Target deduplication method, device, equipment, medium and product
By matching and deduplication of the perceived targets to be matched in the OBU device, the problems of data redundancy and repeated calculations are solved, and data deduplication and calculation accuracy are improved.
Patent Information
- Application Number
- CN202411910439.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-24
- Publication Date
- 2025-03-28
AI Technical Summary
When OBU devices receive multi-source data between the vehicle and the environment, data redundancy and repeated calculations are prone to data redundancy, resulting in target display errors and early warning false alarms.
By obtaining the perceived targets to be matched and connecting targets, data matching and deduplication are performed, ensuring that only successful matching data are retained, thereby avoiding data redundancy and repeated calculations.
Deduplication of multi-source data targets is achieved, solving the problems of data redundancy and memory resource waste of OBU equipment, and avoiding calculation errors and early warning false alarms.
Smart Images
Figure CN119729409A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a target deduplication method, device, equipment, medium and product. Background Art
[0002] Vehicle-road collaboration with vehicle to everything (V2X) wireless communication technology as its core is an important application in the field of urban smart transportation. V2X technology can realize data interaction between vehicles and multiple elements in their external environment, such as communication between vehicles and roadside equipment, vehicle-to-vehicle communication, and vehicle-to-pedestrian communication.
[0003] The Road Side Unit (RSU) can send the perceived object data to the On-board Unit (OBU) through the Road Side Safety Message (RSM). At the same time, the OBU can also receive V2X data from other OBUs through the Basic Safety Message (BSM), resulting in the OBU receiving two or even multiple copies of the same target object. This phenomenon, on the one hand, can easily cause data redundancy and waste of storage resources within the OBU device, and on the other hand, it can easily cause the OBU to repeatedly calculate the same data, resulting in problems such as target display errors and false warnings. Summary of the invention
[0004] The present invention provides a target deduplication method, device, equipment, medium and product, which realizes the deduplication of multi-source data targets, solves the problems of data redundancy and memory resource waste in OBU equipment, and further avoids calculation errors and false warnings caused by repeated calculations based on the same data target.
[0005] In a first aspect, an embodiment of the present disclosure provides a target deduplication method, including:
[0006] Obtaining the perception target to be matched and the network connection target to be matched;
[0007] Performing data matching on the to-be-matched sensing target and the to-be-matched networked target to obtain a matching result;
[0008] If the matching result indicates that the to-be-matched perceived target and the to-be-matched networked target are matched successfully, deduplication processing is performed on the to-be-matched perceived target and the to-be-matched networked target.
[0009] In a second aspect, an embodiment of the present disclosure provides a target deduplication device, comprising:
[0010] A data acquisition module is used to acquire the perception target to be matched and the network connection target to be matched;
[0011] A data matching module is used to perform data matching between the to-be-matched sensing target and the to-be-matched networked target to obtain a matching result;
[0012] The target deduplication module is used to deduplicate the perceived target to be matched and the networked target to be matched if the matching result indicates that the perceived target to be matched and the networked target to be matched are successfully matched.
[0013] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:
[0014] at least one processor; and
[0015] a memory communicatively connected to at least one processor; wherein,
[0016] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute a target deduplication method provided in the above-mentioned first aspect embodiment.
[0017] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a processor to implement a target deduplication method provided in the embodiment of the first aspect above when executing.
[0018] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements a target deduplication method provided in the embodiment of the first aspect.
[0019] A target deduplication method, device, equipment, medium and product of an embodiment of the present invention includes obtaining a perception target to be matched and a networked target to be matched; performing data matching on the perception target to be matched and the networked target to be matched to obtain a matching result; if the matching result indicates that the perception target to be matched and the networked target to be matched are matched successfully, then performing deduplication processing on the perception target to be matched and the networked target to be matched. The above technical solution realizes the deduplication of multi-source data targets, solves the problems of data redundancy and memory resource waste in OBU devices, and further avoids calculation errors and false alarms caused by repeated calculations based on the same data targets.
[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0022] Figure 1 is a flow chart of a target deduplication method provided in Embodiment 1 of the present invention;
[0023] Figure 2 is a flow chart of a target deduplication method provided in Embodiment 2 of the present invention;
[0024] Figure 3 is another flow chart of a target deduplication method provided by the second embodiment of the present invention;
[0025] Figure 4 is a structural schematic diagram of a target deduplication device provided in Embodiment 3 of the present invention;
[0026] Figure 5 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION
[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0028] It should be noted that the terms "first", "second" and "target" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0029] Embodiment 1
[0030] Figure 1It is a flow chart of a target deduplication method provided in Example 1 of the present invention. This embodiment can be applied to the situation where deduplication processing is performed on perceived targets and networked targets at the same time or similar time. The method can be executed by a target deduplication device, and the target deduplication device can be implemented in the form of hardware and / or software.
