy reflectors are objects that strongly reflect electromagnetic waves emitted by radar. For example, most high-energy reflectors are metallic objects, such as large metal billboards, traffic lights, streetlights, and metal medians found in road environments. In road environments with high-energy reflectors like these, multipath effects are very likely to occur when a target passes through the area, creating false targets and reducing radar detection performance. Conversely, if there are no high-energy reflectors in the road environment, multipath effects are less likely to occur when a target passes through the area.

[0035] Specifically, high-energy reflectors on the detection section set up by the radar equipment are pre-detected. If a high-energy reflector is present, it indicates that the detection section is prone to multipath effects, and candidate targets are identified, i.e., whether false targets exist. If no high-energy reflector is present, it indicates that multipath effects rarely occur on the detection section, and therefore, it is not necessary to identify false targets; all targets detected by the radar equipment are considered real targets. The detection of high-energy reflectors on the detection section can be performed manually or through an image acquisition device. For example, image information of the detection section can be pre-acquired using an image acquisition device, and the presence of high-energy reflectors can be determined by classifying and identifying objects in the image information. When manually determining the presence of high-energy reflectors on the detection section, the image acquisition device may not be activated. The activation status of the image acquisition device is determined based on the manually determined high-energy reflector detection results and the candidate target identification results, in order to avoid false detections caused by the image acquisition device being constantly activated, which could interfere with the radar equipment's detection results.

[0036] Step 102: If they exist, then based on the candidate position information of at least two candidate objects determined by the radar equipment, determine the image detection result of the candidate object at the corresponding position in the image information acquired by the image acquisition device.

[0037] Here, candidate location information refers to the actual location coordinates of a candidate object determined by the radar equipment, and corresponding location refers to the corresponding location of the candidate object in the image determined based on these actual location coordinates. That is, if the candidate object is a real target object, then image information of the candidate object should also exist at the corresponding location in the image information; otherwise, the candidate object is a false target object. The candidate object image detection result refers to the result of whether candidate object image information exists at the corresponding location.

[0038] Specifically, if the radar equipment detects at least two candidate objects with similar velocities and positions in a front-to-back direction, it determines their candidate position information based on the radar equipment, identifies their corresponding positions in the image, and determines whether candidate object image information exists at those corresponding positions. Candidate object image information refers to whether a real object exists at each candidate position. If candidate object image information exists at a corresponding position in the image, the detection result for that position is that a real object exists; otherwise, it is determined that no real object exists. The existence of candidate object image information at a corresponding position means that an object exists at that position, and the object's features match the object features of the candidate object. The object features of the candidate object can be determined by the radar equipment or pre-determined according to detection requirements.

[0039] For example, if there is a candidate object with a similar speed behind the target object detected by the radar equipment, the corresponding position in the image is determined based on the candidate position information, and it is determined whether there is an object at the corresponding position in the image. If there is an object, it is determined whether the object matches the target object based on the object features of the target object. If there is no match or there is no object at the corresponding position, the candidate object image detection result is determined to be that there is no real object at the candidate position information. If the object matches the object features of the target object, the candidate object image detection result is determined to be that there is a real object at the candidate position information.

[0040] In one feasible embodiment, before determining the image detection result of the candidate object at the corresponding position in the image information acquired by the image acquisition device based on the candidate position information of at least two candidate objects determined by the radar device, the method further includes:

[0041] Determine the type detection results of the radar equipment and / or image acquisition device for the candidate objects;

[0042] If the type detection result is a preset vehicle model, then the candidate object image detection result is determined;

[0043] Otherwise, the candidate object image detection results will not be determined.

[0044] If the target itself does not strongly reflect the electromagnetic waves emitted by the radar, then this type of target is not prone to multipath effects, even when there are high-energy reflectors in the detection section. Therefore, before determining the candidate object image detection results in conjunction with the image acquisition device, the type of the candidate object should be judged to determine whether it has strong reflectivity.

[0045] The preset vehicle type refers to a vehicle that strongly reflects the electromagnetic waves emitted by radar, such as container trucks, large trucks, and buses—vehicles carrying strong metallic targets. The preset vehicle type can be set according to actual detection needs and is not restricted here.

[0046] Specifically, before determining the candidate object image detection result, the type detection result of the candidate object is first determined. If the candidate object is a pre-determined preset vehicle model with strong reflectivity, then the candidate object image detection result is determined; otherwise, it is considered that there are no false target objects among the candidate objects, and the candidate object image detection result is not determined. For example, according to the pre-determined detection requirements, if it is determined that the type of object to be detected by the radar equipment is not a preset vehicle model, then the determination of the candidate object in step 101 is not necessary. The detection object can be determined directly based on the radar data collected by the radar equipment, and the determination of false target objects is not required. The radar equipment and / or image acquisition device are determined.

