Method, apparatus and terminal device for detecting target object type
By acquiring radar scan frame data and performing cluster analysis, the problem of rapid target object type detection by UAVs was solved, achieving low-cost and rapid detection results.
Patent Information
- Application Number
- CN202310362904.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-04-04
- Publication Date
- 2026-01-30
- Estimated Expiration
- 2043-04-04
AI Technical Summary
During drone flight, when the relative speed between the target object and the drone is relatively large, the drone has difficulty quickly detecting the type of the target object in a short period of time, or even if it can detect it quickly, it requires high costs.
By acquiring frame data from radar scans, target points with a reflected energy difference greater than a preset energy threshold are extracted. The distance and Doppler velocity information of the target points are obtained, and the target points are clustered to obtain multiple target families. The type of target object is determined based on the distance and Doppler velocity information of the target families.
It enables rapid detection of target object types in a short time, without the need for expensive radar detectors; detection can be completed using low-cost radar detectors.
Smart Images
Figure CN116299294B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] Embodiments of the present application relate to the technical field of unmanned aerial vehicle, and particularly relate to a method and device for detecting a type of target object and a terminal device. BACKGROUND
[0002] In the process of flying of an unmanned aerial vehicle, when detecting a type of target object on the ground, it is difficult for the unmanned aerial vehicle to quickly detect the type of target object in a short time when the relative speed between the target object and the unmanned aerial vehicle is relatively large. Or, even if the type of target object can be quickly detected, it is at a high cost. SUMMARY
[0003] The present application provides a method and device for detecting a type of target object and a terminal device to solve some or all of the technical problems in the prior art.
[0004] In a first aspect, the present application provides a method for detecting a type of target object, which is executed by a terminal device, and a radar is arranged on the terminal device, and the method comprises the following steps.
[0005] Obtaining frame data scanned by the radar;
[0006] Extracting a target point with a reflection energy difference greater than a preset energy threshold from each frame of frame data;
[0007] Obtaining target point information corresponding to each target point, wherein the target point information comprises distance information and Doppler velocity information;
[0008] Clustering the target points to obtain a plurality of target families;
[0009] Determining a type of target object corresponding to each target family according to the distance information and the Doppler velocity information of each target point in the plurality of target families.
[0010] Optionally, the type of target object comprises a moving target and a stationary target.
[0011] Determining a type of target object corresponding to each target family according to the distance information and the Doppler velocity information of each target point in the plurality of target families, specifically comprising:
[0012] Determining a distance information range corresponding to the target points in the first target family according to the distance information of each target point in the first target family;
[0013] Determining a velocity information range corresponding to the target points in the first target family according to the Doppler velocity information of each target point in the first target family;
[0014] The target object corresponding to the target family with the largest range of distance information and the largest range of Doppler velocity information in the multiple target families is determined as a stationary target, and the target object corresponding to the other target families in the multiple target families except the target family with the largest range of distance information and the largest range of Doppler velocity information is determined as a moving target, wherein the first target family is any one of the multiple target families.
[0015] Optionally, the method further comprises:
[0016] The center distance corresponding to the center target point in the target family corresponding to the moving target is determined according to the distance information corresponding to each target point in the target family corresponding to the moving target.
[0017] The center distance corresponding to the moving target is selected from the adjacent two frames of frame data containing the same moving target.
[0018] The relative position relationship between the moving target and the terminal device is determined according to the center distance corresponding to the moving target selected from the adjacent two frames of frame data.
[0019] Optionally, the center distance corresponding to the center target point in the target family is determined according to the distance information corresponding to each target point in the target family, and specifically comprises:
[0020] The average value of the distance information corresponding to the target points in the target family is obtained as the center distance corresponding to the center target point in the target family.
[0021] Optionally, the relative position relationship between the moving target and the terminal device is determined according to the center distance corresponding to the moving target selected from the adjacent two frames of frame data, and comprises:
[0022] When it is determined that the difference between the first center distance in the frame data collected at a later time and the second center distance in the frame data collected at an earlier time is less than the second preset distance threshold, it is determined that the distance between the moving target and the terminal device gradually decreases.