[0031] like Figure 1 As shown, the method includes:
[0032] S101. Obtain a perception target to be matched and a networked target to be matched.
[0033] In this embodiment, the perception target to be matched can be understood as the roadside safety message RSM collected and transmitted by the road test unit RSU, which at least includes position coordinates, speed, acceleration, heading angle and yaw rate, and track point information. The networked target to be matched can be understood as the basic safety message BSM transmitted by the OBU in other vehicles deployed with the V2X network, which at least includes position coordinates, speed, acceleration, heading angle and yaw rate, and track point information. It can be understood that the perception target to be matched and the networked target to be matched are pre-processed data with corresponding time.
[0034] Specifically, the initial perception target to be matched transmitted by the road test unit and the initial networked target transmitted by other vehicle OBU are obtained, and the perception target and the networked target are preprocessed respectively to obtain clear, accurate and time-corresponding perception target to be matched and networked target to be matched.
[0035] S102: Perform data matching on the to-be-matched perception target and the to-be-matched networked target to obtain a matching result.
[0036] In this embodiment, the matching result can be understood as the final matching information obtained after multiple matching and comparison of the perception target to be matched and the networked target to be matched, including matching success and matching failure.
[0037] It is understandable that the perception target to be matched and the network target to be matched can carry a matching tag to indicate whether it has entered the matching logic. If not, the tag also records its historical matching results. Among them, the historical matching results can be understood as the matching results for the corresponding perception target to be matched and the network target to be matched in the historical moment target deduplication.
[0038] Specifically, pre-identify the matching tags of the to-be-matched perception target and the to-be-matched networked target to confirm whether they are both matched for the first time. If not, determine whether the to-be-matched perception target and the to-be-matched networked target are successfully matched in the previous round of matching. If successful, determine whether the distance difference between the position coordinate data corresponding to the to-be-matched perception target and the to-be-matched networked target is less than the set distance threshold. If so, determine that the matching result of the to-be-matched perception target and the to-be-matched networked target is a successful match; if the to-be-matched perception target and the to-be-matched networked target do not satisfy any of the above judgment logics, enter the difference matching logic in the point matching logic for the to-be-matched perception target and the to-be-matched networked target to obtain the corresponding matching result.
[0039] It can be understood that the matching logic of the perception target to be matched and the networked target to be matched, in addition to point matching, also includes trajectory matching. If the matching result corresponding to the point matching satisfies the set threshold of the set multiple, the trajectory matching logic is entered to obtain the final matching result. The final matching result only includes matching success and matching failure.
[0040] S103: If the matching result indicates that the to-be-matched perceived target and the to-be-matched networked target are matched successfully, deduplication processing is performed on the to-be-matched perceived target and the to-be-matched networked target.
[0041] In this embodiment, if the matching result indicates that the to-be-matched sensed target and the to-be-matched networked target are matched successfully, it means that the to-be-matched sensed target and the to-be-matched networked target are the same data, and the two are deduplicated, and only one of the to-be-matched sensed target and the to-be-matched networked target is retained to complete the target deduplication. Subsequent functional applications, such as collision warning, are executed based on the retained data.
[0042] The embodiment of the present invention provides a method for deduplicating a target, including obtaining a to-be-matched sensing target and a to-be-matched networked target; performing data matching on the to-be-matched sensing target and the to-be-matched networked target to obtain a matching result; if the matching result indicates that the to-be-matched sensing target and the to-be-matched networked target are successfully matched, deduplicating the to-be-matched sensing target and the to-be-matched networked target. The above technical solution realizes deduplication of multi-source data targets, solves the problem of data redundancy and memory resource waste in OBU devices, and further avoids calculation errors and false alarms caused by repeated calculations based on the same data target.
[0043] Embodiment 2
[0044] Figure 2 It is a flow chart of a target deduplication method provided in Embodiment 2 of the present invention. This embodiment is a further optimization of any of the above embodiments and can be applied to the situation where deduplication is performed on perceived targets and networked targets at the same time or at similar times. The method can be executed by a target deduplication device, which can be implemented in the form of hardware and / or software.
[0045] like Figure 2 As shown, the method includes:
[0046] S201. Acquire a perceived target and a timestamp of the perceived target, pre-process the perceived target, and obtain a perceived target to be matched.
[0047] In this embodiment, the sensing target can be understood as the original data directly transmitted by the drive test unit to the OBU, and the timestamp is information recording the acquisition time of the sensing target.