[0047] The determination of the type detection result of the candidate object can be based solely on the detection results of the radar equipment or the detection results of the image acquisition device, or it can be determined by combining the detection results of the radar equipment and the image acquisition device. No restriction is imposed here.

[0048] In one feasible embodiment, determining the type detection results of the radar equipment and image acquisition device for the candidate object includes:

[0049] If the detection results of the radar equipment and the image acquisition device are different, the type detection result of the candidate object is determined according to the preset weights of the radar equipment and the image acquisition device.

[0050] If a method combining the detection results of radar equipment and image acquisition device is used to determine the type detection result of candidate objects, and the detection results of radar equipment and image acquisition device are different, the final type detection result of candidate objects is determined based on the weighted result of the detection results of different devices.

[0051] The preset weights for the radar equipment and image acquisition device are pre-determined based on the detection reliability of the equipment. For example, if the preset weight of the radar equipment is set to 0.4 and the preset weight of the image acquisition device is set to 0.6, the probability that the radar equipment determines the candidate object to be a preset vehicle model is 0.8, and the probability that the image acquisition device determines the candidate object to be a preset vehicle model is 0.5. The detection result of the radar equipment is that the candidate object is a preset vehicle model, and the detection result of the image acquisition device is that the candidate object is not a preset vehicle model. The weighted result of the detection results is: 0.4*0.8+0.6*0.5=0.62. The preset threshold is 0.7. Therefore, the weighted result of the detection results of different devices determines the final type detection result of the candidate object as not being a preset vehicle model.

[0052] By comprehensively determining the type detection results of candidate objects using different devices, the accuracy of judging the type of candidate objects is improved.

[0053] In one feasible embodiment, after determining the radar device's type detection result for the candidate object, the method further includes:

[0054] If the type detection result is the preset vehicle model, then the image acquisition function of the image acquisition device is activated to determine the image detection result of the candidate object.

[0055] If the method of determining the type detection result of the candidate object is based solely on the detection result of the radar equipment, then in order to avoid the waste of resources and false detections caused by the long-term operation of the image acquisition device, the image acquisition function of the image acquisition device should be turned off.

[0056] If the radar equipment detects a candidate object that is a preset vehicle model, the image acquisition function of the image acquisition device is activated to identify false target objects. For example, if there is a high-energy reflector on the detected road section, the detected object is a preset vehicle model, and there are at least two candidate objects with similar speeds and positions in the front and rear directions, the image acquisition function of the image acquisition device is activated. If none of the conditions are met, it means that it is not necessary to identify false target objects, and the objects detected by the radar equipment are considered to be real target objects, thereby improving detection efficiency.

[0057] Step 103: Determine the target object from the candidate objects based on the candidate object image detection results.

[0058] Since the candidate object image detection result refers to the result of whether candidate object image information exists at the corresponding position, it can be determined whether the object actually exists in the image information acquired by the image acquisition device based on the candidate object image detection result. If the object actually exists in the image, the candidate object is determined to be the target object, that is, the real target object; if the object does not exist in the image, the candidate object is determined to be a false object.

[0059] For example, if a candidate object with a similar velocity exists behind the target object detected by the radar device, the corresponding position in the image is determined based on the candidate position information. If it is determined that there is no object at the corresponding position in the image, or that there is an object but its features do not match the object features of the target object, then the candidate object image detection result is determined to be that there is no real target object at the candidate position information corresponding to that position, and the data of that candidate object in the radar data is removed. If there is an object at the corresponding position in the image and its features match the object features of the target object, then the candidate object image detection result is determined to be that there is a real target object at the candidate position corresponding to that position, and the candidate object in the radar data is determined to be a real target object.

[0060] In one feasible embodiment, step 103 includes:

[0061] If the candidate object image detection result shows that no candidate object is detected at the corresponding position of at least one candidate object, then the candidate object is determined to be a false target object, and the false target object is deleted from the radar data.

[0062] If the candidate image detection result for at least one candidate object is that no candidate object image information exists at the corresponding location, then the candidate object at that corresponding candidate location is determined to be a false target object, and its radar data is deleted. If the candidate image detection result for at least one candidate object is that candidate object image information exists at the corresponding location, then the candidate object at that corresponding candidate location is determined to be the target object, i.e., the real object.

[0063] In one feasible embodiment, step 103 includes:

[0064] If the candidate object image detection result is that no candidate object is detected at the corresponding position of at least one candidate object in a consecutive preset number of frames, then the candidate object is determined to be a false target object, and the false target object is deleted from the radar data.

