Vehicle positioning method, electronic equipment and storage medium

Abstract

The invention provides a vehicle positioning method. The method comprises the steps that the vehicle speed of a target vehicle in a target area is acquired; based on the vehicle speed and a trajectory prediction model, determining trajectory point positions corresponding to different moments when the target vehicle travels in the target area; wherein the trajectory prediction model is used for predicting trajectory points of the target vehicle in the driving process; and generating a driving track of the target vehicle based on the track point positions corresponding to the different moments. According to the invention, the position of the track point of the target vehicle can be obtained based on the combination of two modes, so that the track point can be obtained more accurately, and the identification and positioning of the target vehicle in the target area are more accurate.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent driving technology, and in particular to a vehicle positioning method, electronic equipment and storage medium. Background Art

[0002] In the prior art, multiple cameras can be deployed at designated locations in the parking area. Based on the multiple cameras, multiple image information of the vehicle at different locations can be obtained, and then the vehicle can be positioned based on the multiple image information. However, the camera is particularly sensitive to ambient lighting and is easily affected by external lighting. It also has low accuracy and large recognition errors.

[0003] In order to improve recognition accuracy, the existing technology also deploys cameras and sensor equipment at designated locations at the same time, and fuses the images generated by the cameras and the point cloud data generated by the sensor equipment to achieve vehicle positioning. However, this method has a high deployment cost in reality and the subsequent calculations are relatively complicated. Summary of the invention

[0004] In view of this, an embodiment of the present disclosure provides a vehicle positioning method to solve the problem in the related art that the vehicle cannot be identified and positioned.

[0005] According to a first aspect of an embodiment of the present disclosure, a vehicle positioning method is provided, the method comprising: obtaining a vehicle speed of a target vehicle in a target area; determining, based on the vehicle speed and a trajectory prediction model, positions of trajectory points corresponding to different times when the target vehicle is traveling in the target area; wherein the trajectory prediction model is used to predict trajectory points of the target vehicle during driving; and generating a driving trajectory of the target vehicle based on the positions of trajectory points corresponding to different times.

[0006] According to a second aspect of an embodiment of the present disclosure, a vehicle positioning device is provided, which includes: an acquisition module for acquiring a vehicle speed of a target vehicle in a target area; a determination module for determining, based on the vehicle speed and a trajectory prediction model, positions of trajectory points corresponding to different times when the target vehicle is traveling in the target area; wherein the trajectory prediction model is used to predict the trajectory points of the target vehicle during driving; and a generation module for generating a driving trajectory of the target vehicle based on the trajectory point positions corresponding to different times.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising at least one processor; and a memory for storing instructions executable by at least one processor; wherein the at least one processor is used to execute instructions to implement the steps of the control method of the above-mentioned vehicle positioning device.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the steps of the control method of the above-mentioned vehicle positioning device.

[0009] At least one of the above-mentioned technical solutions adopted in the embodiments of the present disclosure can achieve the following beneficial effects: the present disclosure can obtain the trajectory point positions of the target vehicle in the target area at different times according to the trajectory prediction model, and then generate the corresponding driving trajectory of the target vehicle in the target area according to the multiple trajectory point positions, and at the same time can also determine the corresponding trajectory point positions at different times based on the vehicle speed of the target vehicle in the target area at different times, and generate the corresponding driving trajectory of the target vehicle in the target area according to the multiple trajectory point positions. The trajectory point positions of the target vehicle can be obtained more accurately based on the combination of the two methods, thereby making the identification and positioning of the target vehicle in the target area more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0011] Figure 1 A schematic diagram showing an example system in which various methods described herein may be implemented according to an embodiment of the present disclosure;

[0012] Figure 2 A flow chart of a vehicle positioning method provided by an exemplary embodiment of the present disclosure;

[0013] Figure 3 A schematic diagram of a process for confirming the position of a track point provided by an exemplary embodiment of the present disclosure;

[0014] Figure 4 A schematic structural diagram of a vehicle positioning device provided by an exemplary embodiment of the present disclosure;

[0015] Figure 5 A schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present disclosure;

[0016] Figure 6 A schematic diagram of the structure of a computer system provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0019] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] In the prior art, most of the vehicle positioning technologies for parking areas use short-distance communication technologies for data transmission, such as Bluetooth, wireless networks, carrier-free communication technologies, etc. At the same time, the positioning of vehicles in parking areas also requires the use of terminals, through which vehicle videos are obtained, and then the positioning and navigation of vehicles in the parking area are realized through the vehicle video, and the recognition ability of the video and the target conversion between the image coordinates and the actual coordinates are used to realize the recognition and positioning of the vehicle in the parking area.

[0023] The existing parking area vehicle positioning technology completely relies on the camera installed at the end of the field. The vehicle position in the parking area is obtained by the camera's image recognition capability and coordinate conversion geometric operation. However, due to the limitation of the number of cameras, the accuracy error of the camera positioning method will be relatively large, and the camera is particularly sensitive to ambient lighting. Changes in lighting angle and light intensity will also have a great impact on recognition. At the same time, this method cannot accurately identify the identity of the vehicle in the parking area, and thus cannot be directly used for auxiliary positioning of the vehicle itself.

[0024] In practical applications, dynamic positioning can also be achieved based on the laser vision fusion method. This method uses a three-dimensional target detection module that integrates cameras and sensor devices to obtain vehicle location information and pedestrian location information based on RGB images and point cloud data. This method introduces sensor devices, which are highly accurate and have strong anti-interference capabilities; however, this method requires the deployment of sensor devices and cameras across the entire domain, which is relatively redundant, and the fusion of multiple targets depends on the joint calibration of cameras and sensor devices, which is more difficult and complicated. At the same time, this solution does not solve the problem of identity confirmation of recognition results, but only outputs a global semantic map, which cannot be directly provided to users as an auxiliary positioning for the user's vehicle itself.

