Real-time tracking method for vehicle position information, computer equipment and storage medium

By using mean filtering and Kalman filtering to process vehicle position information in automatic parking technology, the problem of low vehicle position tracking accuracy in complex environments is solved, and the success rate and user experience of automatic parking are improved.

CN118913267APending Publication Date: 2024-11-08HUMAN HORIZONS (SHANGHAI) AUTONOMOUS TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310510329.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-08
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

In complex environments, the real-time tracking accuracy of vehicle position information in the existing automatic parking technology is low, resulting in inaccurate planning of automatic parking paths and low success rate.

Method used

By obtaining the position information of the parking space to be locked on the map that is updated in real time and the real-time position information of the vehicle, performing mean filtering and Kalman filtering to determine whether there is a locked parking space, and updating the vehicle position information based on the relative position distance observation and predicted value.

Benefits of technology

It improves the accuracy of vehicle location information and the accuracy of automatic parking paths, enhances the success rate of automatic parking, and improves the user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118913267A_ABST
    Figure CN118913267A_ABST
Patent Text Reader

Abstract

The invention relates to a vehicle position information real-time tracking method, computer equipment and a storage medium. The method comprises the following steps: acquiring position information of a to-be-locked parking space displayed on a real-time updated map and real-time position information of a vehicle in a world coordinate system; according to the position information of the to-be-locked parking space and the real-time position information of the vehicle, whether a locked parking space exists or not is judged, and the locked parking space is the to-be-locked parking space which is overlapped with the position of the vehicle; if the locked parking space exists, obtaining a relative position distance observation value and a relative position distance prediction value; and performing Kalman filtering according to the relative position distance observation value and the relative position distance prediction value to obtain a relative position distance estimation value, so that the real-time position information of the vehicle is updated according to the relative position distance estimation value. By adopting the method, the accuracy of vehicle position information tracked in real time can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a real-time tracking method for vehicle position information, a computer device, and a storage medium. Background Art

[0002] With the improvement of people's living standards, cars have become an indispensable means of travel for people. However, due to the limited parking space in the city, finding parking spaces in the limited parking spaces and successfully parking are problems that drivers often face. Therefore, automatic parking technology has developed rapidly.

[0003] The most commonly used automatic parking technology is based on visual perception. In the process of realizing automatic parking based on visual perception, after obtaining parking space information according to the visual sensor, the path is planned and tracked starting from the current real-time position of the vehicle. However, the current automatic parking method has low accuracy of real-time tracking of vehicle position information when the vehicle is in a complex environment. Summary of the invention

[0004] Based on this, it is necessary to provide a real-time tracking method, computer equipment and storage medium for vehicle position information that can improve the accuracy of real-time tracking of vehicle position information when the vehicle is in a complex environment to address the above technical problems.

[0005] In one embodiment, a method for real-time tracking of vehicle location information is provided, the method comprising:

[0006] Obtaining the location information of the parking space to be locked displayed on the real-time updated map and the real-time location information of the vehicle in the world coordinate system; wherein the location information of the parking space to be locked is determined according to each key data frame obtained after performing mean filtering on multiple frames of data input by the visual perception module;

[0007] According to the location information of the parking space to be locked and the real-time location information of the vehicle, it is determined whether there is a locked parking space, and the locked parking space is the parking space to be locked that overlaps with the vehicle;

[0008] If there is a locked parking space, obtain the relative position distance observation value and the relative position distance prediction value. The position distance observation value is the relative distance value between the vehicle and the locked parking space in the vehicle coordinate system, and the relative position distance prediction value is the relative distance value between the vehicle and the locked parking space in the world coordinate system.

[0009] Kalman filtering is performed based on the relative position distance observation value and the relative position distance prediction value to obtain the relative position distance estimation value, so that the real-time position information of the vehicle is updated according to the relative position distance estimation value.

