Auxiliary track method and device for dense scene, vehicle and storage medium

Abstract

The invention discloses an auxiliary track method and device for a dense scene, a vehicle and a storage medium. The method comprises the following steps: acquiring current target detection data of a vehicle-mounted radar; based on the current target detection data, analyzing the distribution information of the current detection target in each detection sub-region of the current detection region of the vehicle-mounted radar; based on the distribution information of each current detection target, judging whether the number of target detection regions in each detection sub-region is greater than a preset threshold value or not; wherein the target detection area means that the detection sub-areas, the number of the current detection targets of which meets a preset number, exist in a substitution area; when the number of the target detection areas is greater than a preset threshold value, optimizing a track starting condition and track updating of the current detection target based on the distribution information of each current detection target; wherein the track starting condition of the current detection target is a condition for determining stable starting of the track.

Description

Technical Field

[0001] This application relates to the field of vehicle-mounted radar detection technology, and in particular to an auxiliary navigation method and device, vehicle, and storage medium for dense scenes. Background Technology

[0002] Millimeter-wave radar, with its high resolution, good weather adaptability, and real-time performance, is widely used in obstacle detection and avoidance in autonomous driving, becoming an important sensor device in driver assistance and autonomous driving solutions.

[0003] When a vehicle detects a target using millimeter-wave radar, it emits electromagnetic waves and receives the reflected echo from the target. By analyzing the time delay, amplitude, and phase characteristics of the reflected signal, it obtains information such as the target's position, distance, and speed, thereby obtaining the target's trajectory. This information is then used directly to assist the vehicle in its driving.

[0004] However, most vehicles nowadays are equipped with millimeter-wave radar, so when there are many vehicles, there will be a lot of wireless equipment generating interference signals, affecting signal extraction and processing. Furthermore, in congested scenarios, there are many metallic reflective objects, causing radar signals to be reflected and refracted along multiple paths during propagation, easily leading to false detections. Therefore, in congested environments, it is impossible to accurately detect target information, thus failing to accurately assist in navigation. Summary of the Invention

[0005] In view of the shortcomings of the prior art, this application provides an auxiliary track method and device, vehicle and storage medium for dense scenes, so as to solve the problem that the prior art cannot accurately detect information in dense scenes.

[0006] To achieve the above objectives, this application provides the following technical solution:

[0007] The first aspect of this application provides an auxiliary trajectory method for dense scenes, including:

[0008] Acquire current target detection data from the vehicle-mounted radar;

[0009] Based on the current target detection data, analyze the distribution information of the currently detected targets in each detection sub-region of the current detection area of ​​the vehicle radar;

[0010] Based on the distribution information of each of the current detection targets, it is determined whether the number of target detection regions in each of the detection sub-regions is greater than a preset threshold; wherein, the target detection region refers to the detection sub-region in which the number of the current detection targets in the region meets the preset number;

[0011] When it is determined that the number of target detection areas is greater than a preset threshold, the trajectory start conditions and trajectory updates of the current detection targets are optimized based on the distribution information of each current detection target; wherein, the trajectory start conditions of the current detection targets are the conditions for determining the stable start of the trajectory.

[0012] Optionally, in the above-described auxiliary trajectory method for dense scenes, the optimization of the trajectory start conditions and trajectory update of the current detected targets based on the distribution information of each of the current detected targets includes:

[0013] Based on the distribution information of each of the currently detected targets, the trajectory start transmission threshold of the currently detected targets is adjusted;

[0014] Based on the distribution information of each of the current detected targets, the current detected targets with abnormal tracks are analyzed, and the tracks of the current detected targets with abnormal tracks are corrected. For each current detected target that needs to restart its track, the track of the current detected target is generated.

[0015] Optionally, in the above-described auxiliary trajectory method for dense scenes, adjusting the trajectory start transmission threshold of the current detected target based on the distribution information of each of the currently detected targets includes:

[0016] Based on the distribution information of the current detection targets, the total number of current detection targets and the number of detection targets corresponding to each detection sub-region are determined; wherein, the total number of current detection targets is the number of current detection targets within the current detection region; and the number of detection targets corresponding to each detection sub-region is the number of current detection targets within the detection sub-region.

[0017] For each of the current detection targets, the starting transmission threshold of the current detection target is adjusted according to the number of detection targets corresponding to the detection sub-region in which it is located and the total number of current detection targets.

[0018] Optionally, in the above-described auxiliary trajectory method for dense scenes, the step of analyzing the distribution information of each of the currently detected targets to identify those with abnormal trajectories and correcting the trajectories of the abnormally detected targets includes:

[0019] Based on the distribution information of each of the current detection targets, each of the neighboring detection targets of each of the current detection targets is determined;

[0020] For each of the currently detected targets, determine whether there is an anomaly in the speed of the trajectory of the currently detected target based on each of the neighboring detected targets;

[0021] If the speed of the trajectory of the currently detected target is abnormal, the speed of the trajectory of the currently detected target is corrected based on each of the neighboring detected targets.

