Method, device and equipment for determining radar energy distribution

Abstract

The invention provides a radar energy distribution determination method, device and equipment, and the method comprises the steps: obtaining a plurality of initial tracks outputted by a target radar, and each initial track comprises the distance information and energy information of a plurality of sampling points in a corresponding distance segment; based on the positions of a plurality of preset sampling points in the target distance section, the plurality of initial tracks are updated, a plurality of candidate tracks are obtained, and each candidate track comprises distance information and energy information of at least one preset sampling point; and splicing the plurality of candidate tracks to obtain a spliced track, the spliced track being used for indicating a mapping relationship between the energy information and the distance information of the target radar in the target distance segment. According to the scheme, the distribution of the energy information of the target radar in the target distance section along with the distance domain can be determined.

Description

Technical Field

[0001] The present application relates to the field of radar detection technology, and in particular to a method, device and equipment for determining radar energy distribution. Background Art

[0002] As an all-day, all-weather sensing device, millimeter-wave radar has the inherent advantages of high accuracy in ranging and speed measurement. It is widely used in the fields of vehicle-mounted radar target recognition, traffic flow control, fall monitoring, and vital signs monitoring.

[0003] As a traffic radar, the millimeter-wave radar uses the narrow strip of ground in front as the detection area, and its energy distribution changes with the distance. However, there is currently no relevant technology for determining the relationship between energy distribution and distance change. Therefore, how to determine the distribution of radar energy in the distance domain is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present application provides a method, device and equipment for determining radar energy distribution to obtain the distribution of radar energy in a range domain.

[0005] In a first aspect, the present application provides a method for determining radar energy distribution, comprising:

[0006] Acquire multiple initial tracks output by the target radar, each of the initial tracks including respective distance information and energy information of multiple sampling points in a corresponding distance segment;

[0007] Based on the positions of the plurality of preset sampling points within the target distance segment, the plurality of initial tracks are updated to obtain a plurality of candidate tracks, each of the candidate tracks including distance information and energy information of at least one preset sampling point;

[0008] The multiple candidate tracks are spliced ​​to obtain a spliced ​​track, where the spliced ​​track is used to indicate a mapping relationship between energy information and distance information of the target radar within the target distance segment.

[0009] In a possible implementation manner, the step of splicing the multiple candidate tracks to obtain a spliced ​​track includes:

[0010] Determine a reference track among the plurality of candidate tracks;

[0011] The reference track is respectively spliced ​​with other candidate tracks among the multiple candidate tracks except the reference track to obtain the spliced ​​track.

[0012] In a possible implementation manner, the step of splicing the reference track with other candidate tracks among the plurality of candidate tracks except the reference track to obtain the spliced ​​track includes:

[0013] Determine the track to be spliced among the other candidate tracks. For the first splicing, the track to be spliced is the other candidate track;

[0014] From the track to be spliced, determine the first track that has intersection sampling points with the reference track; splice the reference track and the first track to obtain an updated reference track; the intersection sampling points are a subset of the multiple preset sampling points;

[0015] Repeat the above operations based on the updated reference track until there is no track to be spliced among the other candidate tracks, and determine the updated reference track as the spliced track.

[0016] In a possible implementation, the splicing of the reference track and the first track to obtain an updated reference track includes:

[0017] Based on the energy information of the intersection sampling points on the reference track and the energy information of the intersection sampling points on the first track, determine the energy multiple of the first track relative to the reference track;

[0018] Based on the energy multiple, splice the reference track and the first track to obtain the updated reference track.

[0019] In a possible implementation, the splicing of the reference track and the first track based on the energy multiple to obtain the updated reference track includes:

[0020] Based on the energy multiple, the energy information of the intersection sampling points on the reference track, and the energy information of the intersection sampling points on the first track, obtain the updated energy information of the intersection sampling points;

[0021] Based on the energy multiple and the energy information of other sampling points on the first track except the intersection sampling points, obtain the updated energy information of the other sampling points;

[0022] Based on the updated energy information of the intersection sampling points and the updated energy information of the other sampling points, update the reference track to obtain the updated reference track.

[0023] In a possible implementation, the updating of the multiple initial tracks based on the positions of multiple preset sampling points in a target distance segment to obtain multiple candidate tracks includes:

[0024] For each of the initial tracks, based on the positions of the multiple preset sampling points, determine the target preset sampling points within the distance segment of the initial track;

[0025] Based on the position of the initial track and the target preset sampling point, determine the distance information and energy information of the target preset sampling point;

[0026] Based on the distance information and energy information of the target preset sampling point, obtain the candidate track corresponding to the initial track.

[0027] In a possible implementation manner, the determining the distance information and energy information of the target preset sampling point based on the position of the initial track and the target preset sampling point includes:

[0028] Based on the position of the target preset sampling point, determine the distance information of the target preset sampling point;

[0029] Perform filtering processing on the energy information of multiple sampling points corresponding to the initial track to obtain the filtered energy information of multiple sampling points corresponding to the initial track;

[0030] Based on the position of the target preset sampling point and the filtered energy information of multiple sampling points corresponding to the initial track, obtain the energy information of the target preset sampling point.

[0031] In a possible implementation manner, the obtaining the energy information of the target preset sampling point based on the position of the target preset sampling point and the filtered energy information of multiple sampling points corresponding to the initial track includes:

[0032] Based on the position of the target preset sampling point and the respective distance information of multiple sampling points corresponding to the initial track, determine at least one candidate sampling point from multiple sampling points corresponding to the initial track, and the distance between the target preset sampling point and the candidate sampling point is less than or equal to a preset distance;

[0033] Based on the filtered energy information of the at least one candidate sampling point, determine the energy information of the target preset sampling point.