[0048] When acquiring the perceived target transmitted by the road test unit, the timestamp data of the perceived target is also acquired. For the perceived target, the perceived target is filtered based on a preset filtering algorithm to reduce the impact of individual frame data mutations on subsequent calculation processes, and obtain the perceived target after filtering optimization and correction. Among them, the preset filtering algorithm can be, for example, a Kalman filtering algorithm or other algorithms, and this embodiment does not limit this.
[0049] It can be understood that the acquisition of the perception target is a continuous acquisition, and then the perception target to be matched is obtained continuously.
[0050] S202: Acquire a historical networked target set, determine a historical networked target corresponding to a timestamp from the historical networked target set, pre-process the historical networked target, and obtain a networked target to be matched.
[0051] In this embodiment, the historical connected target set can be understood as a collection of connected targets at historical moments, and the connected targets can be understood as data transmitted from other vehicle OBUs to the vehicle OBU through the V2X network.
[0052] Specifically, during the historical time, the networked targets transmitted by other vehicles in the V2X network are continuously obtained, and a historical networked target set is formed by multiple networked targets obtained during the historical time period. It can be understood that each networked target has its corresponding timestamp. After obtaining the perceived target and its timestamp, search in the historical networked target set whether there is a networked target with the same timestamp as the perceived target. If so, perform the same filtering process on the networked target as the perceived target to obtain the networked target to be matched; if not, search the historical networked target set for the networked target corresponding to the timestamp closest to the timestamp of the perceived target, that is, determine the networked target whose acquisition time is closest to the acquisition time of the perceived target from the historical networked target set, perform the same filtering process on the networked target as the perceived target, and obtain the networked target to be matched.
[0053] It can be understood that the acquisition of the historical networked target set is also a continuous acquisition, and on the basis of continuously acquiring the perceived target, the networked target that matches the perceived target time is continuously determined from the historical networked target set, and then the networked target to be matched is continuously obtained.
[0054] S203: Determine driving difference data between driving data corresponding to the perception target to be matched and driving data corresponding to the networked target to be matched, perform point matching based on the driving difference data, and obtain a first matching result.
[0055] In this embodiment, the driving data includes position coordinates, speed, acceleration, heading angle and yaw rate. The driving difference data can be understood as the distance difference, speed difference and heading angle difference calculated from the driving data of the perception target to be matched and the connected target to be matched, wherein the distance difference is calculated from the position coordinates, the speed difference is calculated from the speed and acceleration, and the heading angle difference is calculated from the heading angle and yaw rate. The first matching result can be understood as the matching result of the point matching, including successful matching, failed matching and the matching result meeting the distance threshold condition.
[0056] It is understandable that the sensing target to be matched and the networked target to be matched can carry a matching tag to indicate whether it has entered the matching logic, that is, whether it is the first match. If it is not the first match, the tag also records its historical matching results. The historical matching results include matching success and matching failure.
[0057] Specifically, first parse the matching tags of the perception target to be matched and the networked target to be matched to determine whether both are matched for the first time. If the perception target to be matched is not matched for the first time, determine the historical matching results of the perception target to be matched in the previous round of matching. If the historical matching result is a matching failure, enter the current matching logic; if the historical matching result is a matching success, then in this round of matching, determine whether the distance difference between the position coordinates corresponding to the perception target to be matched and the position coordinates corresponding to the networked target to be matched is less than the preset difference threshold. If so, determine that the first matching result of this round of matching is a matching success; if not, determine whether the distance difference meets the distance threshold condition. If so, determine that the first matching result of this round of matching meets the distance threshold condition. Otherwise, determine that the first matching result of this round of matching is a matching failure. If the networked target to be matched is not matched for the first time, the same applies.
[0058] If the perception target to be matched and the networked target to be matched are both matched for the first time, the distance difference is obtained based on the position coordinates corresponding to the perception target to be matched and the position coordinates corresponding to the networked target to be matched; the speed difference is obtained based on the speed and acceleration corresponding to the perception target to be matched, and the speed and acceleration corresponding to the networked target to be matched; the heading angle difference is obtained based on the heading angle and yaw angular velocity corresponding to the perception target to be matched, and the heading angle and yaw angular velocity corresponding to the networked target to be matched. It is determined whether the distance difference, speed difference, and heading angle difference are all less than their corresponding thresholds. If so, the first matching result is determined to be a successful match. Otherwise, it is determined whether the distance difference meets the distance threshold condition. If so, it is determined that the first matching result of this round of matching meets the distance threshold condition. If not, it is determined that the first matching result of this round of matching meets the distance threshold condition.