[0022] Optionally, in the above-described auxiliary trajectory method for dense scenes, generating a trajectory for each currently detected target that requires a new trajectory start includes:

[0023] Identify each currently detected target whose outbound trajectory does not match the point cloud;

[0024] For each identified current detection target, the starting direction of the current detection target is determined based on the distribution information of each current detection target;

[0025] Using the distance, azimuth, and Doppler information of the currently detected target detected by the vehicle-mounted radar, the position information and relative speed of the currently detected target are calculated.

[0026] Optionally, in the above-described assisted trajectory method for dense scenes, before analyzing the distribution information of the currently detected targets in each detection sub-region of the current detection area of ​​the vehicle-mounted radar based on the current target detection data, the method further includes:

[0027] In the coordinate system of the vehicle-mounted radar, the current detection area is divided vertically according to two set lateral position thresholds, and horizontally divided according to multiple set lateral position thresholds to obtain multiple detection sub-regions; wherein, the coordinate system of the vehicle-mounted radar is a coordinate system with the location of the vehicle-mounted radar as the origin.

[0028] Optionally, in the above-described auxiliary trajectory method for dense scenes, the step of analyzing the distribution information of currently detected targets within each detection sub-region of the current detection area of ​​the vehicle-mounted radar based on the current target detection data includes:

[0029] Iterate through each of the currently detected targets in the current target detection data;

[0030] Determine whether the x-coordinate of the current target's position coordinates in the currently traversed target detection data is within the range of the two x-coordinate thresholds;

[0031] If it is determined that the horizontal coordinate of the current detected target is within the range of the two horizontal position thresholds, then the detection sub-region where the current detected target is located is determined by comparing the vertical coordinate of the current detected target with each of the vertical position thresholds.

[0032] A second aspect of this application provides a navigation aid for dense environments, comprising:

[0033] The data acquisition unit is used to acquire the current target detection data of the vehicle-mounted radar;

[0034] The distribution analysis unit is used to analyze the distribution information of the currently detected target in each detection sub-region of the current detection area of ​​the vehicle radar based on the current target detection data.

[0035] The scene determination unit is used to determine whether the number of target detection regions in each of the detection sub-regions is greater than a preset threshold based on the distribution information of each of the current detection targets; wherein, the target detection region refers to the detection sub-region in which the number of the current detection targets in the region meets the preset number;

[0036] An optimization unit is used to optimize the trajectory start conditions and trajectory update of the current detection target based on the distribution information of each current detection target when it is determined that the number of target detection areas is greater than a preset threshold; wherein, the trajectory start conditions of the current detection target are the conditions for determining the stable start of the trajectory.

[0037] Optionally, in the above-mentioned auxiliary trajectory device for dense scenarios, the optimization unit includes:

[0038] The threshold adjustment unit is used to adjust the trajectory start transmission threshold of the current detected target based on the distribution information of each of the current detected targets;

[0039] The trajectory correction unit is used to analyze the trajectory of the current detected target with abnormal trajectory based on the distribution information of each of the current detected targets, and to correct the trajectory of the current detected target with abnormal trajectory.

[0040] The track update unit is used to generate a track for each of the currently detected targets that needs to restart the track, based on the distribution information of each of the currently detected targets.

[0041] Optionally, in the above-mentioned auxiliary trajectory device for dense scenes, the threshold adjustment unit includes:

[0042] The quantity determination unit is used to determine the total number of current detection targets and the number of detection targets corresponding to each detection sub-region based on the distribution information of the current detection targets; wherein, the total number of current detection targets is the number of current detection targets within the current detection region; and the number of detection targets corresponding to each detection sub-region is the number of current detection targets within the detection sub-region.

[0043] The transmission threshold adjustment unit is used to adjust the initial transmission threshold of each current detection target based on the number of detection targets corresponding to the detection sub-region in which it is located and the total number of current detection targets.

[0044] Optionally, in the above-mentioned auxiliary trajectory device for dense scenes, the trajectory correction unit includes:

[0045] The target determination unit is used to determine each neighboring target of each current detection target based on the distribution information of each current detection target;

[0046] An anomaly detection unit is used to determine, for each currently detected target, whether the speed of the trajectory of the currently detected target is abnormal based on each of the neighboring detected targets of the current detected target;

[0047] A speed correction unit is used to correct the speed of the trajectory of the currently detected target based on each of its neighboring detected targets when the speed of the trajectory of the currently detected target is abnormal.