[0025] In response to the above problems, the present disclosure provides a vehicle positioning system, which can set a camera at the entrance of the parking area, and use multiple sensor devices for deployment inside the parking area. At the same time, it combines the existing gate system and parking space system in the parking area, and predicts and deduce the vehicle trajectory based on the data of the gate system and the data of the parking space system respectively, and matches and fuses with the image acquisition equipment deployed in the field and the fully covered sensor equipment, so as to help the camera and the sensor equipment confirm the identity information of the vehicle in the parking lot. The present disclosure can process the data from the sensor equipment through an algorithm and fuse it with the data results of the perception system in the present disclosure, make full use of the existing platform capabilities of the parking area, and improve the identity recognition capability of auxiliary positioning through the existing platform, provide auxiliary positioning capabilities to vehicles in the field more efficiently and accurately, and reduce the cost investment of the overall system construction.

[0026] The positioning method of the exemplary embodiment of the present disclosure can be applied to various positioning scenarios. Figure 1 Schematic diagram of an example system in which various methods described herein may be implemented according to an embodiment of the present disclosure. Figure 1 As shown, the schematic diagram 100 of the positioning method of the exemplary embodiment of the present disclosure includes a gate 101, an image acquisition device 120 and a plurality of sensor devices 130. The image acquisition device 120 may be a device with an image acquisition function such as a SLR camera, a sports camera, a panoramic camera, etc., and the sensor device 130 may be a laser radar.

[0027] In practical applications, the barrier 101 generally refers to the currently common parking lot smart barrier system, which may include an image recognition unit and a gate unit, wherein the image recognition unit may include a feature extraction model for extracting feature information of the vehicle. For example, the first feature information of the vehicle, such as the vehicle license plate information, vehicle model information, vehicle body color information, and time information of the vehicle passing through the barrier 101, may be obtained through the image recognition unit. Based on this, when the image recognition unit completes the feature extraction task, it will upload a message that the feature extraction task is completed to the parking lot smart barrier system, and at the same time upload the extracted features to the parking lot smart barrier system. After receiving the message that the feature extraction task is completed, the parking lot smart barrier system sends a release instruction to the gate unit, and the gate unit releases the vehicle in response to the release instruction.

[0028] like Figure 1 As shown, after a vehicle passes through the barrier 101 for a period of time, it will enter the perception area of ​​the image acquisition device 120, that is, the image acquisition area of ​​the image acquisition device 120. The image acquisition device 120 can capture images of the vehicle and send the captured image data to the parking lot smart barrier system. The parking lot smart barrier system can identify the vehicle based on the visual perception algorithm, obtain the vehicle license plate information, vehicle model information, body color information and other second feature information of the vehicle, and then locate the vehicle by comparing the first feature information of the barrier 101 and the second feature information of the image acquisition device 120. At the same time, the present disclosure also sets multiple sensing devices in multiple lanes to obtain the third feature information of the vehicle, and then locates the vehicle by comparing the second feature information and the third feature information.

[0029] The positioning method of the exemplary embodiment of the present disclosure can be executed by the parking lot smart gate system, and can also be executed by a chip applied to the parking lot smart gate system.

[0030] A vehicle positioning method according to an embodiment of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0031] Figure 2 The following is a flow chart of a vehicle positioning method provided by an exemplary embodiment of the present disclosure. Figure 2 As shown, the vehicle positioning method includes:

[0032] S201: Obtaining the vehicle speed of the target vehicle in the target area, wherein the vehicle speed may be an average speed of the target vehicle in a certain period of time, or may be an instantaneous speed of the target vehicle at a certain time point.

[0033] Specifically, the target area can be a parking area. Based on this, multiple vehicle images containing the target vehicle within a time period can be obtained through the image acquisition device in the target area, and then the multiple vehicle images can be analyzed through digital image processing technology, and a mapping relationship between the image pixel coordinates and the corresponding points in space can be established, so as to obtain the displacement of the target vehicle within a period of time, thereby determining the average speed of the target vehicle in this period of time. At the same time, the speed of the target vehicle can be directly measured through multiple sensing devices to determine the instantaneous speed of the target vehicle at a certain point in time. Based on this, different processing solutions can be flexibly designed according to different speeds, so that the driving status of the target vehicle in the target area can be analyzed more accurately.

[0034] S202: Based on the vehicle speed and the trajectory prediction model, determine the trajectory point positions corresponding to different times when the target vehicle is traveling in the target area; wherein the trajectory prediction model is used to predict the trajectory points of the target vehicle during the driving process.

[0035] In some examples, multiple vehicles collected in a time period can be analyzed according to the image acquisition device in the target area to obtain the average speed of the vehicles in the time period. Based on this, the first trajectory point positions corresponding to different times when the vehicle is traveling in the target area can be obtained according to the average speed of the vehicle and the driving time of the vehicle in the target area. At the same time, the second trajectory point positions corresponding to different times when the target vehicle is traveling in the target area can be obtained according to the trajectory prediction model. Then, by analyzing the first trajectory point positions and the second trajectory point positions obtained in the two ways, the trajectory point positions corresponding to different times when the target vehicle is traveling in the target area are determined. It can be seen that the present disclosure adopts two ways to analyze the driving trajectory of the target vehicle in the target area respectively, and combines the analysis results obtained in the two ways to finally obtain the trajectory point position of the target vehicle in the target area, avoiding the situation where the error is too large due to a single analysis, thereby improving the accuracy of obtaining the trajectory point position of the target vehicle.

[0036] S203: Generate a driving trajectory of the target vehicle based on the corresponding trajectory point positions at different times.

[0037] It can be seen that the present invention can obtain the trajectory point positions of the target vehicle in the target area at different times according to the trajectory prediction model, and then generate the corresponding driving trajectory of the target vehicle in the target area according to the multiple trajectory point positions; at the same time, the trajectory point positions corresponding to different times can be determined based on the vehicle speed of the target vehicle in the target area at different times, and the driving trajectory corresponding to the target vehicle can be generated in the target area according to the multiple trajectory point positions. The trajectory point positions of the target vehicle can be obtained more accurately based on the combination of the two methods, thereby making the positioning of the target vehicle in the target area more accurate.