[0059] Optionally, determining driving difference data between driving data corresponding to the to-be-matched perception target and driving data corresponding to the to-be-matched networked target, and performing point matching based on the driving difference data to obtain a first matching result includes:
[0060] S2031. Based on the timestamp of the perceived target to be matched, align the networked target to be matched to obtain a corrected networked target.
[0061] In this embodiment, the modified networked target can be understood as the networked target data after the timestamp is aligned with the perceived target to be matched.
[0062] Specifically, if subsequent difference calculation is performed, since the timestamps of the perceived target and the networked target may be inconsistent, it is necessary to make a prediction correction to the target data based on the difference between the timestamps of the two. The timestamp alignment is performed based on the timestamp of the perceived target, and the position coordinate correction value, speed correction value, and heading angle correction value of the networked target after the timestamp alignment are calculated to obtain the corrected networked target.
[0063] S2032. Determine the driving difference data between the driving data corresponding to the perception target to be matched and the driving data corresponding to the corrected networked target, and obtain the distance difference, speed difference and heading angle difference.
[0064] In this embodiment, the form difference data includes distance difference, speed difference and heading angle difference.
[0065] pass The distance difference dis_diff is calculated, where x represents the horizontal axis coordinate offset of the to-be-matched perceived target relative to the to-be-matched networked target before timestamp alignment (that is, the difference between the x coordinate in the position coordinates of the to-be-matched perceived target and the x coordinate in the position coordinates of the to-be-matched networked target); y represents the vertical axis coordinate offset of the to-be-matched perceived target relative to the to-be-matched networked target before timestamp alignment (that is, the difference between the y coordinate in the position coordinates of the to-be-matched perceived target and the y coordinate in the position coordinates of the to-be-matched networked target); Δx represents the horizontal axis displacement correction of the to-be-matched perceived target relative to the corrected networked target after timestamp alignment (that is, the difference between the x coordinate in the position coordinates of the to-be-matched perceived target and the x coordinate in the position coordinates of the corrected networked target); Δy represents the vertical axis displacement correction of the to-be-matched perceived target relative to the corrected networked target after timestamp alignment (that is, the difference between the y coordinate in the position coordinates of the to-be-matched perceived target and the y coordinate in the position coordinates of the corrected networked target).
[0066] The speed difference speed_diff is calculated by speed_diff=|s_veh_speed-(v2x_veh_speed+v2x_veh_acc*Δt)|, where s_veh_speed represents the speed of the perceived target to be matched; v2x_veh_speed represents the speed of the networked target to be matched before timestamp alignment; v2x_veh_acc represents the acceleration of the networked target to be matched before timestamp alignment; Δt represents the timestamp difference between the perceived target to be matched and the networked target to be matched; (v2x_veh_speed+v2x_veh_acc*Δt) represents the speed of the corrected networked target.
[0067] The heading angle difference heading_diff is calculated by heading_diff=|s_veh_heading-(v2x_veh_heading+v2x_veh_yaw*Δt)|, where s_veh_heading represents the heading angle of the perception target to be matched; v2x_veh_heading represents the heading angle of the networked target to be matched before timestamp alignment; v2x_veh_yaw represents the yaw angular velocity of the networked target to be matched before timestamp alignment; Δt represents the timestamp difference between the perception target to be matched and the networked target to be matched; (v2x_veh_heading+v2x_veh_yaw*Δt) represents the heading angle of the corrected networked target.
[0068] S2033, determining whether the distance difference, the speed difference, and the heading angle difference are all less than corresponding thresholds; if so, determining that the first matching result is a successful match.
[0069] In this embodiment, the first matching result can be understood as a matching result of a point match, including a successful match, a failed match, and a distance threshold condition being met.
[0070] Determine whether the distance difference is less than a preset distance threshold, whether the speed difference is less than a set speed threshold, and whether the heading angle difference is less than a set heading angle threshold. If the distance difference, speed difference, and heading angle difference are all less than the corresponding thresholds, determine that the first matching result is a successful match.
[0071] S2034: If not, determine whether the distance difference satisfies the distance threshold condition; if so, determine that the first matching result satisfies the distance threshold condition; otherwise, determine that the first matching result is a matching failure.
[0072] In this embodiment, the distance threshold condition can be understood as a condition related to the distance threshold and used to determine the matching result, for example, it can be a set multiple of the distance threshold.
[0073] Specifically, determine whether the distance difference between the perceived target to be matched and the corrected networked target meets the distance threshold, for example, whether the distance difference is less than twice the distance threshold. If so, determine that the first matching result meets the distance threshold condition; if not (for example, the distance difference is greater than twice the distance threshold), determine that the first matching result is a matching failure.