[0048] Optionally, in the above-mentioned auxiliary track device for dense scenarios, the track update unit includes:

[0049] A matching unit is used to identify each of the currently detected targets whose tracks do not match the point cloud;

[0050] The direction determination unit is used to determine the starting direction of each current detection target based on the distribution information of each current detection target.

[0051] The information calculation unit is used to calculate the position information and relative speed of the currently detected target using the distance, azimuth angle and Doppler information of the currently detected target detected by the vehicle-mounted radar.

[0052] Optionally, the aforementioned auxiliary navigation device for dense scenarios further includes:

[0053] The region division unit is used to divide the current detection region longitudinally according to two set lateral position thresholds and laterally according to multiple set lateral position thresholds in the coordinate system of the vehicle radar to obtain multiple detection sub-regions; wherein the coordinate system of the vehicle radar is a coordinate system with the location of the vehicle radar as the origin.

[0054] Optionally, in the above-mentioned auxiliary trajectory device for dense scenes, the distribution analysis unit includes:

[0055] A traversal unit is used to traverse each of the currently detected targets in the current target detection data;

[0056] The horizontal coordinate judgment unit is used to determine whether the horizontal coordinate of the position coordinate of the currently detected target in the currently traversed target detection data is within the range of the two horizontal position thresholds;

[0057] The ordinate determination unit is used to determine the detection sub-region where the current detection target is located by comparing the ordinate of the current detection target's position coordinates with each of the two lateral position thresholds when it is determined that the lateral coordinate of the current detection target is within the range of the two lateral position thresholds.

[0058] A third aspect of this application provides a vehicle, comprising:

[0059] Vehicle-mounted radar and electronic control units;

[0060] The vehicle-mounted radar is used to collect current target detection data;

[0061] The electronic control unit is used to execute a program, specifically to implement the assisted navigation method for dense scenarios as described in any of the above.

[0062] A fourth aspect of this application provides a computer storage medium for storing a computer program, which, when executed by a processor, is used to implement the assisted navigation method for dense scenes as described in any of the preceding claims.

[0063] This application provides an auxiliary trajectory method for dense scenes. It acquires current target detection data from a vehicle-mounted radar, and then analyzes the distribution information of currently detected targets within each sub-region of the current detection area, thereby obtaining the distribution of each currently detected target across the current detection area. Next, based on the distribution information of each currently detected target, it determines whether the number of target detection areas in each sub-region exceeds a preset threshold. Here, a target detection area refers to a sub-region within the area where the number of currently detected targets meets a preset threshold. When the number of target detection areas exceeds the preset threshold, it indicates that the vehicle is currently in a dense scene, thus comprehensively evaluating the distribution of detected targets in each sub-region and accurately identifying the dense scene. Then, based on the distribution information of each currently detected target, it optimizes the trajectory start conditions and trajectory updates for the current detected targets. The trajectory start conditions for the current detected targets are conditions for determining a stable trajectory start, which can effectively eliminate false information detected and ensure data accuracy. Furthermore, by optimizing the trajectory updates, detection errors are eliminated, improving the accuracy of the detection data, thus obtaining a method that can accurately identify dense scenes and assist in obtaining accurate trajectories. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0065] Figure 1 A flowchart illustrating an auxiliary trajectory method for dense scenes provided in an embodiment of this application;

[0066] Figure 2 A schematic diagram illustrating an example of the division of a detection region provided in an embodiment of this application;

[0067] Figure 3 A flowchart illustrating a method for analyzing the distribution information of currently detected targets, provided as an embodiment of this application;

[0068] Figure 4 A flowchart illustrating a method for optimizing trajectory initiation conditions and trajectory, provided in an embodiment of this application;

[0069] Figure 5 A flowchart illustrating a method for correcting abnormal flight paths, provided in an embodiment of this application;

[0070] Figure 6 A schematic diagram illustrating an example of the relationship between the position information and relative velocity of a target and track information provided in an embodiment of this application;

[0071] Figure 7 A schematic diagram of the architecture of an auxiliary navigation device for dense scenes provided in an embodiment of this application;

[0072] Figure 8 This is a schematic diagram of the architecture of a vehicle provided in an embodiment of this application. Detailed Implementation

[0073] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0074] In this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0075] Another embodiment of this application provides an auxiliary track method for dense scenes, such as... Figure 1 As shown, it includes the following steps:

[0076] S101. Obtain the current target detection data of the vehicle-mounted radar.

[0077] Optionally, the vehicle-mounted radar can be a millimeter-wave radar.

[0078] Specifically, the vehicle-mounted radar emits electromagnetic waves and receives reflected echoes from targets. Then, by analyzing characteristics such as the time delay, amplitude, and phase of the reflected signals, current target detection data is obtained. Optionally, the current target detection data may include the position information of each detected target.