[0038] Figure 3 A schematic diagram of a process for confirming the position of a track point provided by an exemplary embodiment of the present disclosure. Figure 3 As shown, determining the trajectory point positions corresponding to different times when the target vehicle is traveling in the target area includes:

[0039] S301: Acquire the vehicle speed at a first moment when a target vehicle enters a target area and at a second moment when the target vehicle passes through a first measurement area in the target area.

[0040] In some examples, the vehicle speed of the target vehicle passing through the first measurement area in the target area can be obtained based on the image acquisition device and multiple sensor devices, wherein the first measurement area can be an image acquisition area of ​​the image acquisition device.

[0041] Specifically, the vehicle speed of the target vehicle when passing through the first measurement area can be obtained based on the image acquisition device. For example, the average speed of the target vehicle when passing through the first measurement area can be determined based on the position change of the target vehicle in the multiple frames of vehicle images and the shooting time of the multiple frames of vehicle images for the target vehicle, and the average speed is used as the vehicle speed of the target vehicle. The sensing device can be a laser radar device, and the instantaneous speed of the target vehicle at a certain moment when passing through the first measurement area can be directly obtained based on the laser radar device.

[0042] S302: Acquire a first driving distance of the target vehicle based on the vehicle speed, the first moment and the second moment.

[0043] In practical applications, the target vehicle is analyzed and the time when the target vehicle passes through the gate can be confirmed as the first time when the target vehicle enters the target area, and then the first time Δt when the target vehicle passes through the gate can be obtained. 1A At the same time, the second time Δt when the target vehicle passes through the first measurement area can be obtained based on the image acquisition device. 1B and the current average speed of the target vehicle Based on this, the first driving distance of the target vehicle entering the parking area is obtained Δt1=Δt 1B -Δt 1A Based on this, we can get a path starting from the gate, and the first travel distance for the target vehicle is

[0044] S303: Determine a first position of the target vehicle at a second moment after the target vehicle enters the target area and travels a first driving distance.

[0045] In some examples, a driving trajectory data set may be constructed, wherein the driving trajectory data set includes driving trajectories of different vehicles in a target area; a third position corresponding to a first moment when a target vehicle enters the target area is obtained; a first driving trajectory is determined from the driving trajectory data set, wherein a driving distance included in the first driving trajectory is the same as the first driving distance; and a first position of the target vehicle in a first measurement area is determined based on the first driving trajectory.

[0046] Specifically, the third position of the target vehicle at the barrier can be determined based on the image recognition unit included in the barrier, wherein the third position may include position information of the target vehicle relative to the barrier. Based on this, a search can be performed in the driving trajectory data set based on the third position and the first driving distance of the target vehicle to determine that the trajectory with the third position as the starting point and the driving distance being the same as the first driving distance is the first driving trajectory of the target vehicle.

[0047] S303: Predicting a second position of the target vehicle at a second moment based on the trajectory prediction model.

[0048] In practical applications, there is a certain distance between the barrier and the image acquisition device, that is, there is a certain distance between the image recognition unit of the barrier and the image acquisition device, resulting in no overlap between the recognition area of ​​the image recognition unit and the acquisition area of ​​the image acquisition device. Therefore, directly matching the vehicle feature information at two locations will result in a large matching error. Based on this, the embodiment of the present disclosure also provides a trajectory prediction model for predicting the trajectory points of the target vehicle during driving, thereby providing a reference for matching vehicle feature information.

[0049] In some instances, an embodiment of the present disclosure first constructs a sample set based on a driving trajectory data set; and then, based on map feature information and a trajectory prediction model, obtains a second position of the target vehicle in the first measurement area at a second moment; wherein, the preset model is trained by training samples to obtain the trajectory prediction model, and the training samples are obtained based on the sample set; the map feature information is the map feature information corresponding to the first moment when the target vehicle enters the target area, and the map feature information is used to describe the position information between the target vehicle and the lane.

[0050] Specifically, the trajectory prediction model can be a trajectory prediction model without anchor targets (DenseTNT), and then the entire driving trajectory data set can be used as a training sample to train the preset model, and part of the data from the driving trajectory data set can be selected as a training sample to train the preset model. In the process of model construction, it is first necessary to use a hierarchical graph neural network (VectorNet) to extract features from the map data around the target area and the vehicle images obtained based on the image acquisition device and the gate in the target area, wherein the vehicle image includes the driving trajectory information of the vehicle, and different trajectories can be sampled at fixed time intervals, and the sampling points of the same trajectory are connected into a vector to obtain the driving trajectory information of the vehicle; the acquisition of map features can be to select a starting point and direction in the map around the parking area, where the starting point and direction can be the possible starting point and direction of the vehicle driving from the outside to the parking area, and then evenly extract key points within the same spatial distance, and sequentially connect adjacent key points into vectors, and the key points can be key points that may be passed by driving from the parking area to the parking area. Based on this, the global features of the predicted vehicle can be obtained, and the global features can include map information and driving trajectory information, and then the driving trajectory data set is constructed based on the global features.

[0051] In some embodiments, the lane area included in the image acquisition device acquisition area can also be divided into N square grids, wherein the center point of each square grid can be considered as a prediction point y, that is, when a vehicle passing through the gate unit is captured by the image acquisition area, the position of the vehicle in the image data is located at the prediction point y. Based on this, a prediction point set y = {y1, ..., y N}, and then use the dense goal encoder to generate the prediction point set y = {y1,…,y N It should be understood that the grid division can also be performed in other forms, such as triangles, rectangles, etc., and the prediction points can also be adjusted according to actual conditions.

[0052] In practical applications, we can assume that Y is a random variable of the final position, and its probability distribution satisfies P(Y = y i )=p i ,i=1,…,N. Among them, y1 is the prediction point corresponding to the first square grid, y N is the predicted point corresponding to the Nth square grid, y i is the predicted point corresponding to the i-th square grid, p i is the probability value of the i-th vehicle arriving at the i-th square grid.