[0074] S204. If the first matching result meets the distance threshold condition, trajectory matching is performed according to the trajectory points corresponding to the perceived target to be matched and the trajectory points corresponding to the networked target to be matched to obtain a second matching result.
[0075] In this embodiment, the second matching result can be understood as the result of trajectory matching of the to-be-matched perception target and the to-be-matched networked target (which can also be considered as the corrected networked target after correction), including successful matching and failed matching.
[0076] Specifically, if the first matching result meets the distance threshold condition, the trajectory matching logic of the perception target and the networked target is entered. First, it is determined whether the number of trajectory points in the data set of the perception target to be matched, the number of trajectory points in the data set of the networked target to be matched, and the time difference between the timestamps corresponding to two adjacent trajectory points in the data set are sufficient. If so, the similarity between the trajectory points in the two data sets is further determined. If the similarity meets a specific similarity threshold, the second matching result is determined to be a successful match; if any of the above conditions is not met, the second matching result is considered to be a failed match.
[0077] Optionally, performing trajectory matching according to the trajectory point corresponding to the to-be-matched perception target and the trajectory point corresponding to the to-be-matched networked target to obtain a second matching result includes:
[0078] S2041. Determine a set of perception points corresponding to the trajectory points of the to-be-matched perception target and a set of networked points corresponding to the trajectory points of the to-be-matched networked target.
[0079] In this embodiment, the perception point set SENSE_LIST can be understood as a set of trajectory points corresponding to the perception target to be matched, and the network point set V2X_LIST can be understood as a set of trajectory points corresponding to the networked target to be matched.
[0080] Specifically, a perception target may correspond to multiple trajectory points that the vehicle has passed through, and each trajectory point also has its corresponding timestamp, and the same is true for the networked target. Therefore, for the perception target to be matched, the trajectory points corresponding to the perception target to be matched are constructed in the order of the timestamps of the trajectory points to construct a perception data set, that is, a perception point set; for the perception target to be matched, the trajectory points corresponding to the networked target to be matched are constructed in the order of the timestamps to construct a networked data set, that is, a networked point set.
[0081] It can be understood that the trajectory points in the perception point set satisfy a certain timestamp difference (for example, 1s). Specifically, when constructing the perception point set, the trajectory points are screened according to their timestamps, and several trajectory points that satisfy the time stamp difference between each two of them being greater than or equal to 1s and whose timestamps are closest are selected to form the characteristic trajectory data point set SENSE_LIST of the perception target.
[0082] It is understandable that the number of trajectory points contained in the perception point set and the network point set is at most 50.
[0083] S2042: Determine whether the set of perception points meets the trajectory point quantity threshold; if not, determine that the second matching result is a matching failure.
[0084] In this embodiment, the trajectory point quantity threshold may be understood as a preset minimum value of the trajectory point quantity in the data set, for example, may be 2.
[0085] Specifically, it is determined whether the number of trajectory points in the perception point set is greater than a trajectory point number threshold, and if not, it is determined that the second matching result is a matching failure.
[0086] S2043: If satisfied, determine whether the network point set satisfies the trajectory point quantity threshold and the timestamp difference threshold; if any one of them is not satisfied, determine that the second matching result is a matching failure.
[0087] In this embodiment, the timestamp difference threshold may be understood as the time difference between two adjacent timestamps, for example, may be 0.8 s.
[0088] Specifically, if the number of trajectory points in the perception point set is greater than the trajectory point number threshold, then it is determined whether the number of trajectory points in the networked point set is also greater than the trajectory point number threshold, and at the same time, it is determined whether the difference between the timestamps of two adjacent trajectory points in the networked point set is greater than the set timestamp difference; if the number of trajectory points in the networked point set is less than the trajectory point number threshold or the difference between the timestamps of two adjacent trajectory points in the networked point set is less than the set timestamp difference, then the second matching result is determined to be a matching failure.
[0089] S2044. If both conditions are satisfied, determine the trajectory point similarity of the perception point set and the network point set, and determine whether the trajectory point similarity satisfies the similarity condition. If not, determine that the second matching result is a matching failure. If satisfied, determine that the second matching result is a matching success.
[0090] In this embodiment, the trajectory point similarity can be understood as the overlap between the line formed by the trajectory points included in the perception point set and the line formed by the trajectory points included in the network point set. The similarity condition can be understood as the trajectory point similarity being greater than a set similarity threshold, for example, 0.8. n , where n represents the number of line segments formed by trajectory points.