[0079] S102. Based on the current target detection data, analyze the distribution information of the currently detected targets in each detection sub-region of the current detection area of ​​the vehicle radar.

[0080] The current detection area refers to the range currently detected by the vehicle-mounted radar. The current detection target refers to the target currently detected by the vehicle-mounted radar.

[0081] It should be noted that only when targets are widely detected throughout the current detection area does it meet the criteria for a densely congested scenario that would affect the vehicle's radar. If the detected targets are concentrated in a small area, and the number of detected targets is large, it may not necessarily affect the vehicle's radar detection, or the impact may be minimal. Therefore, in this embodiment, the current detection area is divided into multiple detection sub-regions. Then, based on the information of each currently detected target in the current target detection data, the distribution of each currently detected target within each detection sub-region is analyzed. Optionally, the distribution within each detection sub-region may include which detection sub-region each currently detected target is located in, the number of currently detected targets in each detection sub-region, and the relative positional distribution of each currently detected target. Thus, based on the distribution of each currently detected target within each detection sub-region, it is determined whether the detected targets are widely present throughout the entire current detection area, thereby determining whether the vehicle is currently in a densely congested scenario.

[0082] Optionally, the current detection area can be divided into multiple detection sub-areas of equal size according to a certain area, or other methods can be used for division.

[0083] Optionally, in another embodiment of this application, a method for dividing a detection sub-region is provided, including:

[0084] In the coordinate system of the vehicle radar, the current detection area is divided vertically according to two set lateral position thresholds, and horizontally divided according to multiple set lateral position thresholds to obtain multiple detection sub-regions.

[0085] The coordinate system of the vehicle-mounted radar is a coordinate system with the location of the vehicle-mounted radar as the origin.

[0086] It should be noted that, considering that targets at the edges of the radar detection area have little impact on the vehicle-mounted radar, and since these targets are not in the direction of the vehicle, they will not affect the vehicle's movement, in this embodiment, two lateral position thresholds are set based on actual analysis. For example... Figure 2 As shown, in the coordinate system of the vehicle radar, a horizontal position threshold (x1 and x2) is set on the left and right sides of the origin, respectively. That is, two values ​​are set on the horizontal coordinate. By dividing the vertically according to the two horizontal position thresholds, a region within the range between the two horizontal position thresholds can be obtained.

[0087] Optionally, since the detection area of ​​the vehicle radar is symmetrical with respect to the vehicle radar, the two lateral position thresholds are set to have the same absolute value, which corresponds to the values ​​on the opposite horizontal coordinates.

[0088] Since the closer the target is to the vehicle-mounted radar, the greater its impact on detection. Therefore, in this embodiment, multiple longitudinal position thresholds are set. This allows for lateral segmentation according to these thresholds, further dividing the longitudinally segmented area into multiple rectangular detection sub-regions. Furthermore, by using the lateral and longitudinal position thresholds to segment each detection sub-region, the corresponding thresholds for the x and y coordinates of each region can be obtained, i.e., the coordinate range of each region. This facilitates subsequent analysis to determine the detection sub-region where each currently detected target is located. For example, as... Figure 2 As shown, y1, y2, ..., yn are set, so that the horizontal segmentation can be performed according to these vertical position thresholds, thereby dividing the current detection area into n detection sub-regions with horizontal coordinate range of [x1, x2] and vertical coordinate range of [0, y1], [y1, y2], ..., [yn-1, yn].

[0089] Accordingly, in another embodiment of this application, a specific implementation of step S102 is as follows: Figure 3 As shown, it includes:

[0090] S301. Traverse each currently detected target in the current target detection data.

[0091] S302. Determine whether the horizontal coordinate of the current target's position in the current target detection data is within the range of the two horizontal position thresholds.

[0092] If the x-coordinate of the current detection target is determined to be within the range of two horizontal position thresholds, it indicates that the current detection target is within the defined detection area. Therefore, targets outside the defined area are quickly filtered out using the x-coordinate. For targets within the detection area, further analysis of the sub-region in which they are located is required, so step S303 is executed at this point.

[0093] S303. By comparing the vertical coordinate of the current target's location with each vertical position threshold, the detection sub-region where the current target is located is determined.

[0094] Specifically, by comparing the vertical coordinate of the current detected target's location with various vertical position thresholds, the range of the vertical coordinate of the current detected target is determined, thereby determining the detection sub-region.

[0095] S103. Based on the distribution information of each current detection target, determine whether the number of target detection areas in each detection sub-region is greater than a preset threshold.

[0096] The target detection area refers to a sub-region within the area where the number of currently detected targets meets a preset number. The preset number is at least 1.