[0034] In a second aspect, the present application provides a device for determining the radar energy distribution, including:

[0035] An acquisition module, configured to acquire multiple initial tracks output by a target radar, and each of the initial tracks includes the respective distance information and energy information of multiple sampling points within a corresponding distance segment;

[0036] A processing module, configured to update the multiple initial tracks based on the positions of multiple preset sampling points within a target distance segment to obtain multiple candidate tracks, and each of the candidate tracks includes the distance information and energy information of at least one preset sampling point;

[0037] A splicing module, which is used to splice the multiple candidate tracks to obtain a spliced track, and the spliced track is used to indicate the mapping relationship between the energy information and the distance information of the target radar within the target distance segment.

[0038] In a possible implementation manner, the splicing module is specifically configured to:

[0039] Determine a reference track among the multiple candidate tracks;

[0040] Splice the reference track with other candidate tracks among the multiple candidate tracks except the reference track to obtain the spliced track.

[0041] In a possible implementation manner, the splicing module is specifically configured to:

[0042] Determine a track to be spliced among the other candidate tracks. For the first splicing, the track to be spliced is the other candidate tracks;

[0043] Determine a first track having intersection sampling points with the reference track from the track to be spliced; splice the reference track and the first track to obtain an updated reference track; the intersection sampling points are a subset of the multiple preset sampling points;

[0044] Repeat the above operations based on the updated reference track until there is no track to be spliced among the other candidate tracks, and determine the updated reference track as the spliced track.

[0045] In a possible implementation manner, the splicing module is specifically configured to:

[0046] Determine the energy multiple of the first track relative to the reference track based on the energy information of the intersection sampling points on the reference track and the energy information of the intersection sampling points on the first track;

[0047] Splice the reference track and the first track based on the energy multiple to obtain the updated reference track.

[0048] In a possible implementation manner, the splicing module is specifically configured to:

[0049] Obtain the updated energy information of the intersection sampling points based on the energy multiple, the energy information of the intersection sampling points on the reference track, and the energy information of the intersection sampling points on the first track;

[0050] Obtain the updated energy information of the other sampling points based on the energy multiple and the energy information of the other sampling points on the first track except the intersection sampling points;

[0051] Based on the updated energy information of the intersection sampling points and the updated energy information of the other sampling points, update the reference track to obtain the updated reference track.

[0052] In a possible implementation manner, the processing module is specifically configured to:

[0053] For each of the initial tracks, based on the positions of the multiple preset sampling points, determine the target preset sampling points within the distance segment of the initial track;

[0054] Based on the positions of the initial track and the target preset sampling points, determine the distance information and energy information of the target preset sampling points;

[0055] Based on the distance information and energy information of the target preset sampling points, obtain the candidate track corresponding to the initial track.

[0056] In a possible implementation manner, the processing module is specifically configured to:

[0057] Based on the position of the target preset sampling point, determine the distance information of the target preset sampling point;

[0058] Perform filtering processing on the energy information of the multiple sampling points corresponding to the initial track to obtain the filtered energy information of the multiple sampling points corresponding to the initial track;

[0059] Based on the position of the target preset sampling point and the filtered energy information of the multiple sampling points corresponding to the initial track, obtain the energy information of the target preset sampling point.

[0060] In a possible implementation manner, the processing module is specifically configured to:

[0061] Based on the position of the target preset sampling point and the respective distance information of the multiple sampling points corresponding to the initial track, determine at least one candidate sampling point from the multiple sampling points corresponding to the initial track, where the distance between the target preset sampling point and the candidate sampling point is less than or equal to a preset distance;

[0062] Based on the filtered energy information of the at least one candidate sampling point, determine the energy information of the target preset sampling point.

[0063] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method for determining the radar energy distribution according to any item in the first aspect.

[0064] Fourthly, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for determining the radar energy distribution according to any one of the first aspect is implemented.

[0065] The method, device and equipment for determining the radar energy distribution provided by the present application first obtain a plurality of initial tracks output by a target radar. Each initial track includes the distance information and energy information of each of a plurality of sampling points within a corresponding distance segment. Then, based on the positions of a plurality of preset sampling points within the target distance segment, the plurality of initial tracks are updated to obtain a plurality of candidate tracks. By updating the initial tracks, synchronization of the sampling points is achieved, so that each candidate track includes the distance information and energy information of at least one preset sampling point. Furthermore, the plurality of candidate tracks are spliced to obtain a spliced track, and the spliced track is used to indicate the mapping relationship between the energy information and the distance information of the target radar within the target distance segment. In the solution of the present application, after synchronizing the sampling points between the initial tracks to obtain a plurality of candidate tracks, by splicing the plurality of candidate tracks, the candidate tracks corresponding to different distance segments are spliced to obtain the spliced track corresponding to the target distance segment, thereby obtaining the distribution of the energy information of the target radar within the target distance segment with respect to the distance domain. Description of the Drawings

[0066] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0067] Figure 1 It is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0068] Figure 2 It is a schematic diagram of the distribution of energy information with respect to distance provided by an embodiment of the present application;

[0069] Figure 3 It is a flowchart of the method for determining the radar energy distribution provided by an embodiment of the present application;

[0070] Figure 4 It is a flowchart of updating a plurality of initial tracks provided by an embodiment of the present application;

[0071] Figure 5 It is a flowchart of track splicing provided by an embodiment of the present application;

[0072] Figure 6 It is a schematic diagram of track splicing provided by an embodiment of the present application;

[0073] Figure 7Schematic structural diagram of the radar energy distribution determination device provided by the embodiment of the present application;

[0074] Figure 8 Schematic physical structure diagram of an electronic device provided by the embodiment of the present application. Detailed implementation manners

[0075] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings in the present application. Apparently, the described embodiments are some but not all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0076] The distribution of radar energy in the distance domain is affected by various factors such as radar transmission power, elevation dimension transmitting antenna gain distribution, elevation dimension receiving antenna gain distribution, elevation angle during radar geological exploration, and road flatness. Obtaining the distribution of radar energy along the distance domain is of great significance.