[0065] Since image detection has a certain probability of false detection, judging whether a candidate object is a false target object based on whether it is detected at a corresponding position in a frame of an image will result in false detections. Therefore, in this embodiment of the invention, if the candidate object is not detected at the corresponding position of any candidate object in at least two consecutive frames, the candidate object is determined to be a false target object; otherwise, the candidate object is determined to be a real target object. The preset number of frames can be determined according to the detection accuracy and detection requirements, and is not limited here.

[0066] For example, after identifying candidate objects, a video of a preset length is acquired using an image acquisition device. If no candidate object is detected at any position corresponding to the candidate location information in the video, the candidate object is determined to be a false target object. The preset length of the video is determined based on the detection accuracy and requirements, and is not limited here.

[0067] This invention uses a combination of radar and image acquisition equipment to eliminate false targets caused by multipath effects, improving the accuracy of radar detection results and reducing the difficulty of handling multipath effects in radar algorithms. At the same time, it leverages the advantages of both sensors to provide more comprehensive digital road information.

[0068] This invention provides a feasible implementation method, as detailed below:

[0069] The image acquisition device is turned on at the beginning of the detection process. First, the image acquisition device determines whether there are high-energy reflectors on the road section detected by the radar equipment. If they are found, the road section is determined to be a section with frequent multipath effects, and subsequent candidate object detection is carried out. If they are not found, there is no need to detect candidate objects, and the target object can be detected directly based on the radar data.

[0070] After determining that the detection section is a section where multipath effects frequently occur, the vehicle types in the detection area are comprehensively detected by radar and image acquisition devices. If a vehicle of a preset type exists in the detection area, the objects behind that vehicle are detected. If a vehicle of the same type with a similar speed exists, that vehicle is identified as a candidate object.

[0071] After identifying candidate targets, the system uses video information acquired by the image acquisition device to determine whether the vehicle exists at the image location corresponding to the candidate position in the radar. If it exists, the candidate target is determined to be a real target; otherwise, the candidate target is determined to be a false target, a false target generated by the multipath effect of the vehicle ahead.

[0072] This invention provides another feasible implementation method, as detailed below:

[0073] The image acquisition device is initially turned off. Other methods are used to pre-determine whether there are high-energy reflectors on the road section to be detected by the radar equipment. If they are found, the road section is identified as a section with frequent multipath effects, and subsequent candidate object detection is carried out. If they are not found, there is no need to detect candidate objects, and the target object can be detected directly based on the radar data.

[0074] After determining that the detection section is a section where multipath effects frequently occur, the radar is used to detect the vehicle type in the detection area. If a vehicle of a preset type exists in the detection area, the objects behind that vehicle are detected. If a vehicle of the same type with a similar speed exists, that vehicle is identified as a candidate object.

[0075] After identifying the candidate target, the image acquisition function of the image acquisition device is activated. Based on the acquired video information, it is determined whether the vehicle exists at the image position corresponding to the candidate position of the candidate target in the radar. If it exists, the candidate target is determined to be a real target; if it does not exist, the candidate target is determined to be a false target, a false target generated by the multipath effect of the vehicle in front.

[0076] By controlling the activation of the image acquisition device and the activation of false target detection, the accuracy and efficiency of radar target detection are improved. On the one hand, controlling the activation of the image acquisition device avoids false detection caused by the long-term operation of the image acquisition device. On the other hand, controlling the activation of false target detection avoids the determination of candidate objects and the impact of determination on target detection when there is no multipath effect.

[0077] This invention employs a radar-visual fusion scheme. If the radar generates false targets due to multipath effects, and these are difficult to process at the radar algorithm level, the video feed can detect in real time whether a real target exists at the false alarm location. By using multi-sensor fusion, optical images captured by a camera are used to assist in eliminating false targets generated by the radar due to multipath effects, greatly reducing the difficulty of handling multipath problems at the radar algorithm level. At the same time, the advantages of each sensor are utilized to compensate for their shortcomings, providing more comprehensive digital road information. For example, image information provided by the camera can be used to identify vehicle types, license plates, and other detection effects that radar cannot achieve.

[0078] The image acquisition device in this embodiment of the invention can be a regular camera, or a zoom camera such as a zoom camera or a pan-tilt camera. For example, if the target is far away and a regular camera cannot clearly detect it, a solution combining a zoom camera (such as a pan-tilt camera) and radar can be used to comprehensively cover both near and far ranges, thus avoiding the problem that a regular camera cannot identify targets at a distance.