[0023] Or, when it is determined that the difference between the first center distance and the second center distance is greater than or equal to the second preset distance threshold, it is determined that the distance between the moving target and the terminal device gradually increases.
[0024] Optionally, the target point information further comprises Doppler velocity information; the method further comprises:
[0025] The center velocity information corresponding to the center target point in the target family is determined according to the Doppler velocity information corresponding to each target point in the target family.
[0026] The relative running speed of the moving target compared to the terminal device is determined according to the center velocity information corresponding to the moving target selected from the adjacent two frames of frame data.
[0027] Optionally, the target points are clustered to obtain a plurality of target families, specifically comprising:
[0028] Each target point is taken as a seed point, and the seed connection method is used to cluster the target points to obtain a plurality of target families.
[0029] In a second aspect, the present application provides a device for detecting a type of target object, the device comprising:
[0030] An acquisition module is configured to acquire frame data of radar scanning;
[0031] An extraction module is configured to extract, from each frame of frame data, a target point with a reflection energy difference greater than a preset energy threshold;
[0032] The acquisition module is further configured to acquire target point information corresponding to each target point, wherein the target point information comprises distance information and Doppler velocity information;
[0033] A clustering module is configured to cluster the target points to obtain a plurality of target families;
[0034] A processing module is configured to determine, according to the distance information and the Doppler velocity information corresponding to each target point in the plurality of target families, a type of target object corresponding to each target family.
[0035] In a third aspect, a terminal device is provided, comprising a processor and a memory;
[0036] The memory is configured to store a computer program;
[0037] The processor is configured to execute the program stored on the memory to implement the steps of the method for detecting a type of target object according to any one of the embodiments of the first aspect.
[0038] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method for detecting a type of target object according to any one of the embodiments of the first aspect.
[0039] The above technical solutions provided by the embodiments of the present application have the following advantages compared with the prior art:
[0040] The method provided in this application acquires radar scan frame data and then extracts target points from the frame data whose reflection energy difference is greater than a preset energy threshold. It also acquires target point information for each target point. At least one target point is subjected to simple clustering to obtain multiple target families. A target family is a group of targets corresponding to a target object. That is, this method roughly identifies the number of target objects appearing in the frame data. Then, based on the distance information and Doppler velocity information corresponding to each target point in the multiple target families, the type of target object corresponding to each target family is determined. This method can detect the type of target object in a relatively short time. Furthermore, because this application only utilizes the most basic functions of radar, including acquiring frame data and extracting reflection energy difference and target point information from the frame data, it eliminates the need for high-cost radar detectors; low-cost radar detectors can be used. This achieves rapid detection of target object types at a lower cost. Attached Figure Description
[0041] Figure 1 This is a schematic flowchart of a method for detecting the type of a target object provided in an embodiment of the present invention;
[0042] Figure 2 This invention provides a schematic diagram of a UAV for detecting ground targets.
[0043] Figure 3 A schematic diagram of frame data acquired by radar according to the present invention;
[0044] Figure 4 A simplified schematic diagram containing target points provided by the present invention;
[0045] Figure 5 This is a schematic diagram illustrating the effect of clustering some target points as provided by the present invention.
[0046] Figure 6 This is a schematic diagram illustrating the effect generated after clustering all target points according to the present invention.
[0047] Figure 7 This is a schematic diagram of another method for detecting the type of a target object provided in an embodiment of the present invention;
[0048] Figure 8 This is a schematic diagram of another method for detecting the type of a target object provided in an embodiment of the present invention;
[0049] Figure 9 This is a schematic diagram of another method for detecting the type of a target object provided in an embodiment of the present invention;
[0050] Figure 10A device structure schematic diagram for detecting a target object type is provided for an embodiment of the present application.
[0051] Figure 11 A terminal device structure schematic diagram is provided for an embodiment of the present application. DETAILED DESCRIPTION
[0052] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in a clear and complete manner with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.