[0077] For example, in vehicle type classification applications, vehicle types are usually discriminated by a certain energy threshold. However, since radar energy varies along the distance, it is impossible to find a unified threshold for the entire distance segment. If the distribution of radar energy along the distance is known, the energy can be normalized first, and then a unified threshold can be used for classification, reducing the computational complexity of vehicle type classification.

[0078] The energy received by the radar from the target is affected not only by the distribution of radar energy in the distance domain but also by the radar cross section (RCS) of the target. For vehicles with a large size, such as buses and large trucks, the target echo energy is high, while for vehicles with a small size, the energy is low. If the distribution of radar energy at different distances varies too much, it will lead to a contradiction between the detection rate of small RCS targets and the energy overflow of large RCS targets. Obtaining the distribution of radar energy along the distance can better balance the above contradictions.

[0079] Based on this, the embodiment of the present application provides a method for determining radar energy distribution. The solution of the embodiment of the present application will be introduced below with reference to the accompanying drawings.

[0080] First, in combination with Figure 1 An applicable application scenario of the embodiment of the present application will be introduced.

[0081] Figure 1 Schematic diagram of an application scenario provided by the embodiment of the present application, as Figure 1As shown, it includes a target radar 10, which is in a fixed position and can detect the ground in front of it to obtain the track of the detected target.

[0082] exist Figure 1 In FIG. 1 , the distance segment from point O to point A5 is within the detection range of the target radar 10. There may be different targets within the detection range of the target radar 10, for example, Figure 1 In the example, the targets include vehicle A and vehicle B, and the target radar 10 can detect vehicle A and vehicle B and output their respective tracks.

[0083] The track obtained by the target radar tracking a single target can be understood as the target radar energy sampling at the distance at which the target is located at different frame times.

[0084] By sampling multiple targets at their respective distances, the energy distribution of the target radar with distance can be obtained. However, in the process of the target radar tracking multiple targets, due to the different RCS of different targets, the RCS will also change randomly with the change of distance, resulting in the unknown RCS of the target, and the lengths of multiple candidate tracks are different, and the distance segments corresponding to the candidate tracks are relatively random. Therefore, directly sampling multiple targets at their respective distances, the energy distribution of the target radar with distance is not accurate.

[0085] Figure 2 A schematic diagram of the distribution of energy information with distance provided in the embodiment of the present application is shown in FIG. Figure 2 As shown in the figure, the energy information of two different targets changes with the distance unit. Figure 2 In the figure, the horizontal axis represents the distance unit, that is, the distance between the target and the radar, and the vertical axis represents the energy information of the target. Among them, the track corresponding to target 1 is track 1, and the track corresponding to target 2 is track 2.

[0086] exist Figure 2 In FIG. 1 , track 1 illustrates the change of energy information of target 1 with distance units, where the movement range of target 1 is from 50 distance units to 250 distance units from the target radar (each distance unit represents a certain length). Track 2 illustrates the change of energy information of target 2 with distance units, where the movement range of target 2 is from 40 distance units to 325 distance units from the target radar. The intersection of the tracks of target 1 and target 2 is the distance segment from 50 distance units to 250 distance units from the target radar.

[0087] As mentioned above, the energy received by the radar at the target is affected by the distribution of the radar energy along the range domain and the RCS of the target, see Figure 2,For target 1 and target 2, when the distance units are equal, the energy information of target 1 and target 2 are not equal, which is caused by the unequal RCS of target 1 and target 2.

[0088] based on Figure 2 It can be seen that although the RCS of the two targets have certain random fluctuations during the movement, overall, the energy information of the two targets is approximately proportional in the intersection part of the distance, and the proportionality coefficient is the ratio of the RCS of the two targets.

[0089] Based on the above characteristics, after obtaining multiple candidate tracks, the embodiment of the present application continuously splices the candidate tracks with the same distance segment, and finally obtains a spliced ​​track to indicate the mapping relationship between the energy information and the distance information of the target distance segment.

[0090] exist Figure 1 Based on the application scenario of the example, the following Figure 3 The solution of the embodiment of the present application is introduced.

[0091] Figure 3 A flow chart of a method for determining radar energy distribution provided in an embodiment of the present application, such as Figure 3 As shown, including:

[0092] S31, obtaining a plurality of initial tracks output by the target radar, each initial track including respective distance information and energy information of a plurality of sampling points in a corresponding distance segment.

[0093] After the target radar survey is completed, the distribution of radiated and received energy at different road distances is fixed. The target radar can track different targets and output corresponding multiple initial tracks.

[0094] The initial track includes the distance information and energy information of multiple sampling points in the corresponding distance segment, wherein the distance information of the sampling point indicates the distance between the sampling point and the target radar, and the energy information indicates the energy of the target radar at the corresponding sampling point.

[0095] In the embodiment of the present application, the distance segments corresponding to different initial tracks may be the same or different.

[0096] For example, Figure 1 In the example, the target radar 10 detects that vehicle A travels from point A1 to point A3, with a travel distance of S1, and vehicle B travels from point A2 to point A4, with a travel distance of S2. Then the target radar 10 can output the initial track of distance segment S1 and the initial track of distance segment S2.

[0097] S32. Update multiple initial tracks based on the positions of multiple preset sampling points within a target distance segment to obtain multiple candidate tracks. Each candidate track includes the distance information and energy information of at least one preset sampling point.

[0098] The target distance segment is a pre-set distance segment, which is within the detection distance of the target radar. Multiple preset sampling points are pre-set within the target distance segment, and the positions of the multiple preset sampling points are known. For example, in Figure 1 , the target distance segment is the distance segment L between point O and point A5. Multiple preset sampling points are pre-set within the distance segment L.