[0091] Specifically, if the number of trajectory points in the network point set is greater than the threshold value of the number of trajectory points, and the difference between the timestamps of two adjacent trajectory points in the network point set is greater than the set timestamp difference, the trajectory points in the perception point set and the network point set are connected in series into several line segments, and the direction and length of each line segment are calculated. If the length of a single line segment is less than the set length (for example, 0.01m), it is set to the set length. Calculate the length coefficient L of the i-th line segment i , where v2x_line_length i Indicates the length of the i-th line segment in the network connection point set V2X_LIST; sensed_line_length i Indicates the length of the i-th line segment in the sensing point set SENSE_LIST; v2x_line_interval i Represents the time span of the head and tail positioning points of the i-th line segment in the network connection point set V2X_LIST; sensed_line_interval i Indicates the time span of the head and tail positioning points of the i-th line segment in the sensing point set SENSE_LIST. i If L is greater than 1, then take the inverse. Secondly, if the perception target to be matched in this round of matching is the perception target to be matched that was successfully matched by the networked target to be matched in the previous round of matching, then L i The minimum value of is assigned to 0.9. Then, according to Calculate the angle coefficient Ang of the i-th line segment i , where v2x_line_angle i Represents the angle of the i-th line segment in the network point set V2X_LIST; sensed_line_angle i represents the angle of the i-th line segment in the sensing point set SENSE_LIST. Finally, according to Calculate the trajectory similarity S between the perceived target to be matched and the networked target to be matched, and add the trajectory similarity S to 0.8 n For comparison, if S is greater than 0.8 n , it is determined that the similarity condition is met, and the second matching result is a successful match; otherwise, it is determined that the similarity condition is not met, and the second matching result is a failed match.
[0092] S205. If the matching result indicates that the to-be-matched perceived target and the to-be-matched networked target are matched successfully, deduplication processing is performed on the to-be-matched perceived target and the to-be-matched networked target.
[0093] A target deduplication method provided by an embodiment of the present invention includes obtaining a perceived target and a timestamp of the perceived target, preprocessing the perceived target to obtain a perceived target to be matched; obtaining a historical networked target set, determining a historical networked target corresponding to the timestamp from the historical networked target set, preprocessing the historical networked target to obtain a networked target to be matched; determining driving difference data between driving data corresponding to the perceived target to be matched and driving data corresponding to the networked target to be matched, performing point matching based on the driving difference data, and obtaining a first matching result; if the first matching result meets a distance threshold condition, performing trajectory matching based on trajectory points corresponding to the perceived target to be matched and trajectory points corresponding to the networked target to be matched, and obtaining a second matching result; if the matching result indicates that the perceived target to be matched and the networked target to be matched are successfully matched, deduplication processing is performed on the perceived target to be matched and the networked target to be matched. The above technical solution can make full use of the position coordinates, speed, heading angle, yaw angular velocity and other data of the received target data, and adopt a specific algorithm to optimize the above data to deal with possible data mutation problems; a matching algorithm combining point matching and trajectory matching is used to fuse and de-duplicate multiple targets, and tracking and predicting of position coordinates, speed, heading angle and other data are achieved on the basis of timestamp synchronization during point matching, and the trajectories of multi-source data are matched by calculating trajectory similarity during trajectory matching; the matching algorithm mainly uses point matching based on single-frame data, and performs trajectory matching when necessary, effectively reducing the time complexity of the algorithm; the algorithm program has low requirements on computing power, can run stably in OBU equipment, and ensures high fusion and de-duplication accuracy.
[0094] Figure 3is another flow chart of a target deduplication method provided by the second embodiment of the present invention. Figure 3 As shown, the target deduplication method includes:
[0095] Obtain the latest perception data list and the corresponding network data list, optimize and correct them through Kalman filtering, traverse the targets, and obtain the optimized perception targets to be matched and the network targets to be matched;
[0096] Determine whether the perceived target to be matched and the networked target to be matched enter the algorithm logic for the first time, that is, whether it is the first match; if it is not the first match, determine whether the perceived target and the networked target are successfully matched in the previous round of matching. If not, calculate the distance difference, speed difference and heading angle difference between the perceived target and the networked target, and enter the next point matching logic; if successful, determine whether the distance difference between the perceived target and the networked target is less than the distance threshold. If less than, determine that the match is successful. If greater than or equal to, determine whether the distance difference between the perceived target and the networked target is less than 2 times the distance threshold. If so, enter the trajectory matching logic;
[0097] If it is the first match, the distance difference, speed difference and heading angle difference between the sensed target and the networked target are calculated, and it is determined whether the distance difference, speed difference and heading angle difference are all less than the corresponding thresholds; if so, it is determined that the match is successful; if not, it is determined whether the distance difference is less than 2 times the distance threshold; if not, it is determined that the match fails; if so, it enters the trajectory matching logic;
[0098] When the distance difference is less than 2 times of the distance threshold, the trajectory matching logic is entered, and in the trajectory matching logic, the trajectory point corresponding to the sensed target and the trajectory point corresponding to the networked target are determined;
[0099] Filter the trajectory points corresponding to the perception target to obtain a perception point set, and determine whether the number of trajectory points in the perception point set is greater than 2. If less than 2, it is determined that the matching fails.