[0053] To facilitate the understanding of the embodiments of the present application, further explanation and description will be made with reference to specific embodiments in combination with the drawings. The embodiments do not constitute a limitation on the embodiments of the present application.
[0054] To solve the technical problems mentioned in the background art, the embodiments of the present application provide a method for detecting a target object type, which is specifically described with reference to Figure 1 . Figure 1 A method flow schematic diagram for detecting a target object type is provided for an embodiment of the present application.
[0055] The method is executed by a terminal device, and a radar device is configured on the terminal device. The radar device only needs to meet the basic configuration requirements of the radar. For example, the radar has a scanning function to obtain frame data, and has functions of obtaining reflected energy difference and distance information. In an optional example, the radar can be a low-cost millimeter wave radar. Further optionally, the radar is installed at a certain angle with the horizontal direction.
[0056] In an optional example, the terminal device is, for example, a drone. Specifically, a drone is installed with a radar, and the radar is set at a certain angle with the horizontal direction, as shown in Figure 2 . Figure 2 The radar scans the target object on the ground in the scanning coverage range of the radar. The target object includes a stationary target (including the ground, other stationary objects are also regarded as stationary objects in the ground, and are not specifically identified in the scope of the present application, that is, only to distinguish moving targets and "ground" targets in the present application) and a moving target (such as a vehicle, a walking person, an animal, etc.). Figure 2The diagram illustrates a drone traveling at speed V1 and a vehicle traveling at speed V2. When the radar laser scans the vehicle, the target point corresponding to the vehicle can be extracted from the generated frame data. Here, the target point is defined as one whose reflected energy difference is greater than a preset energy threshold. In an optional example, a value of 9999 can be assigned to any reflected energy difference greater than 0, while no processing is performed if the reflected energy difference is equal to 0.
[0057] The resulting image can be found here. Figure 3 As shown, the horizontal axis represents velocity information, with a velocity range of 0-140; the vertical axis represents distance, with a distance range of 0-300. This is because radar creates scattered laser points when scanning targets on the ground (including the ground itself) with lasers. Figure 3 The colors of the mid-resolution point include gray and light colors. When the laser sweeps across a vehicle, it creates scattered light. When the laser sweeps across the ground, it creates even more scattered light. The energy difference of the reflected light from the scattered light is usually greater than 0. Therefore, as... Figure 3 As shown, Figure 3 The image showing a reflection energy difference greater than 0 represents the portion with "brightness," while the other portions represent areas with zero reflection energy. This is because the ground itself receives more scattered light. Figure 3 The brighter areas shown are the ground, while the slightly dimmer areas correspond to vehicles.
[0058] The method includes the following steps:
[0059] Step 110: Obtain the frame data of the radar scan.
[0060] Step 120: Extract target points from each frame of data whose reflection energy difference is greater than a preset energy threshold.
[0061] Specifically, the reflection energy difference of each resolution point in each frame of data can be obtained through a pre-configured method. Then, as described above, the target points with a reflection energy difference greater than a preset energy threshold can be extracted from each frame of data, which can be done by extracting the resolution points with a reflection energy difference greater than 0 from each frame of data as the target points.
[0062] Step 130: Obtain the target point information corresponding to each target point.
[0063] The target point information includes distance information and Doppler velocity information.
[0064] Specifically, as introduced above, after the laser scanning to the target object, scattering will be formed, and the corresponding speed of the scattering light is the Doppler velocity information corresponding to the target point. A frame of image can include multiple target points. Each target point corresponds to a distance information and a Doppler velocity information, because the means for obtaining the distance information belongs to the conventional means in the field of radar technology, therefore, it will not be explained too much here.
[0065] Step 140, clustering the target points to obtain multiple target families.
[0066] Specifically, in order to more specifically embody the target points and the target families, in the embodiment, the target points are simplified as shown in the following figure, please refer to Figure 4 shown, Figure 4 The multiple black points are used to identify the target points.
[0067] In the process of clustering the target points, multiple clustering methods can be used to achieve.