[0053] Specifically, we can use the prediction point set y = {y1, ..., yN} Randomly select a set of prediction points And calculate the prediction point set The expected error And continuously iterate and optimize the above expected error to obtain a set of predicted target points close to the global optimal solution in, is the first predicted target point, For the kth predicted target point, the target set As pseudo labels, we train our target set predictor. It should be understood that pseudo labeling technology is a process of using a model trained on labeled data to make predictions on unlabeled data, screening samples based on the prediction results, and inputting them into the model for training again.

[0054] In practical applications, the predicted target output by the target set predictor can be used as the possible predicted point where the vehicle will arrive. Based on multiple predicted points, multiple predicted trajectories can be generated to establish a predicted trajectory set. in, is the first predicted trajectory, is the Tth predicted trajectory, and then calculate the predicted trajectory set The offset between the predicted trajectory and the true trajectory s in Among them, L reg is the difference between the predicted trajectory and the true trajectory, is the tth predicted trajectory. Based on this, the trajectory prediction model is trained and continuously optimized to make the trajectory endpoint output by the trajectory prediction model more accurate.

[0055] Based on this, when using the trajectory prediction model, the map data around the target area when the target vehicle enters the target area can be obtained based on the image recognition unit of the gate, and then the map data can be extracted using VectorNet to obtain map feature information, and then the map feature information is input into the trajectory prediction model to obtain the second position P of the target vehicle in the first measurement area at the second moment. A '.

[0056] S304: Determine a trajectory point position of the target vehicle at a second moment based on the first position and the second position, wherein the trajectory point position is located in the first measurement area.

[0057] In some examples, the trajectory prediction model can be used to obtain the second position P of the target vehicle after Δt1 time A '; Combined with the second position P A 'With the first position The position information of the target vehicle at the second moment Δt is determined 1B The trajectory point position P1 is calculated using the following formula:

[0058]

[0059] Among them, P cam represents the location information of the image acquisition device, α represents Corresponding weights. It should be understood that if or P A 'If it is not within the perception range of the image acquisition device, the corresponding weight is set to 0. and P A ' are not within the perception range of the image acquisition device, the position error term can be ignored in subsequent matching.

[0060] In some examples, the embodiments of the present disclosure can determine first vehicle characteristic information of a target vehicle entering a target area; at the same time, determine second vehicle characteristic information measured at a trajectory point position of the first vehicle; finally, obtain characteristic difference information based on the first vehicle characteristic information and the second vehicle characteristic information; and when the difference value is less than a preset threshold, determine that the first vehicle is a target vehicle.

[0061] Specifically, the first vehicle characteristic information of the third position corresponding to the first moment when the target vehicle enters the target area can be obtained based on the gate system, and the first vehicle characteristic information includes the vehicle license plate L1, vehicle model V1, body color C1, etc. of the target vehicle. At the same time, the second vehicle characteristic information measured by the first vehicle in the first measurement area at the second moment can also be obtained based on the image acquisition device, and the second vehicle characteristic information includes the second characteristic information such as vehicle license plate L2, vehicle model V2, body color C2, etc. At the same time, coordinate conversion is performed according to the vehicle pixel information obtained by the image acquisition device to obtain the current position P2 of the first vehicle.

[0062] In some embodiments, while obtaining the feature difference information based on the first vehicle feature information and the second vehicle feature information, the trajectory point position P1 of the target vehicle and the current position P2 of the first vehicle may be compared, and then the difference value M1 between the first vehicle and the target vehicle may be determined based on the position difference information and the feature difference information:

[0063] M1=α 11 D+α 12 L+α 13 V+α 14 C

[0064] D(P1,P2)=||P1-P2||

[0065]

[0066] V(V1,V2)=0if V1=V2else 10

[0067] C(C1,C2)=0if C1=C2else 10

[0068]

[0069] Specifically, D represents the displacement error between positions P1 and P2, where L represents the similarity between vehicle license plates L1 and L2, V represents the difference between vehicle models V1 and V2, C represents the similarity between vehicle body colors C1 and C2, S represents the number of matching characters between L1 and L2, that is, comparing the characters in the vehicle license plate one by one, len(L1)+len(L2) represents the total number of characters in L1 and L2, that is, the total number of characters contained in the vehicle license plate; score 1i Indicates the importance of the corresponding indicator feature. For example, the most important indicator among the four indicators has a score of 4, and the least important indicator has a score of 1. 11 represents the weight of D, α 12 represents the weight of L, α 13 represents the weight of V, α 14 Represents the weight of C.

[0070] Based on this, when the difference value M1 is less than the preset threshold, the first vehicle is determined to be the target vehicle, where the difference value can be 4%, 5%, and can be determined specifically according to the actual situation, confirming that the first vehicle successfully matches the target vehicle, and assigning the target vehicle's license plate information to the first vehicle. At the same time, a digital ID is assigned to the first vehicle, and the license plate is bound to the digital ID and entered into the parking lot smart gate system as the unique identity of the current first vehicle.

[0071] In some examples, the present disclosure may also obtain speed limit information and target area map data corresponding to the target area; wherein the target area map data includes all driving trajectories in the target area; based on the speed limit information and the target area map data, the departure trajectory point positions corresponding to different times when the target vehicle leaves the parking space and drives in the target area are determined in the target area map data; and the departure driving trajectory of the target vehicle is generated based on the departure trajectory point positions corresponding to different times.

[0072] In practical applications, a second measurement area (ROI) can be defined in the target area, which is an area that the vehicle will inevitably pass through when leaving the target area. Based on this, when the target vehicle leaves the target parking space, The vehicle will pass through the ROI area and be recognized by the sensor device 1 corresponding to the ROI area within the time. Determine departure distance At the same time, combined with the target area map data of the target area, taking the parking space as the starting point, we get The total length corresponding to multiple moments in time is The departure trajectory point P L .