[0010] In one of the embodiments, obtaining the position information of the parking spaces to be locked displayed on the map updated in real time includes: obtaining the target parking space position information corresponding to each data frame; the target parking space position information includes the parking space position information of each parking space to be locked in the world coordinate system; performing mean filtering on each data frame according to the standard deviation of the target parking space position information corresponding to each data frame to obtain each key data frame; and updating the map in real time according to each key frame data frame to obtain the position information of the parking spaces to be locked.

[0011] In one of the embodiments, the method further includes: after acquiring the target parking space position information corresponding to each data frame, storing each data frame in a cache queue in the order of acquisition time; wherein, according to the standard deviation of the target parking space position information corresponding to each data frame, performing mean filtering on each data frame to obtain each key data frame, including: determining whether the number of data frames in the cache queue is greater than or equal to the set number of frames; if the number of data frames in the cache queue is greater than or equal to the set number of frames, calculating the standard deviation according to the target parking space position information corresponding to each data frame; in response to the standard deviation being less than the standard deviation threshold, determining each data frame in the cache queue as a key data frame.

[0012] In one of the embodiments, each data frame is subjected to mean filtering processing according to the standard deviation of the target parking space position information corresponding to each data frame to obtain each key data frame, and also includes: in response to the standard deviation being greater than or equal to the standard deviation threshold, deleting the current first frame of data in the cache queue, inserting a new frame of data after the current last frame of data in the cache queue, and returning to the step of calculating the standard deviation according to the target parking space position information corresponding to each data frame.

[0013] In one of the embodiments, each data frame is subjected to mean filtering processing according to the standard deviation of the target parking space position information corresponding to each data frame to obtain each key data frame, and also includes: if the number of data frames is less than the set number of frames, a new data frame is added after the current last frame of data in the cache queue, so that the number of data frames in the cache queue is greater than or equal to the set number of frames.

[0014] In one of the embodiments, obtaining target parking space position information corresponding to multiple frames of data frames input by visual perception includes: obtaining initial parking space position information corresponding to each data frame; the initial parking space position information includes parking space position information of each parking space to be locked in a vehicle coordinate system; performing coordinate conversion from a vehicle coordinate system to a world coordinate system on the initial parking space position information corresponding to each data frame to obtain target parking space position information corresponding to each data frame.

[0015] In one of the embodiments, judging whether there is a locked parking space based on the position information of the parking space to be locked and the real-time position information of the vehicle includes: determining the degree of overlap of each parking space to be locked based on the position information of the parking space to be locked and the real-time position information of the vehicle; wherein the degree of overlap is used to characterize the degree of overlap between the area where the corresponding parking space to be locked is located and the projection area of ​​the vehicle; if there is any overlap degree greater than or equal to an overlap degree threshold, the parking space to be locked corresponding to the overlap degree greater than the overlap degree threshold is judged as a locked parking space; if each overlap degree is less than the overlap degree threshold, it is judged that there is no locked parking space among the parking spaces to be locked.

[0016] In one of the embodiments, the degree of overlap of each parking space to be locked is determined based on the location information of the parking space to be locked and the real-time location information of the vehicle, including: calculating based on the location information of the parking space to be locked and the real-time location information of the vehicle to obtain the overlapping area of ​​each parking space to be locked; wherein the overlapping area is the area where the area where the corresponding parking space to be locked is located overlaps with the projection area of ​​the vehicle; and determining the corresponding degree of overlap based on each overlapping area.

[0017] In one of the embodiments, the above method also includes: before performing mean filtering processing on each data frame according to the standard deviation of the target parking space position information corresponding to each data frame to obtain each key data frame, performing deformed parking space filtering processing on the target parking space position information corresponding to each data frame to obtain standard parking space position information of the corresponding data frame; the standard parking space position information includes the parking space position information of each standard parking space in the world coordinate system; wherein, performing mean filtering processing on each data frame according to the standard deviation of the target parking space position information corresponding to each data frame to obtain each key data frame includes: performing mean filtering processing on each data frame according to the standard deviation of the standard parking space position information corresponding to each data frame to obtain each key frame.

[0018] In one embodiment, the method further includes: updating the current automatic parking path according to the relative position distance estimation value to obtain an updated automatic parking path, so that the vehicle automatically parks according to the updated automatic parking path.