[0068] Preferably, in the embodiment, the seed connected method is selected to achieve. The schematic diagram of the target points after clustering is shown in Figure 5 and Figure 6 shown, Figure 5 In the figure, the effect schematic diagram of the target points of one of the target families after clustering is first shown, that is, the points belonging to the same target family in the figure are marked as small 1. In the same way, the points belonging to another target family can also be marked as small 2, for example Figure 6 shown.
[0069] Step 150, according to the distance information and the Doppler velocity information corresponding to each target point in the multiple target families, respectively determining the type of the target object corresponding to each target family.
[0070] In an optional example, the type of the target object mainly includes moving targets and stationary targets. As introduced above, the moving targets include vehicles, people or animals and all targets in the process of motion, while the stationary targets are targets that are in a stationary state, and in the embodiment, all stationary objects except the ground are "blurred" and are not considered in the scope of the present application, and the stationary target in the present application is regarded as the ground.
[0071] In the embodiment, the type of the target object is mainly identified, and the moving targets are especially distinguished. Therefore, in an optional implementation, when determining the type of the target object, the following method can be used to achieve, including the following method steps, please refer to Figure 7 shown.
[0072] Step 710: Determine the range of distance information corresponding to the target points in the first target family based on the distance information corresponding to each target point in the first target family.
[0073] Step 720: Determine the velocity information range corresponding to the target points in the first target group based on the Doppler velocity information corresponding to each target point in the first target group.
[0074] Step 730: Determine that the target group with the largest range of distance information and the largest range of Doppler velocity information among multiple target groups is a stationary target, and determine that the target groups other than the target group with the largest range of distance information and the largest range of Doppler velocity information among multiple target groups are moving targets.
[0075] The first target family is any one of multiple target families.
[0076] Specifically, see Figure 3 As shown, when the target object is the ground, its corresponding velocity and distance ranges are the largest compared to other moving objects. This is because the ground itself can produce a large area of reflection, naturally creating more target points. Furthermore, the Doppler velocity and distance information of the resulting target points is also more extensive.
[0077] Therefore, after acquiring multiple target families, the distance information range corresponding to the target points in each target family is first determined based on the distance information of the target points in that target family. Then, the velocity information range corresponding to the target points in that target family is determined based on the Doppler velocity information of the target points in each target family.
[0078] Ultimately, the target family with the largest range of both distance and Doppler velocity information was selected from multiple target families. The target object corresponding to this family is naturally the ground, i.e., a stationary target. All other target families correspond to moving targets. This conclusion can also be drawn from... Figure 3 Verification yielded, for example Figure 3 The speed information corresponding to the ground ranges from 80 to 130, while the speed information of the moving target ranges from 45 to 60; similarly, the distance information corresponding to the ground ranges from 30 to 50, while the distance information of the moving target ranges from 40 to 50.
[0079] Further optionally, in addition to determining whether the target object is a moving target or a stationary target, embodiments of this application can also determine the relative positional relationship between the moving target and the terminal device. For example, whether it is moving away from the terminal device or moving closer to the terminal device.
[0080] In one optional implementation, the method steps may include the following, see details below.Figure 8 As shown, comprising:
[0081] Step 810, according to the distance information corresponding to each target point in the target family corresponding to the moving target, determine the center distance corresponding to the center target point.
[0082] In an optional embodiment, after determining the distance information corresponding to each target point in the target family, the center distance of the center target point can be obtained by averaging.
[0083] That is, the following formula is used to calculate:
[0084]
[0085] Wherein, C R is the center distance of the center target point, R i is the distance information corresponding to the i-th target point, and n is the number of target points in the target family.
[0086] Of course, in addition to the average of the distance information of all target points, other methods can also be used, for example, only the average of the distance information of several target points is selected as the center distance of the center target point, and the selected target points are also the nearest target points to the center target point.
[0087] Step 820, from the adjacent two frames of frame data containing the same moving target, respectively select the center distance corresponding to the moving target.
[0088] Step 830, according to the center distance corresponding to the moving target selected from the adjacent two frames of frame data, determine the relative position relationship between the moving target and the terminal device.