[0100] If it is greater than, filter the trajectory points corresponding to the networked target to obtain a networked point set, and determine whether the number of trajectory points in the networked point set is greater than 2, and whether the time stamp difference between two adjacent trajectory points is greater than 0.8s; if they are both less than, determine that the match fails;
[0101] If both are greater than, calculate the trajectory similarity S of the perceived target and the networked target, and determine whether the trajectory similarity is greater than 0.8 n , if yes, determine that the match is successful, if no, determine that the match fails;
[0102] If the match is successful, it is determined that the perceived target and the networked target are the same data, and the perceived target and the networked target are deduplicated, retaining only one data.
[0103] Embodiment 3
[0104] Figure 4 Schematic diagram of the structure of a target deduplication device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device comprises:
[0105] A data acquisition module 31 is used to acquire a sensing target to be matched and a networked target to be matched;
[0106] A data matching module 32 is used to perform data matching between the to-be-matched sensing target and the to-be-matched networked target to obtain a matching result;
[0107] The target deduplication module 33 is used to deduplicate the to-be-matched perceived target and the to-be-matched networked target if the matching result indicates that the to-be-matched perceived target and the to-be-matched networked target are successfully matched.
[0108] The target deduplication device adopted in this technical solution can achieve the deduplication of multi-source data targets, solve the problems of data redundancy and memory resource waste in OBU devices, and further avoid calculation errors and false warnings caused by repeated calculations based on the same data targets.
[0109] Optionally, the data acquisition module 31 is specifically used for:
[0110] Acquire a perceived target and a timestamp of the perceived target, preprocess the perceived target, and obtain a perceived target to be matched;
[0111] A historical networked target set is obtained, a historical networked target corresponding to the timestamp is determined from the historical networked target set, and the historical networked target is preprocessed to obtain a networked target to be matched.
[0112] Optionally, the data matching module 32 includes:
[0113] a point matching unit, configured to determine driving difference data between driving data corresponding to the to-be-matched perception target and driving data corresponding to the to-be-matched networked target, and perform point matching based on the driving difference data to obtain a first matching result;
[0114] A trajectory matching unit is used to perform trajectory matching according to the trajectory points corresponding to the perception target to be matched and the trajectory points corresponding to the networked target to be matched, if the first matching result meets the distance threshold condition, to obtain a second matching result.
[0115] Optionally, the driving difference data includes a distance difference, a speed difference and a heading angle difference;
[0116] The first matching result includes a matching success, a matching failure, and a matching result that satisfies a distance threshold condition;
[0117] The second matching result includes a matching success and a matching failure.
[0118] Optional, point matching unit, specifically used for:
[0119] Based on the timestamp of the to-be-matched perception target, align the to-be-matched networked target to obtain a modified networked target;
[0120] Determine driving difference data between the driving data corresponding to the to-be-matched perception target and the driving data corresponding to the corrected networked target, and obtain a distance difference, a speed difference, and a heading angle difference;
[0121] Determine whether the distance difference, speed difference, and heading angle difference are all less than corresponding thresholds, and if so, determine that the first matching result is a successful match;
[0122] If not, determine whether the distance difference satisfies a distance threshold condition; if so, determine that the first matching result satisfies the distance threshold condition; otherwise, determine that the first matching result is a matching failure.
[0123] Optionally, a trajectory matching unit is used to:
[0124] Determine a set of perception points corresponding to the trajectory points of the to-be-matched perception target and a set of networked points corresponding to the trajectory points of the to-be-matched networked target;
[0125] Determining whether the set of perception points meets a trajectory point quantity threshold, and if not, determining the second matching result as a matching failure;
[0126] If satisfied, determining whether the network point set satisfies a trajectory point quantity threshold and a timestamp difference threshold, and if any one of them is not satisfied, determining the second matching result as a matching failure;
[0127] If both conditions are satisfied, determine the trajectory point similarity between the perception point set and the network point set, and determine whether the trajectory point similarity satisfies the similarity condition. If not, determine that the second matching result is a matching failure. If satisfied, determine that the second matching result is a matching success.