[0097] Optionally, a preset number can be set to define a detection sub-region where the number of currently detected targets is greater than or equal to the preset number as a target detection region. Alternatively, a corresponding number can be set for each detection sub-region, and the preset number for each sub-region can be used to determine whether it belongs to a target detection region. For example, since the closer a target is to the vehicle radar, the greater its impact; therefore, even a small number of targets can have a significant impact on the vehicle radar. Thus, the preset number can be set larger for areas farther from the vehicle radar.

[0098] It should be noted that if the number of target detection areas is greater than the preset threshold, it means that most of the detection sub-regions have a large number of detection targets, which means that the current detection targets are very dense, that is, the vehicle is currently in a dense scene, so step S104 is executed at this time.

[0099] S104. Based on the distribution information of each currently detected target, optimize the trajectory start conditions and trajectory update of the current detected target.

[0100] Because this is a dense scene, each currently detected target will affect the detected data. Therefore, it is necessary to optimize the trajectory initiation conditions and trajectory updates of the current detected targets based on the distribution information of each target. Specifically, based on the impact of dense scenes on the detection data of the targets and experience in eliminating these impacts, corresponding optimization logic is set to optimize the trajectory initiation conditions and trajectory updates of the current detected targets.

[0101] The current target track initiation condition is the condition for determining the stable initiation of the track. This refers to determining the stable and mature conditions of the track when detecting it. In other words, the track is considered to have started only after certain conditions are met. If the conditions are not met, it indicates a false target. Therefore, this method can help avoid false alarms, i.e., detect false targets.

[0102] Since false points are relatively easy to detect in dense scenes, it is necessary to optimize and adjust the starting conditions of the current target's trajectory to adapt to dense scenes, usually by adjusting to more stringent conditions. Specific adjustment conditions can be pre-analyzed and set to account for the impact of dense scenes.

[0103] Similarly, since signal extraction and processing in dense scenes can affect signal quality and thus the generated track, corresponding optimization logic can be set according to the impact of dense scenes on the track. This can optimize the generated mature and stable track of the current detection target, eliminate the impact, and ensure the accuracy of the track.

[0104] Optionally, in another embodiment of this application, one specific implementation of step S105 is as follows: Figure 4 As shown, it includes:

[0105] S401. Based on the distribution information of each currently detected target, adjust the trajectory start transmission threshold of the currently detected target.

[0106] The initial transmission threshold is the threshold for the cumulative number of cycles transmitted to the auxiliary system to determine the stability of the target's trajectory.

[0107] It should be noted that the radar-detected track accumulates a clock count from the first frame of point cloud detection. When the clock count exceeds the initial transmission threshold, the track is considered a stable and mature target, and only then is it output for subsequent ADAS fusion. If the relevant point cloud cannot be detected before the clock count exceeds the initial transmission threshold, it indicates a false target, and its track will not be generated.

[0108] Optionally, in another embodiment of this application, one specific implementation of step S401 includes:

[0109] Based on the distribution information of the current detection targets, the total number of current detection targets and the number of detection targets corresponding to each detection sub-region are determined. For each current detection target, the starting transmission threshold of the current detection target is adjusted according to the number of detection targets corresponding to its detection sub-region and the total number of current detection targets.

[0110] The total number of currently detected targets is the number of currently detected targets within the current detection area. The number of detected targets corresponding to a detection sub-region is the number of currently detected targets within that sub-region.

[0111] It should be noted that the impact varies depending on the total number of current detection targets, and the detection targets in the same detection sub-region also affect each other. Therefore, in this application, both the total number of current detection targets and the number of detection targets in the corresponding detection sub-region are considered, and the initial sending threshold is adjusted accordingly to make the adjusted threshold more accurate.

[0112] S402. Based on the distribution information of each currently detected target, analyze the currently detected targets with abnormal tracks and correct the tracks of the currently detected targets with abnormal tracks.

[0113] It should be noted that due to the influence of dense scenes, some established tracks may be abnormal, that is, they may not conform to the actual situation. For example, if a target's track is heading towards an obstacle, this is obviously abnormal. Therefore, it is necessary to correct the track of the currently detected target with abnormal track.

[0114] To ensure that the modified trajectory is not also abnormal, it needs to be adjusted based on the distribution information of each currently detected target. For example, when adjusting a trajectory that is heading towards an obstacle, the direction of the trajectory can be adjusted based on the distribution of each currently detected target to avoid heading towards other currently detected targets.

[0115] Optionally, in another embodiment of this application, one specific implementation of step S402 is as follows: Figure 5 As shown, it includes:

[0116] S501. Based on the distribution information of each current detection target, determine each neighboring detection target of each current detection target.