[0089] In an optional embodiment, when the relative position relationship between the moving target and the terminal device is determined according to the center distance corresponding to the moving target in the adjacent two frames of frame data, the following method steps are included:
[0090] When it is determined that the difference between the first center distance in the frame data collected later and the second center distance in the frame data collected earlier in the adjacent two frames of frame data is less than the second preset distance threshold, it is determined that the distance between the moving target and the terminal device gradually decreases.
[0091] Or, when it is determined that the difference between the first center distance and the second center distance is greater than or equal to the second preset distance threshold, it is determined that the distance between the moving target and the terminal device gradually increases.
[0092] The second preset distance threshold is set to 0 for example, that is, when the difference between the first center distance and the second center distance is less than 0, it indicates that the distance between the moving target and the aircraft is getting closer and closer, and the moving target is approaching the aircraft, otherwise, if the difference is greater than or equal to 0, it indicates that the distance between the moving target and the aircraft is getting farther and farther, that is, the moving target is moving away from the aircraft.
[0093] Further optionally, the method can further include the following method steps, please refer to Figure 9 as shown:
[0094] Step 910, according to the Doppler velocity information corresponding to each target point in the target family, determining the center velocity information corresponding to the center target point in the target family.
[0095] The specific calculation method is similar to the calculation of the center distance information corresponding to the center target point, that is, the average value can be obtained, please refer to the following:
[0096]
[0097] Wherein, C V is the center velocity information corresponding to the center target point, V i is the Doppler velocity corresponding to the i-th target point in the target family, and n is the total number of target points in the target family.
[0098] Step 920, according to the center velocity information corresponding to the moving target respectively selected in the adjacent two frames of frame data, determining the relative running speed of the moving target compared with the terminal device.
[0099] Specifically, the difference between the center velocity information corresponding to the moving target respectively selected in the adjacent two frames of frame data can be taken as the relative running speed of the moving target compared with the terminal device.
[0100] For example, if the moving target is gradually approaching the unmanned aerial vehicle, the unmanned aerial vehicle can determine that the moving target is approaching at a speed of 10 m / s or 50 m / s. Further, the unmanned aerial vehicle can execute other operations according to the relative running speed between itself and the moving target.
[0101] The method for detecting the type of the target object provided in the embodiments of the present application comprises the following steps: acquiring frame data scanned by a radar, extracting a target point with a reflection energy difference greater than a preset energy threshold from the frame data, and acquiring target point information corresponding to each target point. At least one target point is clustered to obtain a plurality of target families. The target families correspond to target objects. That is, the number of target objects appearing in the frame data is roughly identified by the method. Then, the type of the target object corresponding to each target family is determined according to distance information and Doppler velocity information corresponding to each target point in the plurality of target families. In this way, the type of the target object can be detected in a short time. Moreover, only the basic functions of the radar are used in the present application, including acquiring frame data, extracting a target point with a reflection energy difference greater than a preset energy threshold, and extracting target point information, and therefore a low-cost radar detector can be used instead of a high-cost radar detector. Thus, the type of the target object can be detected quickly at a low cost.
[0102] The above are several method embodiments for detecting the type of the target object provided in the present application. The following describes other embodiments for detecting the type of the target object provided in the present application. For details, refer to the following.
[0103] Figure 10 The device for detecting the type of the target object provided in the embodiments of the present application comprises an acquisition module 1001, an extraction module 1002, a clustering module 1003, and a processing module 1004.
[0104] The acquisition module 1001 is configured to acquire frame data scanned by a radar.
[0105] The extraction module 1002 is configured to extract a target point with a reflection energy difference greater than a preset energy threshold from each frame of frame data.
[0106] The acquisition module 1001 is further configured to acquire target point information corresponding to each target point, wherein the target point information comprises distance information and Doppler velocity information.
[0107] The clustering module 1003 is configured to cluster the target points to obtain a plurality of target families.