[0019] In one embodiment, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of any method in the above method embodiments are implemented.

[0020] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any method in the above method embodiments are implemented.

[0021] In the above-mentioned real-time tracking method of vehicle position information, computer equipment and storage medium, the position information of the parking space to be locked displayed on the real-time updated map and the real-time position information of the vehicle in the world coordinate system are obtained; wherein, the position information of the parking space to be locked is determined according to each key data frame with high stability obtained after mean filtering of multiple frames of data frames input by the visual perception module, and it has high accuracy; then, according to the position information of the parking space to be locked and the real-time position information of the vehicle, it is timely judged whether there is a parking space to be locked that overlaps with the position of the vehicle, that is, the locked parking space; then, when there is a locked parking space, Kalman filtering is started, and the position distance prediction value is Kalman filtered according to the acquired relative position distance observation value and relative position distance prediction value to obtain a relative position distance estimation value, so that the real-time position information of the vehicle is updated according to the relative position distance estimation value, thereby realizing the optimal estimation of the relative distance value between the vehicle and the locked parking space, and also being able to complete the updating of the real-time position information of the vehicle according to the relative position distance estimation value, thereby improving the accuracy of the real-time position information of the vehicle and reducing the error of the real-time position information of the vehicle. The position distance observation value is the relative distance value between the vehicle and the locked parking space in the vehicle coordinate system, and the relative position distance prediction value is the relative distance value between the vehicle and the locked parking space in the world coordinate system. It can be understood that since the vehicle position information needs to be tracked in real time during the path planning process, the above embodiment improves the accuracy of the vehicle's real-time position information while also improving the accuracy of the subsequently planned automatic parking path, thereby improving the success rate of automatic parking and thus improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A diagram of an application environment of a method for real-time tracking of vehicle position information in an embodiment;

[0023] Figure 2 A first flow chart of a method for real-time tracking of vehicle position information in an embodiment;

[0024] Figure 3 A first flow chart of a step of acquiring location information of a parking space to be locked displayed on a map updated in real time in one embodiment;

[0025] Figure 4 is a flowchart of a step of determining whether there is a locked parking space according to the position information of the parking space to be locked and the real-time position information of the vehicle in one embodiment;

[0026] Figure 5 A second flow chart of the step of obtaining the location information of the parking space to be locked displayed on the map updated in real time in one embodiment;

[0027] Figure 6A second flow chart of a method for real-time tracking of vehicle position information in one embodiment;

[0028] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0030] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0032] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first resistor may be referred to as a second resistor, and similarly, a second resistor may be referred to as a first resistor. Both the first resistor and the second resistor are resistors, but they are not the same resistor.

[0033] It can be understood that the “connection” in the following embodiments should be understood as “electrical connection”, “communication connection”, etc. if the connected circuits, modules, units, etc. have electrical signals or data transmission between each other.

[0034] When used herein, the singular forms "a", "an", and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" etc. specify the presence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof.

[0035] The real-time tracking method of vehicle position information provided by the present disclosure can be applied to Figure 1In the vehicle 100 shown, the vehicle 100 may include an onboard terminal 110 and a visual perception module 120. The onboard terminal 110 includes at least one memory 20 and at least one processor 10, wherein a computer program is stored in the at least one memory 20, and when the computer program is executed by the at least one processor 10, the real-time tracking method of vehicle position information according to the exemplary embodiment of the present disclosure is executed. It can be understood that the onboard terminal 110 does not have to be a single electronic device, but may also be any collection of devices or circuits that can execute the above-mentioned computer program alone or in combination.

[0036] In the vehicle terminal 110, the processor 10 may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller or a microprocessor. As an example but not limitation, the processor 10 may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array or a network processor, etc.

[0037] In the vehicle-mounted terminal 110, the processor 10 can run a computer program stored in the memory 20, which can be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory 20 and executed by the processor 10 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device. For example, the detail compensation model in the embodiment of the present disclosure can be one of the modules / units.