[0117] It should be noted that whether the trajectory of a currently detected target is abnormal is mainly relative to other nearby targets, that is, obstacles around the currently detected target. Therefore, we can first determine the nearby detected targets of each currently detected target based on the coordinates of the distribution of each currently detected target.

[0118] S502. For each currently detected target, determine whether there is an anomaly in the speed of the current detected target's trajectory based on the various neighboring detected targets.

[0119] In this embodiment, the anomaly determination of the trajectory mainly involves determining whether its speed is abnormal. Specifically, based on the various neighboring targets of the currently detected target, it is determined whether the speed magnitude and speed direction of the current detected target's trajectory are abnormal. For example, if the current detected target is close to a neighboring target but its speed is high, it indicates that its speed is abnormal. If the current detected target's speed direction is towards colliding with other targets, it indicates that its speed direction is abnormal. Therefore, if the speed magnitude or direction of the current detected target's trajectory is abnormal, step S503 is executed.

[0120] S503. Correct the speed of the current target's trajectory based on the neighboring targets of the current target.

[0121] Optionally, the speed direction can be adjusted to avoid nearby detection targets, and the speed magnitude can be adjusted to match the distance between the speed and obstacles. Optionally, the magnitude of the speed direction and speed adjustment can be pre-analyzed for various conditions, i.e., summarizing the adjustment experience information for various conditions, so that previous experience information can be directly used for adjustment.

[0122] S403. Based on the distribution information of each currently detected target, generate a track for each currently detected target that needs to restart the track.

[0123] It should be noted that during radar detection, there may be situations where the point cloud detected by the radar does not match the mature track detected by the radar. In such cases, a new track needs to be generated. To ensure that the generated track is accurate and utilizes the current dense scene, the track of the currently detected target is generated based on the distribution information of each currently detected target.

[0124] Steps S402 and S403 are independent, so the execution order in this embodiment is only one possible way. The two steps can be executed simultaneously, or step S403 can be executed first and then step S402 can be executed.

[0125] Optionally, in another embodiment of this application, one specific implementation of step S403 includes:

[0126] Each currently detected target whose track does not match the point cloud is identified. Then, for each identified currently detected target, the starting direction of the target is determined based on the distribution information of each target. The position information and relative speed of the target are calculated using the distance, azimuth angle and Doppler information of the target detected by the vehicle radar.

[0127] Specifically, the point cloud of the radar-detected target and the mature track detected by the radar are identified as currently detected targets that do not match. Then, based on the distribution information of each currently detected target, the starting direction of the currently detected target can be determined. Finally, using the range r, azimuth α, and Doppler information v of the currently detected target detected by the vehicle-mounted radar, the position information (x, y) and relative velocity V1 of the currently detected target are calculated.

[0128] Specifically, the relationship between the target's position information and relative velocity and distance r, azimuth angle α, and Doppler information v, such as Figure 6 As shown, the specific calculation process is as follows:

[0129]

[0130]

[0131]

[0132] This application provides an auxiliary trajectory method for dense scenes. It acquires current target detection data from a vehicle-mounted radar, and then analyzes the distribution information of currently detected targets within each sub-region of the current detection area, thereby obtaining the distribution of each currently detected target across the various regions of the current detection area. Next, based on the distribution information of each currently detected target, it determines whether the number of target detection regions in each sub-region exceeds a preset threshold. Here, a target detection region refers to a sub-region within the area where the number of currently detected targets meets a preset threshold. If the number of target detection regions exceeds the preset threshold, it indicates that the vehicle is currently in a dense scene, thus comprehensively evaluating the distribution of detected targets in each sub-region and accurately identifying the dense scene. Then, based on the distribution information of each currently detected target, it optimizes the trajectory start conditions and trajectory updates for the current detected targets. The trajectory start conditions for the current detected targets are conditions for determining a stable trajectory start, thereby effectively eliminating false information and ensuring data accuracy. Furthermore, by optimizing the trajectory updates, detection errors are eliminated, improving the accuracy of the detection data.

[0133] Another embodiment of this application provides an auxiliary navigation device for dense scenes, such as... Figure 7 As shown, it includes:

[0134] The data acquisition unit 701 is used to acquire the current target detection data of the vehicle-mounted radar.

[0135] The distribution analysis unit 702 is used to analyze the distribution information of the currently detected targets in each detection sub-region of the current detection area of ​​the vehicle radar based on the current target detection data.

[0136] The scene judgment unit 703 is used to determine whether the number of target detection regions in each detection sub-region is greater than a preset threshold based on the distribution information of each currently detected target. Here, a target detection region refers to a detection sub-region within a region where the number of currently detected targets meets a preset threshold.