[0108] The processing module 1004 is configured to determine the type of the target object corresponding to each target family according to distance information and Doppler velocity information corresponding to each target point in the plurality of target families.
[0109] Optionally, the type of the target object comprises a moving target and a stationary target.
[0110] The processing module 1004 is specifically configured to determine a distance information range corresponding to the target points in the first target family according to the distance information corresponding to each of the target points in the first target family.
[0111] The processing module 1004 is specifically configured to determine a speed information range corresponding to the target points in the first target family according to the Doppler velocity information corresponding to each of the target points in the first target family.
[0112] The processing module 1004 is specifically configured to determine that a target object corresponding to a target family with the maximum distance information range and the maximum Doppler velocity information range in the multiple target families is a stationary target, and determine that target objects corresponding to other target families except the target family with the maximum distance information range and the maximum Doppler velocity information range in the multiple target families are moving targets, wherein the first target family is any one of the multiple target families.
[0113] Optionally, the processing module 1004 is further configured to determine a central distance corresponding to a central target point according to the distance information corresponding to each of the target points in the target family corresponding to the moving target.
[0114] The processing module 1004 is specifically configured to select the central distance corresponding to the moving target from adjacent two frame data containing the same moving target.
[0115] The processing module 1004 is specifically configured to determine the relative position relationship between the moving target and the terminal device according to the central distance corresponding to the moving target selected from the adjacent two frame data.
[0116] Optionally, the processing module 1004 is specifically configured to obtain an average value of the distance information corresponding to the target points in the target family as the central distance corresponding to the central target point in the target family.
[0117] Optionally, the processing module 1004 is specifically configured to determine that the distance between the moving target and the terminal device gradually decreases when it is determined that a difference between a first central distance in frame data of a later collection time and a second central distance in frame data of an earlier collection time in the adjacent two frame data is less than a second preset distance threshold.
[0118] Or, when it is determined that the difference between the first central distance and the second central distance is greater than or equal to the second preset distance threshold, it is determined that the distance between the moving target and the terminal device gradually increases.
[0119] Optionally, the processing module 1004 is further configured to determine central speed information corresponding to the central target point in the target family according to the Doppler velocity information corresponding to each of the target points in the target family.
[0120] The processing module 1004 is specifically configured to determine the relative running speed of the moving target compared with the terminal device according to the central speed information corresponding to the moving target selected from the adjacent two frame data.
[0121] Optionally, the clustering module 1003 is specifically configured to take each target point as a seed point, and adopt a seed connection method to cluster the target points, so as to obtain a plurality of target families.
[0122] The functions performed by the components in the device for detecting the type of target object provided in the embodiments of the present application have been described in detail in any of the method embodiments, and thus will not be described here again.
[0123] The device for detecting the type of target object provided in the embodiments of the present application obtains frame data scanned by a radar, and then extracts target points with a reflection energy difference greater than a preset energy threshold from the frame data. Target point information of each target point is obtained. At least one target point is simply clustered to obtain a plurality of target families. The target families are target families corresponding to target objects. That is, by this means, the number of target objects appearing in the frame data is roughly identified. Then, the type of target object corresponding to each target family is determined according to distance information and Doppler velocity information of each target point in the plurality of target families. By this method, the type of target object can be detected in a relatively short time. Moreover, because only the basic functions of a radar are used in the present application, including collecting frame data, extracting a reflection energy difference and target point information from the frame data, etc., a low-cost radar detector can be used instead of a high-cost radar detector. Thus, the detection of the type of target object can be quickly completed at a low cost.
[0124] As shown in FIG. 1, Figure 11 The present application provides a terminal device, and the terminal device is provided with a radar 111. The terminal device includes a processor 112 and a memory 113.
[0125] The memory 113 is used to store a computer program.
[0126] In an embodiment of the present application, the processor 112 is used to execute the program stored in the memory 113, so as to implement the method for detecting the type of target object provided in any of the preceding method embodiments, including:
[0127] Obtaining frame data scanned by a radar;
[0128] Extracting target points with a reflection energy difference greater than a preset energy threshold from each frame of frame data;
[0129] Obtaining target point information corresponding to each target point, wherein the target point information includes distance information and Doppler velocity information;
[0130] Clustering the target points to obtain a plurality of target families;
[0131] According to the distance information and the Doppler velocity information corresponding to each target point in each target family, the type of the target object corresponding to each target family is determined respectively.