[0099] After obtaining multiple initial tracks, based on the positions of multiple preset sampling points, the multiple initial tracks can be updated to obtain corresponding candidate tracks. Each candidate track includes the distance information and energy information of at least one preset sampling point.

[0100] For any initial track, it includes the distance information and energy information of multiple sampling points within the corresponding distance segment. Taking the initial track of the distance segment S1 in Figure 1 as an example, it includes the distance information and energy information of multiple sampling points within the distance segment S1. For the multiple preset sampling points, some of these preset sampling points are within the distance segment S1. The process of updating the initial track is the process of determining the energy information of these preset sampling points.

[0101] For any one initial track, the initial track includes the distance information and energy information of each of multiple sampling points. It is possible to determine the preset sampling points within the distance segment corresponding to the initial track among the multiple preset sampling points, and combine the distance information and energy information of each of the multiple sampling points to determine the energy information of the preset sampling points within the distance segment corresponding to the initial track, thereby realizing the update process of the initial track to obtain the corresponding candidate track.

[0102] S33. Stitch multiple candidate tracks to obtain a stitched track, which is used to indicate the mapping relationship between the energy information and distance information of the target radar within the target distance segment.

[0103] Each candidate track includes the distance information and energy information of at least one preset sampling point, thus realizing the synchronization of sampling points among multiple candidate tracks. Then, stitch multiple candidate tracks. Finally, obtain a stitched track. The stitched track includes the distance information and energy information of each of the multiple preset sampling points within the target distance segment. The distance information and energy information of each of these multiple preset sampling points are used to indicate the mapping relationship between the energy information and distance information of the target radar within the target distance segment, that is, the distribution of the energy of the target radar within the target distance segment with respect to the distance domain.

[0104] The method for determining the radar energy distribution provided by the embodiment of the present application first obtains a plurality of initial tracks output by the target radar. Each initial track includes the distance information and energy information of each of the multiple sampling points within the corresponding distance segment. Then, based on the positions of multiple preset sampling points within the target distance segment, the multiple initial tracks are updated to obtain multiple candidate tracks. By updating the initial tracks, the synchronization of the sampling points is achieved, so that each candidate track includes the distance information and energy information of at least one preset sampling point. Furthermore, the multiple candidate tracks are spliced to obtain a spliced track, and the spliced track is used to indicate the mapping relationship between the energy information and the distance information of the target radar within the target distance segment. In the solution of the embodiment of the present application, after synchronizing the sampling points between the initial tracks to obtain multiple candidate tracks, by splicing the multiple candidate tracks, the candidate tracks corresponding to different distance segments are spliced to obtain the spliced track corresponding to the target distance segment, thereby obtaining the distribution of the energy information of the target radar within the target distance segment with respect to the distance domain.

[0105] Based on any of the above embodiments, the solution of the embodiment of the present application will be further introduced below with reference to the accompanying drawings.

[0106] Assume that the detection distance of the target radar is L. Then, from the target radar to the distance L, it is the target distance segment. N preset sampling points are set within the target distance segment, and N is a positive integer. The N preset sampling points can be set at equal distances or not at equal distances, and the embodiment of the present application does not limit this. In the following embodiments, an example of equal-distance setting will be used for introduction.

[0107] N preset sampling points are set within the target distance segment, and the distance of any nth preset sampling point to the target radar is set as x n , x n = nL / N, n = 1, 2,..., N, x n That is, the distance information of the nth preset sampling point.

[0108] Then, a plurality of initial tracks output by the target radar are obtained. In a possible implementation manner, the tracks output by the target radar can be screened for long tracks to obtain a plurality of initial tracks, where a long track refers to a track with more than M consecutive sampling points, and M can be preset. For example, it can be set as M = 40, or other values, and the embodiment of the present application does not limit this.

[0109] After obtaining a plurality of initial tracks, the multiple initial tracks can be updated based on the positions of the multiple preset sampling points. The following will be combined with Figure 4 to introduce this process.

[0110] Figure 4 is the flowchart for updating a plurality of initial tracks provided by the embodiment of the present application, asFigure 4 As shown in

[0111] S41. For each initial track, based on the positions of multiple preset sampling points, determine the target preset sampling points within the distance segment of the initial track.

[0112] Since the processing procedures for multiple initial tracks are similar, in the following embodiments, any one of the multiple initial tracks will be taken as an example for introduction.

[0113] For any initial track, the initial track includes the distance information and energy information of multiple sampling points within the corresponding distance segment. First, based on the positions of multiple preset sampling points, it is necessary to determine the target preset sampling points within the distance segment of the initial track.

[0114] For example, if the distance segment of the initial track is the distance segment from 50 meters to 80 meters from the target radar, then based on the positions of multiple preset sampling points, it is possible to determine the preset sampling points among the multiple preset sampling points that are within the distance segment from 50 meters to 80 meters from the target radar, and use them as the target preset sampling points within the distance segment of the initial track.

[0115] For each initial track, the above method can be used to obtain the target preset sampling points within the distance segment of each initial track. Among them, each preset sampling point is within the distance segment of at least one initial track, thereby achieving full coverage of multiple preset sampling points.

[0116] S42. Based on the position of the initial track and the target preset sampling point, determine the distance information and energy information of the target preset sampling point.

[0117] For any initial track, after determining the target preset sampling points within the distance segment of the initial track, the distance information and energy information of the target preset sampling point can be determined.

[0118] Since the position of the target preset sampling point is known, based on the position of the target preset sampling point and the position of the target radar, the distance from the target preset sampling point to the target radar can be obtained, and the distance from the target preset sampling point to the target radar is used as the distance information of the target preset sampling point.

[0119] The energy information of the target preset sampling point needs to be determined in combination with the energy information of multiple sampling points in the initial track.