[0079] Example 2

[0080] Figure 2 This is a schematic diagram of the radar target detection device in Embodiment 2 of the present invention. This embodiment is applicable to the situation where false targets generated by multipath effects are eliminated during radar equipment detection, and is performed by radar equipment equipped with an image acquisition device. Figure 2 As shown, the device includes:

[0081] The candidate object module 210 is used to determine whether there are at least two candidate objects in the collected radar data whose velocity difference is less than a preset velocity threshold, and at least two candidate objects whose longitudinal distance difference is greater than a preset distance.

[0082] The image detection module 220 is used to determine the image detection result of the candidate object at the corresponding position in the image information acquired by the image acquisition device, based on the candidate position information of the at least two candidate objects determined by the radar device, if there are at least two candidate objects.

[0083] The target object determination module 230 is used to determine the target object from the candidate objects based on the candidate object image detection results.

[0084] This invention uses a combination of radar and image acquisition equipment to eliminate false targets caused by multipath effects, improving the accuracy of radar detection results and reducing the difficulty of handling multipath effects in radar algorithms. At the same time, it leverages the advantages of both sensors to provide more comprehensive digital road information.

[0085] Optional, the target object determination module is specifically used for:

[0086] If the candidate object image detection result is that no candidate object is detected at the corresponding position of at least one candidate object, then the candidate object is determined to be a false target object, and the false target object is deleted from the radar data.

[0087] Optional, the target object determination module is specifically used for:

[0088] If the candidate object image detection result is that no candidate object is detected at the corresponding position of at least one candidate object in a consecutive preset number of frames, then the candidate object is determined to be a false target object, and the false target object is deleted from the radar data.

[0089] Optionally, the device further includes a candidate object type detection module, configured to, before determining the candidate object image detection result at the corresponding position in the image information acquired by the image acquisition device based on the candidate position information of the at least two candidate objects determined by the radar device, include:

[0090] A type detection result determination unit is used to determine the type detection result of the radar device and / or the image acquisition device for the candidate object;

[0091] The type detection result determination unit is used to determine the candidate object image detection result if the type detection result is a preset vehicle model; otherwise, it does not determine the candidate object image detection result.

[0092] Optional, the type detection result determination unit is specifically used for:

[0093] If the detection results of the radar device and the image acquisition device are different, the type detection result of the candidate object is determined according to the preset weights of the radar device and the image acquisition device.

[0094] Optionally, the device further includes an image acquisition device activation determination module, used to determine the type detection result of the radar device on the candidate object after determining the type detection result of the candidate object.

[0095] If the type detection result is a preset vehicle model, then the image acquisition function of the image acquisition device is activated to determine the candidate object image detection result.

[0096] Optionally, the device further includes a road segment determination module, used to determine whether there are at least two candidate objects in the collected radar data whose speed difference is less than a preset speed threshold, and before the longitudinal distance difference between at least two candidate objects is greater than a preset distance.

[0097] Determine the detection results of high-energy reflectors on the tested road section;

[0098] If a high-energy reflector exists, then candidate objects are determined.

[0099] The radar target detection device provided in the embodiments of the present invention can execute the radar target detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the radar target detection method.

[0100] Example 3

[0101] Figure 3 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. Figure 3 A block diagram is shown of an exemplary electronic device 12 suitable for implementing embodiments of the present invention. Figure 3 The electronic device 12 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0102] like Figure 3 As shown, the electronic device 12 is represented in the form of a general-purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, system storage device 28, and bus 18 connecting different system components (including system storage device 28 and processing unit 16).

[0103] Bus 18 represents one or more of several bus architectures, including a memory device bus or memory device controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0104] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0105] System storage device 28 may include computer system readable media in the form of volatile storage devices, such as random access memory (RAM) 30 and / or cache storage device 32. Electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 3 Not shown; usually referred to as a "hard drive"). Although Figure 3 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Storage device 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0106] A program / utility 40 having a set (at least one) of program modules 42 may be stored in, for example, storage device 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0107] Electronic device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with device 12, and / or with any device that enables device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, electronic device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 3 As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18. It should be understood that, although... Figure 3 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0108] Processing unit 16 executes various functional applications and data processing by running programs stored in system storage device 28, such as implementing the radar target detection method provided in the embodiments of the present invention, which is executed by radar equipment configured with an image acquisition device, including:

[0109] Determine whether there are at least two candidate objects in the collected radar data whose velocity difference is less than a preset velocity threshold, and whether the longitudinal distance difference between at least two candidate objects is greater than a preset distance;

[0110] If they exist, the image detection result of the candidate object at the corresponding position in the image information acquired by the image acquisition device is determined based on the candidate position information of the at least two candidate objects determined by the radar device.