[0132] Optionally, the type of the target object includes a moving target and a stationary target.
[0133] According to the distance information and the Doppler velocity information corresponding to each target point in each target family, the type of the target object corresponding to each target family is determined respectively, and specifically includes:
[0134] According to the distance information corresponding to each target point in the first target family, a distance information range corresponding to the target points in the first target family is determined.
[0135] According to the Doppler velocity information corresponding to each target point in the first target family, a velocity information range corresponding to the target points in the first target family is determined.
[0136] The target object corresponding to the target family with the maximum distance information range and the maximum Doppler velocity information range in the multiple target families is determined as a stationary target, and the target object corresponding to the other target families except the target family with the maximum distance information range and the maximum Doppler velocity information range in the multiple target families is determined as a moving target, wherein the first target family is any target family in the multiple target families.
[0137] Optionally, the method further includes: determining a center distance corresponding to a center target point according to the distance information corresponding to each target point in the target family corresponding to the moving target.
[0138] The center distance corresponding to the moving target is selected from adjacent two frames of frame data containing the same moving target respectively.
[0139] According to the center distance corresponding to the moving target selected from the adjacent two frames of frame data respectively, the relative position relationship between the moving target and the terminal device is determined.
[0140] Optionally, the center distance corresponding to the center target point in the target family is determined according to the distance information corresponding to each target point in the target family, and specifically includes:
[0141] The average value of the distance information corresponding to the target points in the target family is obtained as the center distance corresponding to the center target point in the target family.
[0142] Optionally, according to the center distance corresponding to the moving target selected from the adjacent two frames of frame data respectively, the relative position relationship between the moving target and the terminal device is determined, and includes:
[0143] When it is determined that the difference between the first center distance in the frame data after the collection time and the second center distance in the frame data before the collection time in the adjacent two frames of frame data is less than the second preset distance threshold, it is determined that the distance between the moving target and the terminal device gradually decreases.
[0144] Alternatively, when it is determined that the difference between the first center distance and the second center distance is greater than or equal to the second preset distance threshold, it is determined that the distance between the moving target and the terminal device gradually increases.
[0145] Optionally, the method further comprises: determining center speed information corresponding to a center target point in the target family according to Doppler speed information corresponding to each target point in the target family.
[0146] According to the center speed information corresponding to the moving target in the adjacent two frames of frame data, the relative running speed of the moving target relative to the terminal device is determined.
[0147] Optionally, the target points are clustered to obtain a plurality of target families, and the clustering specifically comprises:
[0148] Each target point is taken as a seed point, and the seed connectivity method is used to cluster the target points to obtain a plurality of target families.
[0149] Embodiments of the present application also provide a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the steps of the method for detecting a target object type provided by any one of the preceding method embodiments.
[0150] It should be noted that, in this document, relational terms such as“first” and“second”, and the like, are used solely to distinguish one entity or action from another entity or action, without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms“comprises”,“comprising”, or any other variations 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 more limitations, an element preceded by“comprises...” does not, without more limitations, foreclose the existence of additional identical elements in the process, method, article, or apparatus that includes the element.
[0151] The foregoing is considered as illustrative of the principles of the application. Numerous modifications and changes will readily occur to those skilled in the art, and it is intended to embody these modifications and changes into the scope of the application insofar as they fall within the scope of the appended claims.