[0073] In some instances, the target area includes multiple parking spaces. When the target vehicle leaves the parking space, the sensor device will report the parking information of the parking space, namely, the license plate information, parking space information, parking space status change time, size, predicted position, etc. to the server in real time; the server will continuously monitor the ROI area according to the parking space status change time and the ROI area corresponding to the parking space.

[0074] Specifically, the third vehicle characteristic information of the target vehicle when it is located in the first measurement area at the second moment can be obtained based on the sensing device 2, and the third vehicle characteristic information includes the position information P3, vehicle size information U3, vehicle heading angle information H3, vehicle instantaneous speed information R3 and vehicle type T3 of the target vehicle, etc. At the same time, the fourth vehicle characteristic information measured at the departure trajectory point of the second vehicle in the second measurement area can be obtained based on the sensing device 1, and the fourth vehicle characteristic information includes the departure trajectory point P of the second vehicle. L , vehicle size information U4, vehicle heading angle information H4, vehicle instantaneous speed information R4 and vehicle type T4 of the second vehicle, etc. Based on this, the difference value M2 between the second vehicle and the target vehicle can be determined based on the third vehicle characteristic information and the fourth vehicle characteristic information:

[0075] M2=α 21 B+α 22 D 11 +α 23 U 11 +α 24 H 11 +α 25 R 11 +α 26 T 11

[0076] B(P L )=0if P L in ROI else 20

[0077] D 11 (P L ,P3)=||P L -P3||

[0078] U 11 (U3,U4)=0if||U3-U4||≤50cm else 10

[0079] H 11 (H3,H4)=0if||H3-H4||≤20°else 10

[0080] R 11 (R3, R4) = || R3-R4 ||, R3 = D 11 / Δt

[0081] T 11 (T3,T4)=0if T3=4else 10

[0082]

[0083] Where B represents P L Whether it falls within the ROI; D 11 Indicates P L The distance from P3, U 11 Indicates the degree of difference between the vehicle size information of the target vehicle and the second vehicle; H 11 Indicates the degree of difference between the vehicle heading angles of the target vehicle and the second vehicle; based on the time difference Δt=t2-t1 between the time t1 when the second vehicle leaves the parking space and the time t2 when the second vehicle appears in the ROI area, and the distance D between the current position of the second vehicle and the parking space 11 , calculate the average speed R3, and compare it with the current speed R4 of the second vehicle to see whether the difference R meets the preset range; T 11 Indicates the degree of difference between the vehicle type information of the target vehicle and the second vehicle. Based on this, when the difference value M1 is less than the preset threshold, the second vehicle is determined to be the target vehicle; Score 2i Indicates the importance of the corresponding indicator feature. For example, the most important indicator among the four indicators has a score of 6, and the least important indicator has a score of 1. 21 represents the weight of B, α 22 Indicates D 11 The weight, α 23 Indicates U 11 The weight, α 24 Indicates H 11 The weight, α 25 Represents R 11 The weight, α 26 Indicates T 11 The weight of .

[0084] Based on this, when the difference value M2 is less than the preset threshold, the second vehicle is determined to be the target vehicle, where the difference value can be 4%, 5%, and can be determined specifically according to the actual situation, confirming that the second vehicle successfully matches the target vehicle, and assigning the target vehicle's license plate information to the second vehicle. At the same time, a digital ID is assigned to the first vehicle, and the license plate is bound to the digital ID and entered into the parking lot smart gate system as the unique identity of the current second vehicle.

[0085] In some instances, the embodiments of the present disclosure may set a sensing device within a certain range from the image acquisition device. For example, a sensing device 3 may be set within a first measurement range to match the image acquisition device and the vehicle acquired by the sensing device.

[0086] In practical applications, the fifth vehicle characteristic information of the target vehicle when it is located in the first measurement area at the second moment can be obtained based on the image acquisition device, and the fifth vehicle characteristic information includes the position information P5, vehicle size information U5, vehicle heading angle information H5, vehicle instantaneous speed information R5 and vehicle type T5 of the target vehicle, etc. At the same time, the sixth vehicle characteristic information measured by the third vehicle in the first measurement area can be obtained based on the sensor device 3, and the sixth vehicle characteristic information includes the position P6, vehicle size information U6, vehicle heading angle information H6, vehicle instantaneous speed information R6 and vehicle type T6 of the third vehicle, etc. It should be understood that a sensor device 3 whose radar beam coverage area overlaps with the perception area of ​​the image acquisition device can be set within a certain range from the image acquisition device, and the setting range here can be set according to actual conditions, as long as there is an overlapping area.

[0087] Based on this, the difference value M3 between the third vehicle and the target vehicle can be determined based on the fifth vehicle characteristic information and the sixth vehicle characteristic information:

[0088] M3=α 31 D 21 +α 32 U 21 +α 33 H 21 +α 34 R 21 +α 35 T 21

[0089] D 21 (P5,P6)=||P5-P6||

[0090] U 21 (U5,U6)=0if||U5-U6||≤50cm else 10

[0091] H 21 (H5,H6)=0if||H5-H6||≤20°else 10

[0092] R 21 (R5,R6)=||R5-R6||

[0093] T 21 (T5,T6)=0if T5=T6else 10

[0094]

[0095] Among them, D 21 represents the distance between the position P5 of the target vehicle and the position P6 of the third vehicle; U 21 Indicates the degree of difference between the target vehicle size U5 and the third vehicle size U6; H 21 Indicates the degree of difference between the heading angle H5 of the target vehicle and the heading angle H6 of the third vehicle; R 21 represents the difference between the speed R5 of the target vehicle and the speed R6 of the third vehicle; T 21 Indicates whether the type of the target vehicle T5 is consistent with the type of the third vehicle T6. The weight parameter α indicates the importance of each characteristic factor. score indicates the importance of the corresponding indicator feature. For example, the most important indicator among the four indicators has score = 5, and the least important indicator has score = 1, α 31 Indicates D 21 The weight, α 32 Indicates U 21 The weight, α 33 Indicates H 21 The weight, α 34 Represents R 21 The weight, α 35 Indicates T 21 The weight of .