[0120] In a possible implementation, to smooth the error caused by the jitter of the target RCS, the energy information of multiple sampling points corresponding to the initial track can be filtered to obtain the filtered energy information of multiple sampling points corresponding to the initial track. Among them, the filtering process can be implemented by a moving average filter. The length P of the moving average filter is preset in advance, and then the energy information of multiple sampling points corresponding to the initial track is filtered based on the length P.

[0121] After obtaining the filtered energy information of multiple sampling points corresponding to the initial track, based on the position of the target preset sampling point within the distance segment of the initial track and the filtered energy information of multiple sampling points corresponding to the initial track, the energy information of the target preset sampling point is obtained.

[0122] The energy information of the target preset sampling point can be obtained by means of track interpolation. Specifically, based on the position of the target preset sampling point and the respective distance information of multiple sampling points corresponding to the initial track, at least one candidate sampling point is determined from multiple sampling points corresponding to the initial track. The distance between the target preset sampling point and the candidate sampling point is less than or equal to a preset distance, and the size of the preset distance can be set as required. Among them, at least one candidate sampling point is a sampling point among multiple sampling points corresponding to the initial track that is relatively close to the target preset sampling point. For example, at least one candidate sampling point may include the sampling point among multiple sampling points corresponding to the initial track that is on the left side of the target preset sampling point and closest to the target preset sampling point, and the sampling point among multiple sampling points corresponding to the initial track that is on the right side of the target preset sampling point and closest to the target preset sampling point.

[0123] Then, based on the filtered energy information of at least one candidate sampling point, the energy information of the target preset sampling point is determined. For example, the mean value of the filtered energy information of at least one candidate sampling point can be taken to obtain the energy information of the target preset sampling point. For example, based on the distance information indicating a candidate sampling point and the distance information of the target preset sampling point, the filtered energy information of at least one candidate sampling point can be scaled proportionally to obtain the energy information of the target preset sampling point, and so on. The embodiments of the present application do not limit this.

[0124] S43. Based on the distance information and energy information of the target preset sampling point, a candidate track corresponding to the initial track is obtained.

[0125] For any initial track, after determining the distance information and energy information of the target preset sampling point within the distance segment of the initial track, the candidate track corresponding to the initial track can be obtained.

[0126] In the above embodiments, the process of updating the initial track to obtain multiple candidate tracks is introduced. Next, the process of splicing multiple candidate tracks is introduced.

[0127] After obtaining multiple candidate tracks, first determine a reference track among the multiple candidate tracks. In the embodiments of the present application, any one of the multiple candidate tracks can be selected as the reference track, or the reference track can be determined based on the lengths of the distance segments corresponding to the multiple candidate tracks respectively. For example, the candidate track corresponding to the longest distance segment can be used as the reference track; the candidate track corresponding to the second longest distance segment can be used as the reference track; any one of the candidate tracks whose corresponding distance segment length is greater than or equal to a preset length can be selected as the reference track, and so on.

[0128] After determining the reference track, splice the reference track with other candidate tracks among the multiple candidate tracks except the reference track, and the spliced track can be obtained. The following combines Figure 5 to introduce this process.

[0129] Figure 5 is a flowchart of track splicing provided by the embodiments of the present application. As Figure 5 shown, it includes:

[0130] S51, determine a track to be spliced among other candidate tracks. For the first splicing, the track to be spliced is other candidate tracks.

[0131] Initially, among the multiple candidate tracks, other candidate tracks except the reference track are all tracks to be spliced.

[0132] S52, determine a first track having an intersection sampling point with the reference track from the tracks to be spliced; splice the reference track and the first track to obtain an updated reference track; the intersection sampling point is a subset of multiple preset sampling points.

[0133] After determining the track to be spliced, according to the preset sampling points included in each track to be spliced and the preset sampling points included in the reference track, determine a first track having an intersection sampling point with the reference track. If there are multiple tracks among the tracks to be spliced that all have intersection sampling points with the reference track, any one of these multiple tracks can be selected as the first track.

[0134] After determining the first track, the reference track and the first track can be spliced. Specifically, for the intersection sampling point between the reference track and the first track, obtain the energy information of the intersection sampling point on the reference track and the energy information of the intersection sampling point on the first track. Then, based on the energy information of the intersection sampling point on the reference track and the energy information of the intersection sampling point on the first track, determine the energy multiple of the first track relative to the reference track.

[0135] In a possible implementation manner, the energy multiple of the first track relative to the reference track can be obtained based on the least squares method. The following combinesFigure 6 Introduce this process.

[0136] Figure 6 It is a schematic diagram of track stitching provided by an embodiment of this application. As Figure 6 shown, it includes track B and track C. Track B is the reference track, and track C is the first track.

[0137] Track B includes 6 preset sampling points, namely preset sampling point x1, preset sampling point x2, preset sampling point x3, preset sampling point x4, preset sampling point x5, and preset sampling point x5. Track C includes 5 preset sampling points, namely preset sampling point x4, preset sampling point x5, preset sampling point x6, preset sampling point x7, and preset sampling point x8. Then the intersection sampling points between track B and track C include preset sampling point x4, preset sampling point x5, and preset sampling point x6.

[0138] For the intersection sampling points between the reference track and the first track, the energy information on the reference track and the energy information on the first track can be obtained. For example, in Figure 6 it, the energy information of the intersection sampling points between track B and track C on track B is represented by vector g b and the energy information of the intersection sampling points between track B and track C on track C is represented by vector g c Then there is:

[0139]

[0140]

[0141] Among them, g b (x4), g b (x5), g b (x6) represent the energy information of preset sampling point x4, preset sampling point x5, and preset sampling point x6 on track B in sequence, and g c (x4), g c (x5), g c (x6) represent the energy information of preset sampling point x4, preset sampling point x5, and preset sampling point x6 on track C in sequence.