Claims
1. A method of detecting a target object type, the method comprising: The method is executed by a terminal device provided with a radar, and comprises: acquiring frame data of radar scanning; extracting target points with a reflection energy difference greater than a preset energy threshold from each frame of the frame data; acquiring target point information corresponding to each of the target points, wherein the target point information comprises distance information and Doppler velocity information; clustering the target points to obtain a plurality of target families; determining a type of a target object corresponding to each of the target families according to the distance information and the Doppler velocity information corresponding to each of the target points in each of the target families, wherein the type of the target object comprises a moving target and a stationary target; The method further comprises: determining a center distance corresponding to a center target point according to the distance information corresponding to each target point in a target family corresponding to the moving target; selecting the center distance corresponding to the moving target from adjacent two frames of the frame data containing the same moving target; determining a relative positional relationship between the moving target and the terminal device according to the center distance corresponding to the moving target selected from adjacent two frames of the frame data.
2. The method of claim 1, wherein, The determination of the type of the target object corresponding to each of the target families according to the distance information and the Doppler velocity information corresponding to each of the target points in each of the target families specifically comprises: determining a distance information range corresponding to the target points in a first target family according to the distance information corresponding to each of the target points in the first target family; determining a velocity information range corresponding to the target points in the first target family according to the Doppler velocity information corresponding to each of the target points in the first target family; determining that a target object corresponding to a target family with the largest distance information range and the largest Doppler velocity information range among the plurality of target families is the stationary target, and determining that target objects corresponding to other target families among the plurality of target families except the target family with the largest distance information range and the largest Doppler velocity information range are the moving targets, wherein the first target family is any one of the plurality of target families.
3. The method of claim 1, wherein, The determination of the center distance corresponding to the center target point in the target family according to the distance information corresponding to each of the target points in the target family specifically comprises: obtaining an average value of the distance information corresponding to the target points in the target family as the center distance corresponding to the center target point in the target family.
4. The method according to claim 1 or 3, characterized in that, The determination of the relative positional relationship between the moving target and the terminal device according to the center distance corresponding to the moving target selected from adjacent two frames of the frame data comprises: when it is determined that a difference between a first center distance in frame data collected at a later time and a second center distance in frame data collected at an earlier time is less than a second preset distance threshold, it is determined that a distance between the moving target and the terminal device gradually decreases; or, when it is determined that the difference between the first center distance and the second center distance is greater than or equal to the second preset distance threshold, it is determined that the distance between the moving target and the terminal device gradually increases.
5. The method according to claim 1 or 3, characterized in that, The method further comprises: According to the Doppler velocity information corresponding to each of the target points in the target family, determine the center velocity information corresponding to a center target point in the target family; According to the center velocity information corresponding to the moving target in each of the adjacent two frames of frame data, determine the relative running speed of the moving target compared with the terminal device.
6. The method according to any one of claims 1 to 3, characterized in that, The clustering of the target points to obtain a plurality of target families specifically includes: Taking each of the target points as a seed point, the seed connectivity method is used to cluster a plurality of target points to obtain a plurality of target families.
7. An apparatus for detecting a target object type, the apparatus comprising: The device includes: An acquisition module is configured to acquire frame data of radar scanning; An extraction module is configured to extract target points with a reflection energy difference greater than a preset energy threshold from each frame of the frame data; The acquisition module is further configured to acquire target point information corresponding to each of the target points, wherein the target point information includes distance information and Doppler velocity information; A clustering module is configured to cluster the target points to obtain a plurality of target families; A processing module is configured to determine the type of a target object corresponding to each of the target families according to distance information and Doppler velocity information corresponding to each of the target points in the plurality of target families, wherein the type of the target object includes a moving target and a stationary target; According to the distance information corresponding to each of the target points in the target family corresponding to the moving target, determine the center distance corresponding to a center target point; Select the center distance corresponding to the moving target from the adjacent two frames of frame data containing the same moving target; According to the center distance corresponding to the moving target in each of the adjacent two frames of frame data, determine the relative position relationship between the moving target and the terminal device.
8. A terminal device, comprising: The device includes a processor and a memory; The memory is configured to store a computer program; The processor is configured to execute the program stored on the memory to implement the steps of the method for detecting the type of a target object according to any one of claims 1-6.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method for detecting the type of a target object according to any one of claims 1-6.
Citation Information
Patent Citations
Radar measurement data processing method and device
CN115170601A