[0111] The target object is determined from the candidate objects based on the candidate object image detection results.

[0112] Example 4

[0113] Embodiment 4 of the present invention also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements the radar target detection method as provided in the embodiments of the present invention, which is executed by a radar device equipped with an image acquisition device, including:

[0114] Determine whether there are at least two candidate objects in the collected radar data whose velocity difference is less than a preset velocity threshold, and whether the longitudinal distance difference between at least two candidate objects is greater than a preset distance;

[0115] If they exist, the image detection result of the candidate object at the corresponding position in the image information acquired by the image acquisition device is determined based on the candidate position information of the at least two candidate objects determined by the radar device.

[0116] The target object is determined from the candidate objects based on the candidate object image detection results.

[0117] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0118] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0119] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0120] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0121] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A radar target detection method, characterized in that, Performed by a radar device equipped with an image acquisition unit, the radar device being installed on the detection section, including: Determine whether there are at least two candidate objects in the collected radar data whose velocity difference is less than a preset velocity threshold, and whether the longitudinal distance difference between at least two candidate objects is greater than a preset distance; If present, the image acquisition function of the image acquisition device is activated, and the image detection result of the candidate object at the corresponding position in the image information acquired by the image acquisition device is determined based on the candidate position information of the at least two candidate objects determined by the radar device. The target object is determined from the candidate objects based on the candidate object image detection results; The method further includes, before determining whether there are at least two candidate objects in the collected radar data whose velocity difference is less than a preset velocity threshold, and whether the longitudinal distance difference between at least two candidate objects is greater than a preset distance: If a high-energy reflector is present on the detection section and the detection target is a preset vehicle type, then candidate targets are determined; the preset vehicle type refers to a vehicle type that has strong reflectivity to the electromagnetic waves emitted by the radar. Otherwise, ensure that all targets detected by the radar equipment are real targets, and determine the target based on the radar data.

2. The method according to claim 1, characterized in that, Determining the target object from the candidate objects based on the candidate object image detection results includes: If the candidate object image detection result is that no candidate object is detected at the corresponding position of at least one candidate object, then the candidate object is determined to be a false target object, and the false target object is deleted from the radar data.

3. The method according to claim 1, characterized in that, Determining the target object from the candidate objects based on the candidate object image detection results includes: If the candidate object image detection result is that no candidate object is detected at the corresponding position of at least one candidate object in a consecutive preset number of frames, then the candidate object is determined to be a false target object, and the false target object is deleted from the radar data.

4. The method according to claim 1, characterized in that, Before determining the image detection result of the candidate object at the corresponding position in the image information acquired by the image acquisition device based on the candidate position information of the at least two candidate objects determined by the radar device, the method further includes: Determine the type detection result of the radar equipment and / or the image acquisition device for the candidate object; If the type detection result is a preset vehicle model, then the candidate object image detection result is determined; Otherwise, the candidate object image detection results will not be determined.

5. The method according to claim 4, characterized in that, Determining the type detection results of the radar equipment and the image acquisition device for the candidate object includes: If the detection results of the radar device and the image acquisition device are different, the type detection result of the candidate object is determined according to the preset weights of the radar device and the image acquisition device.

6. The method according to claim 4, characterized in that, After determining the type detection result of the radar device for the candidate object, the method further includes: If the type detection result is a preset vehicle model, then the image acquisition function of the image acquisition device is activated to determine the candidate object image detection result.

7. A radar target detection device, characterized in that, Performed by a radar device equipped with an image acquisition unit, the radar device being installed on the detection section, including: The candidate object module is used to determine whether there are at least two candidate objects in the collected radar data whose velocity difference is less than a preset velocity threshold, and the longitudinal distance difference between at least two candidate objects is greater than a preset distance. The image detection module is used to activate the image acquisition function of the image acquisition device if it exists, and to determine the image detection result of the candidate object at the corresponding position in the image information acquired by the image acquisition device based on the candidate position information of the at least two candidate objects determined by the radar device. A target object determination module is used to determine a target object from the candidate objects based on the candidate object image detection results; The device further includes a road segment determination module, used to determine whether there are at least two candidate objects in the collected radar data whose speed difference is less than a preset speed threshold, and before the longitudinal distance difference between at least two candidate objects is greater than a preset distance. If a high-energy reflector is present on the detection section and the detection target is a preset vehicle type, then candidate targets are determined; the preset vehicle type refers to a vehicle type that has strong reflectivity to the electromagnetic waves emitted by the radar. Otherwise, ensure that all targets detected by the radar equipment are real targets, and determine the target based on the radar data.

8. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the radar target detection method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the radar target detection method as described in any one of claims 1-6.

Images