[0142] Based on the least squares method, the energy multiple p of track C relative to track B can be obtained:

[0143]

[0144] represents the conjugate transpose of g b .

[0145] After obtaining the energy multiple, based on the energy multiple, splice the reference track and the first track to obtain the updated reference track.

[0146] For the intersection sampling points between the reference track and the first track, based on the energy multiple, the energy information of the intersection sampling points on the reference track, and the energy information of the intersection sampling points on the first track, obtain the updated energy information of the intersection sampling points. Since the energy multiple reflects the ratio between the target RCSs corresponding to the reference track and the first track respectively, therefore, the energy information of the intersection sampling points on the first track can be multiplied by the energy multiple, and then averaged with the energy information of the intersection sampling points on the reference track to obtain the updated energy information of the intersection sampling points.

[0147] For other sampling points on the first track except the intersection sampling points, based on the energy multiple and the energy information of other sampling points on the first track except the intersection sampling points, obtain the updated energy information of other sampling points. Since other sampling points are preset sampling points not included in the reference track, therefore, multiply the energy multiple by the energy information of other sampling points on the first track to obtain the updated energy information of other sampling points, and supplement it to the reference track.

[0148] Then, based on the updated energy information of the intersection sampling points and the updated energy information of other sampling points, update the reference track to obtain the updated reference track. The updated reference track includes the energy information and distance information of all preset sampling points in the original reference track and the first track.

[0149] Still taking Figure 6 as an example, for the preset sampling point x4, which belongs to the intersection sampling points between track B and track C, the updated energy information of the preset sampling point x4 is:

[0150]

[0151] Among them, is the updated energy information of the preset sampling point x4, g b (x4) is the energy information of the preset sampling point x4 on track B, g c (x4) is the energy information of the preset sampling point x4 on track C, and p is the energy multiple.

[0152] Based on a similar way to formula (4), the updated energy information of the preset sampling point x5 can be obtained and the updated energy information of the preset sampling point x6

[0153] For the preset sampling point x7, which belongs to other sampling points on track C except the intersection sampling points, the updated energy information of the preset sampling point x7 is:

[0154]

[0155] Among them, is the updated energy information of the preset sampling point x7, and g c (x7) is the energy information of the preset sampling point x7 on the track C, and p is the energy multiple.

[0156] Based on a similar manner as in Equation (5), the updated energy information of the preset sampling point x8 can be obtained

[0157] As Figure 6 shown, based on the above updated energy information, the updated track B can be obtained. The updated track B includes the preset sampling point x1, the preset sampling point x2, the preset sampling point x3, the preset sampling point x4, the preset sampling point x5, the preset sampling point x6, the preset sampling point x7, and the preset sampling point x8.

[0158] S53. Based on the updated reference track, repeat the above operations until the track to be spliced is not included in other candidate tracks, and determine the updated reference track as the spliced track.

[0159] In the above embodiment, the implementation process of splicing the reference track and the first track is introduced in combination with Figure 6 After splicing the reference track and the first track, the updated reference track is obtained. Then, the first track is the spliced track. Then, re-determine the first track with intersection sampling points with the updated reference track among the remaining tracks to be spliced, and implement the splicing process based on the manner in the example of S52 until all other candidate tracks are spliced with the reference track, and determine the finally obtained updated reference track as the spliced track. The spliced track includes the distance information and energy information of multiple preset sampling points within the target distance segment, indicating the mapping relationship between the energy information and the distance information of the target radar within the target distance segment, that is, the distribution of the energy information with respect to the distance domain.

[0160] The distribution of the energy information with respect to the distance domain can be applied to different application scenarios such as vehicle type recognition and traffic flow statistics. Taking vehicle type recognition as an example, the application of the distribution of the energy information of the target radar with respect to the distance domain in vehicle type recognition is introduced below.

[0161] For the binary classification vehicle type recognition task, the energy multiples of multiple candidate tracks relative to the spliced track can be determined. The method for determining the energy multiples can refer to the above Equation (3), which will not be elaborated here. After obtaining the energy multiples of multiple candidate tracks relative to the spliced track, unsupervised learning based on Kmeans can be performed based on the energy multiples of multiple candidate tracks relative to the spliced track.

[0162] Since the energy multiple of the candidate track relative to the spliced track reflects the ratio between the target RCS corresponding to the candidate track and the target RCS corresponding to the spliced track, and there is a correlation between the size of the target RCS and the vehicle type, with the RCS of large vehicles generally being greater than that of small vehicles, the energy multiples of multiple candidate tracks relative to the spliced track will be in two different intervals, which respectively correspond to large vehicles and small vehicles. Based on these two different intervals, the vehicle type determination threshold Γ between large vehicles and small vehicles can be obtained.

[0163] After obtaining the vehicle type determination threshold Γ, for any vehicle to be recognized, the target radar can be used to detect the vehicle to be recognized, and the distance information of the target of the vehicle to be recognized at the k-th frame is obtained as r(k), and the energy information is g(k). Then, the energy information g(k) of the vehicle to be recognized is normalized to obtain the normalized energy of the vehicle to be recognized:

[0164]

[0165] where g(k) is the energy information of the vehicle to be recognized at the distance information r(k), is the preset sampling point closest to the distance information r(k) among the multiple preset sampling points of the spliced track, is on the spliced track is the energy information, is the normalized energy of the vehicle to be recognized at the distance information r(k).

[0166] Through the normalization process shown in Equation (6), the difference in the target radar illumination energy at different distances is removed. Then, is compared with the vehicle type determination threshold Γ. When is greater than the vehicle type determination threshold Γ, it is determined that the vehicle to be recognized is a large vehicle. When is less than or equal to the vehicle type determination threshold Γ, it is determined that the vehicle to be recognized is a small vehicle.