[0096] Based on this, when the difference value M3 is less than the preset threshold, the third vehicle is determined to be the target vehicle, where the difference value can be 4%, 5%, and can be determined specifically according to the actual situation, confirming that the third vehicle successfully matches the target vehicle, and assigning the target vehicle's license plate information to the third vehicle. At the same time, a digital ID is assigned to the first vehicle, and the license plate is bound to the digital ID and entered into the parking lot smart gate system as the unique identity of the current third vehicle.

[0097] In an optional manner, when the traffic volume is large, the embodiment of the present disclosure can use the Hungarian algorithm to treat two vehicles of the same type with the smallest comprehensive differences in vehicle position information, vehicle size information, vehicle heading angle information, vehicle instantaneous speed information, and vehicle type as the same object, thereby obtaining the vehicle that best matches the target vehicle.

[0098] In some instances, within the sensing range of a single sensor device, multiple targets can be tracked using the Kalman filter algorithm based on the output information of the three-dimensional detection frame. By associating the detection results of the previous frame with the current frame, a unique identity is assigned to each detected vehicle, and each unique identity is bound to the characteristic information of the vehicle. Based on this, when a vehicle enters the overlapping coverage area of ​​multiple sensor devices, the vehicle is continuously identified and positioned across points, keeping the corresponding unique identity of the vehicle in the parking area unchanged, and accurately positioning the vehicle in the parking area.

[0099] Specifically, the embodiment of the present disclosure is also equipped with sensor devices in multiple lanes of the parking area. The multiple sensor devices transmit radar beams to cover all lanes of the parking area, and the beam coverage areas of the multiple sensor devices have overlapping areas, thereby realizing accurate positioning of vehicles in the parking area.

[0100] In some examples, in the target area, the seventh vehicle characteristic information measured by the target vehicle in the target area can be obtained based on the sensing device 4, and the seventh vehicle characteristic information includes the position P7, vehicle size information U7, vehicle heading angle information H7, vehicle instantaneous speed information R7 and vehicle type T7 of the target vehicle; at the same time, the eighth vehicle characteristic information measured by the fourth vehicle in the target area can be obtained based on the sensing device 5, and the eighth vehicle characteristic information includes the position P8, vehicle size information U8, vehicle heading angle information H8, vehicle instantaneous speed information R8 and vehicle type T8 of the fourth vehicle. Based on this, the difference value M4 between the fourth vehicle and the target vehicle can be determined based on the seventh vehicle characteristic information and the eighth vehicle characteristic information:

[0101] The difference value M4 can be calculated based on the following formula:

[0102] M4=α 41 D 31 +α 42 U 31 +α 43 H 31 +α 44 R 31

[0103] D 31 (P7,P8)=||P7-P8||

[0104] U 31 (U7,U8)=0if||U7-U8||≤50cm else 10

[0105] H 31 (H7,H8)=0if||H7-H8||≤20°else 10

[0106] R 31 (R7,R8)=||R7-R8||

[0107]

[0108] Among them, D 31 represents the distance between the vehicle positions of the target vehicle and the fourth vehicle; U 31 Indicates the degree of difference between the vehicle size information of the target vehicle and the fourth vehicle; H 31 Indicates the degree of difference between the vehicle heading angle information of the target vehicle and the fourth vehicle; R 31 Indicates the difference between the instantaneous speed of the target vehicle and the fourth vehicle. The weight parameter α indicates the importance of each characteristic factor. score indicates the importance of the corresponding indicator feature, for example, the most important indicator score among the four indicators is 4, and the least important indicator score is 1 in descending order. Based on this, when the difference value M4 is less than the preset threshold, the fourth vehicle is determined to be the target vehicle.

[0109] Based on this, when the difference value M4 is less than the preset threshold, the fourth vehicle is determined to be the target vehicle, where the difference value can be 4%, 5%, and can be determined specifically according to the actual situation, confirming that the fourth vehicle successfully matches the target vehicle, and assigning the target vehicle's license plate information to the fourth vehicle. At the same time, a digital ID is assigned to the fourth vehicle, and the license plate is bound to the digital ID and entered into the parking lot smart gate system as the unique identity of the current fourth vehicle.

[0110] The disclosed embodiment can use the Hungarian algorithm to find two vehicles with the smallest comprehensive differences in position, speed, heading angle, shape difference, etc. and less than the matching threshold, and regard them as the same vehicle; for the two matching vehicles, the vehicle identity information and global ID corresponding to the target vehicle are assigned to the successfully matched vehicle, thereby ensuring that the vehicle identity information is not lost when crossing the sensing area of ​​the sensor device. Since there are multiple sensor devices in the parking area, it is necessary to realize continuous cross-point identification and positioning of the vehicle until the vehicle is parked in the parking space, to ensure that the vehicle has a unique identity and corresponding positioning information after entering the parking lot.

[0111] It can be seen that the present disclosure mainly relies on a single sensor device in the venue to identify and locate the two vehicles, and re-proposes a matching model, and there is no need to perform joint calibration of the camera and radar, which is relatively simple to implement; and the gate system, image acquisition system and parking space system are used to realize the identity confirmation of the vehicle, and a trajectory deduction model of gate data and parking space data is proposed. The license plate information identified by the gate and parking space is relatively accurate, and accurate identity information can be provided to the vehicles in the venue; the accurate identity recognition capability can be increased under the premise of ensuring accurate positioning, and at the same time, the installation of the overall equipment can be reduced, the consumption of computing power can be reduced, and the cost of overall deployment can be reduced. Through the identity confirmation of vehicles entering and leaving the venue and the continuous identification and positioning of global sensor equipment, we can maintain continuous tracking and identity confirmation of all vehicles in the venue, and then send it to the vehicle through communication methods such as 5g uu or rsu, so that the vehicle can obtain accurate positioning information of its own vehicle even without GPS signals.