[0128] The target deduplication device provided in the embodiment of the present invention can execute the target deduplication method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0129] Embodiment 4
[0130] Figure 5It is a structural schematic diagram of an electronic device provided by Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein. In the present embodiment, the electronic device is preferably represented as an onboard unit OBU.
[0131] like Figure 5 As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.
[0132] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0133] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 performs the various methods and processes described above, such as the target deduplication method.
[0134] In some embodiments, the target deduplication method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the target deduplication method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the target deduplication method in any other suitable manner (e.g., by means of firmware).
[0135] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0136] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0137] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0138] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0139] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0140] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0141] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0142] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A target deduplication method, characterized in that: include: Obtaining the perception target to be matched and the network connection target to be matched; Performing data matching on the to-be-matched sensing target and the to-be-matched networked target to obtain a matching result; If the matching result indicates that the to-be-matched perceived target and the to-be-matched networked target are matched successfully, deduplication processing is performed on the to-be-matched perceived target and the to-be-matched networked target.
2. The method according to claim 1, characterized in that The obtaining of the to-be-matched sensing target and the to-be-matched networked target includes: Acquire a perceived target and a timestamp of the perceived target, preprocess the perceived target, and obtain a perceived target to be matched; A historical networked target set is obtained, a historical networked target corresponding to the timestamp is determined from the historical networked target set, and the historical networked target is preprocessed to obtain a networked target to be matched.
3. The method according to claim 1, characterized in that The step of performing data matching on the to-be-matched sensing target and the to-be-matched networked target to obtain a matching result includes: Determine driving difference data between driving data corresponding to the to-be-matched perception target and driving data corresponding to the to-be-matched networked target, and perform point matching based on the driving difference data to obtain a first matching result; If the first matching result meets the distance threshold condition, trajectory matching is performed according to the trajectory points corresponding to the perceived target to be matched and the trajectory points corresponding to the networked target to be matched to obtain a second matching result.
4. The method according to claim 3, characterized in that The driving difference data includes distance difference, speed difference and heading angle difference; The first matching result includes a matching success, a matching failure, and a matching result that satisfies a distance threshold condition; The second matching result includes a matching success and a matching failure.
5. The method according to claim 3, characterized in that: The determining of driving difference data between the driving data corresponding to the to-be-matched perception target and the driving data corresponding to the to-be-matched networked target, and performing point matching based on the driving difference data to obtain a first matching result includes: Based on the timestamp of the to-be-matched perception target, align the to-be-matched networked target to obtain a modified networked target; Determine driving difference data between the driving data corresponding to the to-be-matched perception target and the driving data corresponding to the corrected networked target, and obtain a distance difference, a speed difference, and a heading angle difference; Determine whether the distance difference, speed difference, and heading angle difference are all less than corresponding thresholds, and if so, determine that the first matching result is a successful match; If not, determine whether the distance difference satisfies a distance threshold condition; if so, determine that the first matching result satisfies the distance threshold condition; otherwise, determine that the first matching result is a matching failure.
6. The method according to claim 3, characterized in that: Performing trajectory matching according to the trajectory point corresponding to the to-be-matched perception target and the trajectory point corresponding to the to-be-matched networked target to obtain a second matching result, including: Determine a set of perception points corresponding to the trajectory points of the to-be-matched perception target and a set of networked points corresponding to the trajectory points of the to-be-matched networked target; Determining whether the set of perception points meets a trajectory point quantity threshold, and if not, determining the second matching result as a matching failure; If satisfied, determining whether the network point set satisfies a trajectory point quantity threshold and a timestamp difference threshold, and if any one of them is not satisfied, determining the second matching result as a matching failure; If both conditions are satisfied, determine the trajectory point similarity between the perception point set and the network point set, and determine whether the trajectory point similarity satisfies the similarity condition. If not, determine that the second matching result is a matching failure. If satisfied, determine that the second matching result is a matching success.
7. A target deduplication device, characterized in that: include: A data acquisition module is used to acquire the perception target to be matched and the network connection target to be matched; A data matching module is used to perform data matching between the to-be-matched sensing target and the to-be-matched networked target to obtain a matching result; The target deduplication module is used to deduplicate the perceived target to be matched and the networked target to be matched if the matching result indicates that the perceived target to be matched and the networked target to be matched are successfully matched.
8. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a target deduplication method as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a target deduplication method according to any one of claims 1 to 6 when executed.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements a target deduplication method according to any one of claims 1-6.