[0167] It can be seen that through the distribution of the target radar energy in the distance domain, the energy information of the vehicle to be recognized can be normalized, and a unified threshold can be used for classification, thereby reducing the complexity of vehicle type classification.

[0168] In summary, in the solution of the embodiment of the present application, after determining the reference track, the energy multiple of other candidate tracks relative to the reference track is determined based on the least square method, and the splicing process between the reference track and other candidate tracks is realized based on the energy multiple, so as to obtain the distribution of the energy information of the target radar with respect to the distance domain. In the vehicle type classification scenario, through the distribution of the energy information of the target radar with respect to the distance domain, the energy normalization of the target can be performed, thereby avoiding the transformation of the vehicle type classification energy threshold at different distances and reducing the complexity of vehicle type classification.

[0169] The determination device for radar energy distribution provided by the present application will be described below. The determination device for radar energy distribution described below can be correspondingly referred to the determination method for radar energy distribution described above.

[0170] Figure 7 is a schematic structural diagram of the determination device for radar energy distribution provided by the embodiment of the present application, as Figure 7 shown. The device includes:

[0171] An acquisition module 71, configured to acquire a plurality of initial tracks output by the target radar, each of the initial tracks including the distance information and energy information of each of a plurality of sampling points within a corresponding distance segment;

[0172] A processing module 72, configured to update the plurality of initial tracks based on the positions of a plurality of preset sampling points within the target distance segment to obtain a plurality of candidate tracks, each of the candidate tracks including the distance information and energy information of at least one preset sampling point;

[0173] A splicing module 73, configured to splice the plurality of candidate tracks to obtain a spliced track, and the spliced track is used to indicate the mapping relationship between the energy information and the distance information of the target radar within the target distance segment.

[0174] In a possible implementation manner, the splicing module 73 is specifically configured to:

[0175] Determine a reference track among the plurality of candidate tracks;

[0176] Splice the reference track with other candidate tracks in the plurality of candidate tracks except the reference track to obtain the spliced track.

[0177] In a possible implementation manner, the splicing module 73 is specifically configured to:

[0178] Determine a track to be spliced among the other candidate tracks. For the first splicing, the track to be spliced is the other candidate track;

[0179] Determine a first track from the tracks to be spliced that has intersection sampling points with the reference track; splice the reference track and the first track to obtain an updated reference track; the intersection sampling points are a subset of the multiple preset sampling points;

[0180] Repeat the above operations based on the updated reference track until there are no tracks to be spliced among the other candidate tracks, and determine the updated reference track as the spliced track.

[0181] In a possible implementation manner, the splicing module 73 is specifically configured to:

[0182] Determine an energy multiple of the first track relative to the reference track based on the energy information of the intersection sampling points on the reference track and the energy information of the intersection sampling points on the first track;

[0183] Splice the reference track and the first track based on the energy multiple to obtain the updated reference track.

[0184] In a possible implementation manner, the splicing module 73 is specifically configured to:

[0185] Obtain updated energy information of the intersection sampling points based on the energy multiple, the energy information of the intersection sampling points on the reference track, and the energy information of the intersection sampling points on the first track;

[0186] Obtain updated energy information of the other sampling points based on the energy multiple and the energy information of the other sampling points on the first track except the intersection sampling points;

[0187] Update the reference track based on the updated energy information of the intersection sampling points and the updated energy information of the other sampling points to obtain the updated reference track.

[0188] In a possible implementation manner, the processing module 72 is specifically configured to:

[0189] For each of the initial tracks, determine target preset sampling points within the distance segment of the initial track based on the positions of the multiple preset sampling points;

[0190] Determine the distance information and energy information of the target preset sampling points based on the positions of the initial track and the target preset sampling points;

[0191] Obtain a candidate track corresponding to the initial track based on the distance information and energy information of the target preset sampling points.

[0192] In a possible implementation, the processing module 72 is specifically configured to:

[0193] Determine the distance information of the target preset sampling point based on the position of the target preset sampling point;

[0194] Perform filtering processing on the energy information of multiple sampling points corresponding to the initial track to obtain the filtered energy information of multiple sampling points corresponding to the initial track;

[0195] Obtain the energy information of the target preset sampling point based on the position of the target preset sampling point and the filtered energy information of multiple sampling points corresponding to the initial track.

[0196] In a possible implementation, the processing module 72 is specifically configured to:

[0197] Determine at least one candidate sampling point from multiple sampling points corresponding to the initial track based on the position of the target preset sampling point and the respective distance information of multiple sampling points corresponding to the initial track, where the distance between the target preset sampling point and the candidate sampling point is less than or equal to a preset distance;

[0198] Determine the energy information of the target preset sampling point based on the filtered energy information of the at least one candidate sampling point.

[0199] Figure 8 An example of a schematic physical structure diagram of an electronic device is shown as Figure 8 shown. The electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840. Among them, the processor 810, the communication interface 820, and the memory 830 complete mutual communication through the communication bus 840. The processor 810 may call logic instructions in the memory 830 to execute a method for determining the radar energy distribution. The method includes: obtaining multiple initial tracks output by a target radar, where each of the initial tracks includes the respective distance information and energy information of multiple sampling points within a corresponding distance segment; based on the positions of multiple preset sampling points within a target distance segment, updating the multiple initial tracks to obtain multiple candidate tracks, where each of the candidate tracks includes the distance information and energy information of at least one preset sampling point; splicing the multiple candidate tracks to obtain a spliced track, and the spliced track is used to indicate the mapping relationship between the energy information and the distance information of the target radar within the target distance segment.