[0137] The optimization unit 704 is used to optimize the trajectory start conditions and trajectory update of the current detected target based on the distribution information of each currently detected target when it is determined that the number of target detection areas is greater than a preset threshold. The trajectory start conditions of the current detected target are the conditions for determining a stable trajectory start.

[0138] Optionally, in another embodiment of the auxiliary track device for dense scenes provided in this application, the optimization unit includes:

[0139] The threshold adjustment unit is used to adjust the trajectory start transmission threshold of the current detected target based on the distribution information of each current detected target.

[0140] The track correction unit is used to analyze the distribution information of each currently detected target, identify the currently detected target with an abnormal track, and correct the track of the currently detected target with an abnormal track.

[0141] The track update unit is used to generate a track for each currently detected target that needs to restart its track, based on the distribution information of each currently detected target.

[0142] Optionally, in another embodiment of the auxiliary track device for dense scenes provided in this application, the threshold adjustment unit includes:

[0143] The quantity determination unit is used to determine the total number of currently detected targets and the number of targets corresponding to each detection sub-region based on the distribution information of the currently detected targets. The total number of currently detected targets refers to the number of currently detected targets within the current detection region. The number of targets corresponding to each detection sub-region refers to the number of currently detected targets within that sub-region.

[0144] The transmission threshold adjustment unit is used to adjust the initial transmission threshold of each current detection target based on the number of detection targets corresponding to its detection sub-region and the total number of current detection targets.

[0145] Optionally, in another embodiment of the auxiliary track device for dense scenes provided in this application, the track correction unit includes:

[0146] The target determination unit is used to determine each neighboring target of each current detection target based on the distribution information of each current detection target.

[0147] The anomaly detection unit is used to determine whether the speed of the current detection target's trajectory is abnormal for each current detection target, based on the various neighboring detection targets.

[0148] The speed correction unit is used to correct the speed of the current detected target's trajectory based on the speed of each of its neighboring detected targets when the speed of the current detected target's trajectory is abnormal.

[0149] Optionally, in another embodiment of the auxiliary track device for dense scenes provided in this application, the track update unit includes:

[0150] The matching unit is used to identify each currently detected target that does not match the track and the point cloud.

[0151] The direction determination unit is used to determine the starting direction of each current detection target based on the distribution information of each current detection target.

[0152] The information calculation unit is used to calculate the position information and relative speed of the currently detected target using the distance, azimuth angle and Doppler information of the currently detected target detected by the vehicle-mounted radar.

[0153] Optionally, in another embodiment of the auxiliary navigation device for dense scenes provided in this application, the device further includes:

[0154] The region segmentation unit is used to divide the current detection area vertically according to two set lateral position thresholds, and horizontally according to multiple set lateral position thresholds, in the coordinate system of the vehicle-mounted radar, to obtain multiple detection sub-regions. The coordinate system of the vehicle-mounted radar is a coordinate system with the location of the vehicle-mounted radar as the origin.

[0155] Optionally, in another embodiment of the auxiliary track device for dense scenes provided in this application, the distribution analysis unit includes:

[0156] The traversal unit is used to traverse each currently detected target in the current target detection data.

[0157] The horizontal coordinate judgment unit is used to determine whether the horizontal coordinate of the current target's position coordinate in the current target detection data being traversed is within the range of two horizontal position thresholds.

[0158] The vertical coordinate judgment unit is used to determine the detection sub-region where the current detection target is located by comparing the vertical coordinate of the current detection target's position coordinate with each vertical position threshold when the horizontal coordinate of the current detection target is determined to be within the range of two horizontal position thresholds.

[0159] It should be noted that the specific working process of each unit provided in the above embodiments of this application can be referred to the implementation process of the corresponding steps in the above method embodiments, and will not be repeated here.

[0160] Another embodiment of this application provides a vehicle, such as Figure 8 As shown, it includes:

[0161] Vehicle-mounted radar 801 and electronic control unit 802.

[0162] Among them, the vehicle-mounted radar 801 is used to collect current target detection data.

[0163] The electronic control unit 802 is used to execute a program, specifically to implement the assisted track method for dense scenes as provided in any of the above embodiments.

[0164] Another embodiment of this application provides a computer storage medium for storing a computer program, which, when executed by a processor, is used to implement the assisted navigation method for dense scenes as provided in any of the above embodiments.

[0165] Computer storage media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0166] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0167] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for assisting navigation in dense scenes, characterized in that, include: Acquire current target detection data from the vehicle-mounted radar; Based on the current target detection data, analyze the distribution information of the currently detected targets in each detection sub-region of the current detection area of ​​the vehicle radar; Based on the distribution information of each of the current detection targets, it is determined whether the number of target detection regions in each of the detection sub-regions is greater than a preset threshold; wherein, the target detection region refers to the detection sub-region in which the number of the current detection targets in the region meets the preset number; When the number of target detection areas is greater than a preset threshold, the trajectory start conditions and trajectory updates of the current detection targets are optimized based on the distribution information of each current detection target; wherein, the trajectory start conditions of the current detection targets are the conditions for determining the stable start of the trajectory.