[0112] The above mainly introduces the solution provided by the embodiment of the present disclosure from the perspective of the server. It is understandable that, in order to implement the above functions, the server includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0113] The embodiments of the present disclosure may divide the server into functional units according to the above method examples. For example, each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiments of the present disclosure is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0114] In the case of dividing each functional module according to each function, an exemplary embodiment of the present disclosure provides a vehicle positioning device, which may be a server or a chip applied to a server. Figure 4 FIG. 2 shows a schematic diagram of the structure of a vehicle positioning device according to an exemplary embodiment of the present disclosure. Figure 4 As shown, the vehicle positioning device 400 includes:

[0115] An acquisition module 401 is used to acquire the vehicle speed of the target vehicle when it is in the target area;

[0116] The determination module 402 is used to determine the trajectory point positions corresponding to different times when the target vehicle is traveling in the target area based on the vehicle speed and the trajectory prediction model; wherein the trajectory prediction model is used to predict the trajectory points of the target vehicle during the driving process.

[0117] The generation module 403 is used to generate the driving trajectory of the target vehicle based on the trajectory point positions corresponding to different moments.

[0118] In a possible implementation, the determination module 402 is also used to obtain the first moment when the target vehicle enters the target area and the vehicle speed of the target vehicle passing through the first measurement area in the target area at the second moment; based on the vehicle speed, the first moment and the second moment, obtain the first driving distance of the target vehicle; determine the first position of the target vehicle at the second moment after entering the target area and traveling the first driving distance; predict the second position of the target vehicle at the second moment based on the trajectory prediction model; determine the trajectory point position of the target vehicle at the second moment based on the first position and the second position, wherein the trajectory point position is located in the first measurement area.

[0119] In one possible implementation, first vehicle characteristic information of the target vehicle entering the target area is determined; second vehicle characteristic information measured at the trajectory point position of the first vehicle is determined; based on the first vehicle characteristic information and the second vehicle characteristic information, the characteristic difference information is obtained; and when the difference value is less than a preset threshold, the first vehicle is determined to be the target vehicle.

[0120] In a possible implementation, determining the first position of the target vehicle at the second moment after entering the target area and traveling the first driving distance includes: constructing a driving trajectory dataset, wherein the driving trajectory dataset includes driving trajectories of different vehicles in the target area; obtaining a third position corresponding to the first moment when the target vehicle enters the target area; determining a first driving trajectory from the driving trajectory dataset, wherein the driving distance included in the first driving trajectory is the same as the first driving distance; and determining the first position of the target vehicle in the first measurement area based on the first driving trajectory.

[0121] In a possible implementation, predicting the second position of the target vehicle at the second moment based on the trajectory prediction model includes: constructing a sample set according to a driving trajectory data set; obtaining the second position of the target vehicle in the first measurement area at the second moment based on map feature information and the trajectory prediction model; wherein the trajectory prediction model is obtained by training a preset model through training samples, and the training samples are obtained based on the sample set; the map feature information is the map feature information corresponding to the first moment when the target vehicle enters the target area, and the map feature information is used to describe the position information between the target vehicle and the lane.

[0122] In a possible implementation, based on map feature information and the trajectory prediction model, obtaining the second position of the target vehicle in the first measurement area at a second moment includes: acquiring map data around the target area; performing feature extraction on the map data to obtain map feature information; inputting the map feature information into the trajectory prediction model to determine probability values ​​of the target vehicle at different positions in the first measurement area, and determining the position with the largest probability value as the second position of the target vehicle in the first measurement area predicted by the trajectory prediction model.

[0123] In a possible implementation, speed limit information and target area map data corresponding to the target area are obtained; wherein the target area map data includes all driving trajectories in the target area; based on the speed limit information and the target area map data, the positions of departure trajectory points corresponding to different times when the target vehicle drives in the target area after leaving the parking space are determined in the target area map data; and the departure driving trajectory of the target vehicle is generated based on the departure trajectory point positions corresponding to different times.

[0124] In a possible implementation, multiple second measurement areas are determined in the target area map data, wherein the second measurement area is an area that the vehicle must pass through when leaving the target area; third vehicle characteristic information measured in the first measurement area of ​​the target vehicle is determined; fourth vehicle characteristic information measured in the second measurement area of ​​the second vehicle is determined; based on the third vehicle characteristic information and the fourth vehicle characteristic information, the characteristic difference information is obtained; and when the difference value is less than a preset threshold, the second vehicle is determined to be the target vehicle.

[0125] An embodiment of the present disclosure also provides an electronic device, comprising: at least one processor; a memory for storing instructions executable by at least one processor; wherein the at least one processor is used to execute instructions to implement the steps of the above method disclosed in the embodiment of the present disclosure.

[0126] Figure 5The structure diagram of an electronic device provided by an exemplary embodiment of the present disclosure is shown in FIG. Figure 5 As shown, the electronic device 500 includes at least one processor 501 and a memory 502 coupled to the processor 501 , and the processor 501 can execute corresponding steps in the above method disclosed in the embodiment of the present disclosure.

[0127] The processor 501 may also be referred to as a central processing unit (CPU), which may be an integrated circuit chip having signal processing capabilities. Each step in the method disclosed in the embodiment of the present disclosure may be completed by an integrated logic circuit of hardware in the processor 501 or by instructions in the form of software. The processor 501 may be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present disclosure may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a memory 502, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, or other mature storage media in the art. The processor 501 reads the information in the memory 502 and completes the steps of the method in combination with its hardware.

[0128] In addition, when various operations / processes according to the present disclosure are implemented by software and / or firmware, they can be transmitted from a storage medium or a network to a computer system having a dedicated hardware structure, for example, Figure 6 The computer system 140 shown is installed with the programs constituting the software. When the various programs are installed, the computer system can perform various functions, including the functions described above. Figure 6 A schematic diagram of the structure of a computer system provided by an exemplary embodiment of the present disclosure.

[0129] Computer system 600 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, 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 disclosure described and / or claimed herein.