[0200] In addition, when the logical instructions in the above-mentioned memory 830 can be implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0201] On the other hand, this application also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for determining the radar energy distribution provided by the above-mentioned various methods. The method includes: obtaining a plurality of initial tracks output by a target radar, each of the initial tracks including the distance information and energy information of each of a plurality of sampling points within a corresponding distance segment; based on the positions of a plurality of preset sampling points within a target distance segment, updating the plurality of initial tracks to obtain a plurality of candidate tracks, each of the candidate tracks including the distance information and energy information of at least one preset sampling point; splicing the plurality of candidate tracks to obtain a spliced track, and the spliced track is used to indicate the mapping relationship between the energy information and distance information of the target radar within the target distance segment.

[0202] On another aspect, this application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the method for determining the radar energy distribution provided by the above-mentioned various methods. The method includes: obtaining a plurality of initial tracks output by a target radar, each of the initial tracks including the distance information and energy information of each of a plurality of sampling points within a corresponding distance segment; based on the positions of a plurality of preset sampling points within a target distance segment, updating the plurality of initial tracks to obtain a plurality of candidate tracks, each of the candidate tracks including the distance information and energy information of at least one preset sampling point; splicing the plurality of candidate tracks to obtain a spliced track, and the spliced track is used to indicate the mapping relationship between the energy information and distance information of the target radar within the target distance segment.

[0203] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.

[0204] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0205] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A method for determining the radar energy distribution, characterized in that Including: Obtaining a plurality of initial tracks output by a target radar, each of the initial tracks including distance information and energy information of respective multiple sampling points within a corresponding distance segment; Updating the plurality of initial tracks based on the positions of multiple preset sampling points within a target distance segment to obtain a plurality of candidate tracks, each of the candidate tracks including distance information and energy information of at least one preset sampling point; Stitching the plurality of candidate tracks to obtain a stitched track, where the stitched track is used to indicate the mapping relationship between the energy information and the distance information of the target radar within the target distance segment.

2. The method according to claim 1, wherein The step of stitching the plurality of candidate tracks to obtain a stitched track includes: Determining a reference track among the plurality of candidate tracks; Stitching the reference track to other candidate tracks among the plurality of candidate tracks except the reference track to obtain the stitched track.

3. The method according to claim 2, wherein The step of stitching the reference track to other candidate tracks among the plurality of candidate tracks except the reference track to obtain the stitched track includes: Determining a track to be stitched among the other candidate tracks. For the first stitching, the track to be stitched is the other candidate track; Determining a first track having intersection sampling points with the reference track from the track to be stitched; stitching the reference track and the first track to obtain an updated reference track; the intersection sampling points are a subset of the multiple preset sampling points; Repeating the above operations based on the updated reference track until there is no track to be stitched among the other candidate tracks, and determining the updated reference track as the stitched track.

4. The method according to claim 3, characterized in that The step of stitching the reference track and the first track to obtain an updated reference track includes: Determining an energy multiple of the first track relative to the reference track based on the energy information of the intersection sampling points on the reference track and the energy information of the intersection sampling points on the first track; Stitching the reference track and the first track based on the energy multiple to obtain the updated reference track.

5. The method according to claim 4, wherein The step of stitching the reference track and the first track based on the energy multiple to obtain the updated reference track includes: Obtaining updated energy information of the intersection sampling points based on the energy multiple, the energy information of the intersection sampling points on the reference track, and the energy information of the intersection sampling points on the first track; Obtaining updated energy information of the other sampling points based on the energy multiple and the energy information of the other sampling points on the first track except the intersection sampling points; Updating the reference track based on the updated energy information of the intersection sampling points and the updated energy information of the other sampling points to obtain the updated reference track.

6. The method according to any one of claims 1-5, characterized in that, The step of updating the plurality of initial tracks based on the positions of multiple preset sampling points within a target distance segment to obtain a plurality of candidate tracks includes: For each of the initial tracks, determining a target preset sampling point within the distance segment of the initial track based on the positions of the multiple preset sampling points; Determine the distance information and energy information of the target preset sampling point based on the position of the initial track and the target preset sampling point; Obtain the candidate track corresponding to the initial track based on the distance information and energy information of the target preset sampling point.

7. The method according to claim 6, wherein The determining the distance information and energy information of the target preset sampling point based on the position of the initial track and the target preset sampling point includes: Determine the distance information of the target preset sampling point based on the position of the target preset sampling point; Perform filtering processing on the energy information of multiple sampling points corresponding to the initial track to obtain the filtered energy information of multiple sampling points corresponding to the initial track; Obtain the energy information of the target preset sampling point based on the position of the target preset sampling point and the filtered energy information of multiple sampling points corresponding to the initial track.

8. The method according to claim 7, characterized in that, The obtaining the energy information of the target preset sampling point based on the position of the target preset sampling point and the filtered energy information of multiple sampling points corresponding to the initial track includes: Based on the position of the target preset sampling point and the respective distance information of multiple sampling points corresponding to the initial track, determine at least one candidate sampling point from multiple sampling points corresponding to the initial track, and the distance between the target preset sampling point and the candidate sampling point is less than or equal to a preset distance; Determine the energy information of the target preset sampling point based on the filtered energy information of the at least one candidate sampling point.

9. A device for determining the radar energy distribution, characterized in that Includes: An acquisition module, configured to acquire multiple initial tracks output by a target radar, and each of the initial tracks includes the respective distance information and energy information of multiple sampling points within a corresponding distance segment; A processing module, configured to update the multiple initial tracks based on the positions of multiple preset sampling points within a target distance segment to obtain multiple candidate tracks, and each of the candidate tracks includes the distance information and energy information of at least one preset sampling point; A splicing module, configured to splice the multiple candidate tracks to obtain a spliced track, and the spliced track is used to indicate the mapping relationship between the energy information and the distance information of the target radar within the target distance segment.

10. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for determining the radar energy distribution according to any one of claims 1 to 8.

Images