2. The method according to claim 1, characterized in that, The optimization of the trajectory start conditions and trajectory update of the current detected targets based on the distribution information of each of the current detected targets includes: Based on the distribution information of each of the currently detected targets, the trajectory start transmission threshold of the currently detected targets is adjusted; Based on the distribution information of each of the current detected targets, the current detected targets with abnormal tracks are analyzed, and the tracks of the current detected targets with abnormal tracks are corrected. For each current detected target that needs to restart its track, the track of the current detected target is generated.

3. The method according to claim 2, characterized in that, The step of adjusting the trajectory start transmission threshold of the current detected target based on the distribution information of each of the current detected targets includes: Based on the distribution information of the current detection targets, the total number of current detection targets and the number of detection targets corresponding to each detection sub-region are determined; wherein, the total number of current detection targets is the number of current detection targets within the current detection region; and the number of detection targets corresponding to each detection sub-region is the number of current detection targets within the detection sub-region. For each of the current detection targets, the starting transmission threshold of the current detection target is adjusted according to the number of detection targets corresponding to the detection sub-region in which it is located and the total number of current detection targets.

4. The method according to claim 2, characterized in that, The step of analyzing the distribution information of each of the currently detected targets to identify those with abnormal flight paths and correcting the flight paths of these abnormal targets includes: Based on the distribution information of each of the current detection targets, each of the neighboring detection targets of each of the current detection targets is determined; For each of the currently detected targets, determine whether there is an anomaly in the speed of the trajectory of the currently detected target based on each of the neighboring detected targets; If the speed of the trajectory of the currently detected target is abnormal, the speed of the trajectory of the currently detected target is corrected based on each of the neighboring detected targets.

5. The method according to claim 2, characterized in that, The step of generating a trajectory for each currently detected target that requires a new trajectory start includes: Identify each currently detected target whose outbound trajectory does not match the point cloud; For each identified current detection target, the starting direction of the current detection target is determined based on the distribution information of each current detection target; Using the distance, azimuth, and Doppler information of the currently detected target detected by the vehicle-mounted radar, the position information and relative speed of the currently detected target are calculated.

6. The method according to claim 1, characterized in that, Before analyzing the distribution information of currently detected targets in each detection sub-region of the current detection area of ​​the vehicle-mounted radar based on the current target detection data, the method further includes: In the coordinate system of the vehicle-mounted radar, the current detection area is divided vertically according to two set lateral position thresholds, and horizontally divided according to multiple set lateral position thresholds to obtain multiple detection sub-regions; wherein, the coordinate system of the vehicle-mounted radar is a coordinate system with the location of the vehicle-mounted radar as the origin.

7. The method according to claim 6, characterized in that, The step of analyzing the distribution information of currently detected targets in each detection sub-region of the current detection area of ​​the vehicle-mounted radar based on the current target detection data includes: Iterate through each of the currently detected targets in the current target detection data; Determine whether the x-coordinate of the current target's position coordinates in the currently traversed target detection data is within the range of the two x-coordinate thresholds; If it is determined that the horizontal coordinate of the current detected target is within the range of the two horizontal position thresholds, then the detection sub-region where the current detected target is located is determined by comparing the vertical coordinate of the current detected target with each of the vertical position thresholds.

8. A navigation aid for dense environments, characterized in that, include: The data acquisition unit is used to acquire the current target detection data of the vehicle-mounted radar; The distribution analysis unit is used to analyze the distribution information of the currently detected target in each detection sub-region of the current detection area of ​​the vehicle radar based on the current target detection data. The scene determination unit is used to determine whether the number of target detection regions in each of the detection sub-regions is greater than a preset threshold based on the distribution information of each of the current detection targets; wherein, the target detection region refers to the detection sub-region in which the number of the current detection targets in the region meets the preset number; An optimization unit is used to optimize the trajectory start conditions and trajectory updates of the current detected targets based on the distribution information of each of the current detected targets when the number of target detection areas is greater than a preset threshold; wherein, the trajectory start conditions of the current detected targets are the conditions for determining the stable start of the trajectory.

9. A vehicle, characterized in that, include: Vehicle-mounted radar and electronic control units; The vehicle-mounted radar is used to collect current target detection data; The electronic control unit is used to execute a program to specifically implement the assisted navigation method in dense scenes as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, Used to store a computer program, which, when executed by a processor, is used to implement the assisted navigation method for dense scenes as described in any one of claims 1 to 7.

Images