[0130] like Figure 6 As shown, the computer system 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer system 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 606 is also connected to the bus 604.

[0131] A plurality of components in the computer system 600 are connected to the I / O interface 606, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 can be any type of device capable of inputting information to the computer system 600, and the input unit 606 can receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 607 can be any type of device capable of presenting information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 608 can include but is not limited to a disk, an optical disk. The communication unit 609 allows the computer system 600 to exchange information / data with other devices over a network such as the Internet, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, for example, a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0132] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above. For example, in some embodiments, the above methods disclosed in the embodiments of the present disclosure may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via the ROM 602 and / or the communication unit 609. In some embodiments, the computing unit 601 may be configured to perform the above methods disclosed in the embodiments of the present disclosure in any other appropriate manner (e.g., by means of firmware).

[0133] The embodiment of the present disclosure also provides a computer-readable storage medium, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the above method disclosed in the embodiment of the present disclosure.

[0134] The computer-readable storage medium in the disclosed embodiments may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. The 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. More specifically, the computer-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.

[0135] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0136] The embodiments of the present disclosure also provide a computer program product, including a computer program, wherein the computer program implements the above method disclosed in the embodiments of the present disclosure when executed by a processor.

[0137] In embodiments of the present disclosure, computer program codes for performing the operations of the present disclosure may be written in one or more programming languages ​​or combinations thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer.

[0138] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0139] The modules, components or units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the names of the modules, components or units do not, in some cases, limit the modules, components or units themselves.

[0140] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0141] The above descriptions are only some embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, a technical solution formed by replacing the above features with the technical features with similar functions disclosed in the present disclosure (but not limited to).

[0142] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A vehicle positioning method, characterized in that: include: Obtain the vehicle speed of the target vehicle when it is in the target area; Based on the vehicle speed and trajectory prediction model, determining the trajectory point positions corresponding to different times when the target vehicle is traveling in the target area; wherein the trajectory prediction model is used to predict the trajectory points of the target vehicle during the driving process; The driving trajectory of the target vehicle is generated based on the trajectory point positions corresponding to the different moments.

2. The vehicle positioning method according to claim 1, characterized in that: The determining of the trajectory point positions corresponding to different times when the target vehicle is traveling in the target area includes: Acquire a first moment when the target vehicle enters the target area and a vehicle speed when the target vehicle passes through a first measurement area in the target area at a second moment; Based on the vehicle speed, the first moment and the second moment, obtaining a first travel distance of the target vehicle; Determine a first position of the target vehicle at the second time after the target vehicle enters the target area and travels the first travel distance; Predicting a second position of the target vehicle at the second moment based on the trajectory prediction model; A track point position of the target vehicle at the second moment is determined based on the first position and the second position, wherein the track point position is located in the first measurement area.

3. The vehicle positioning method according to claim 2, characterized in that: The method further comprises: Determine first vehicle characteristic information of the target vehicle entering the target area; Determine characteristic information of a second vehicle measured by the first vehicle at the position of the trajectory point; obtaining the characteristic difference information based on the first vehicle characteristic information and the second vehicle characteristic information; When the difference value is less than a preset threshold, the first vehicle is determined to be the target vehicle.

4. The vehicle positioning method according to claim 2, characterized in that: The determining the first position of the target vehicle at the second time after the target vehicle enters the target area and travels the first travel distance includes: Constructing a driving trajectory data set, wherein the driving trajectory data set includes driving trajectories of different vehicles in the target area; Acquire a third position corresponding to the first moment when the target vehicle enters the target area; Determine a first driving trajectory from the driving trajectory data set, wherein the driving distance included in the first driving trajectory is the same as the first driving distance; A first position of the target vehicle in the first measurement area is determined based on the first driving trajectory.

5. The vehicle positioning method according to claim 2, characterized in that: The predicting the second position of the target vehicle at the second moment based on the trajectory prediction model includes: Construct a sample set based on the driving trajectory dataset; Based on the map feature information and the trajectory prediction model, a second position of the target vehicle in the first measurement area at a second moment is obtained; wherein the trajectory prediction model is obtained by training a preset model through training samples, and the training samples are obtained based on a sample set; the map feature information is the map feature information corresponding to the first moment when the target vehicle enters the target area, and the map feature information is used to describe the position information between the target vehicle and the lane.

6. The vehicle positioning method according to claim 5, characterized in that: Based on the map feature information and the trajectory prediction model, obtaining a second position of the target vehicle in the first measurement area at a second moment includes: Acquire map data around the target area; Extracting features from the map data to obtain map feature information; The map feature information is input into a trajectory prediction model to determine probability values ​​of the target vehicle at different positions in the first measurement area, and the position with the largest probability value is determined as the second position of the target vehicle in the first measurement area predicted by the trajectory prediction model.

7. The vehicle positioning method according to claim 1, characterized in that: The method further comprises: Acquire speed limit information corresponding to the target area and target area map data; wherein the target area map data includes all driving tracks in the target area; Based on the speed limit information and the target area map data, determining in the target area map data the positions of the departure trajectory points corresponding to different moments when the target vehicle drives in the target area after leaving the parking space; The departure driving trajectory of the target vehicle is generated based on the departure trajectory point positions corresponding to the different time periods.

8. The vehicle positioning method according to claim 1, characterized in that: The method further comprises: Determining a plurality of second measurement areas in the target area map data, wherein the second measurement areas are areas that a vehicle must pass through when leaving the target area; Determining third vehicle characteristic information measured by the target vehicle in the first measurement area; Determining fourth vehicle characteristic information measured by the second vehicle in the second measurement area; obtaining the characteristic difference information based on the third vehicle characteristic information and the fourth vehicle characteristic information; When the difference value is less than a preset threshold, the second vehicle is determined to be the target vehicle.

9. An electronic device, characterized in that: include: at least one processor; a memory for storing the at least one processor-executable instruction; The at least one processor is configured to execute the instructions to implement the steps of the method as claimed in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method as claimed in any one of claims 1 to 8.

Images