[0038] The memory 20 may be integrated with the processor 10, for example, by placing RAM or flash memory within an integrated circuit microprocessor or the like. In addition, the memory may include a separate device, such as an external disk drive, a storage array, or any other storage device that may be used by a database system. The memory and processor may be operatively coupled, or may communicate with each other, such as through an I / O port, a network connection, etc., so that the processor can read files stored in the memory.

[0039] In addition, the vehicle terminal 110 may also include a display device (such as a liquid crystal display) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.) All components of the vehicle terminal 110 may be connected to each other via a bus and / or a network.

[0040] The visual perception module 120 may be a surround view camera, and the number of the visual perception modules 120 and the installation position on the vehicle 100 may be determined according to actual needs. The visual perception module 120 may generally include four fisheye cameras, which are respectively installed on the front of the vehicle, the parking space, the left rearview mirror, and the right rearview mirror. Therefore, the visual perception module 120 can obtain visual images in the four directions of the front, back, left, and right of the vehicle through the above-mentioned installation positions. The above are only specific examples, which can be flexibly set according to user needs in actual applications and are not limited here.

[0041] First, as Figure 2 As shown, a real-time tracking method for vehicle position information is provided, and the method is applied to Figure 1 Taking the vehicle-mounted terminal 110 as an example, the above-mentioned method for real-time tracking of vehicle location information includes the following steps 202 to 208.

[0042] Step 202: Acquire the location information of the parking space to be locked displayed on the map updated in real time and the real-time location information of the vehicle in the world coordinate system.

[0043] It is understandable that the vehicle terminal 110 is pre-configured with a real-time updated map, and the real-time updated map displays the location information of the parking space to be locked with high accuracy. The vehicle terminal 110 can obtain the location information of the parking space to be locked displayed on the real-time updated map and the real-time location information of the vehicle in the world coordinate system. In addition, the above-mentioned real-time updated map can be, but is not limited to, a self-built map.

[0044] The parking space to be locked is a parking space within the perception area of ​​the visual perception module 120. The position information of the parking space to be locked is determined according to each key data frame obtained after the mean filtering is performed on the multiple frames of data input by the visual perception module 120. It can be understood that the corresponding key data frame is obtained after the mean filtering is performed on the multiple frames of data, which reduces the noise of the data frame and improves the stability of the key data frame, thereby ensuring the high accuracy of the position information of the parking space to be locked.

[0045] In a specific example, the real-time position information of the vehicle in the world coordinate system can be obtained by a positioning device, or by fusing the information collected by multiple positioning devices. Specifically, the real-time position information of the vehicle can be obtained by one of the perception sensors, the kinematic sensors of the vehicle, or the third-party positioning system, or by fusing the positioning information collected by multiple devices therein. For example, the first positioning information can be collected by the perception sensors such as the visual sensing module, ultrasonic radar, laser radar, etc. of the vehicle, the second positioning information of the vehicle can be collected by the vehicle kinematic sensors such as wheel speed odometer or inertial measurement unit (IMU), etc., and the third-party positioning system such as global navigation satellite system (GNSS) can collect the third positioning information of the vehicle. Among them, one of the first positioning information, the second positioning information, or the third positioning information can be used as the positioning information of the vehicle, or multiple positioning information can be fused to obtain the real-time position information of the vehicle. The above is only a specific example, which is flexibly set according to user needs in actual applications and is not limited here.

[0046] In one embodiment, if Figure 3 As shown, obtaining the location information of the parking space to be locked displayed on the map updated in real time includes steps 301 to 303.

[0047] Step 301, obtaining the target parking space position information corresponding to each data frame.

[0048] Among them, the target parking space position information includes the parking space position information of each parking space to be locked in the world coordinate system. In a specific example, the parking space position information of the parking space to be locked can be represented by the coordinate values ​​of the four corner points of the parking space to be locked in the world coordinate system, the parking space width and the parking space length. It should be noted that the parking space position information of the parking space to be locked can be represented in numerical form. For example, the parking space position information of the parking space to be locked can be expressed by the line segment expression of the four parking space lines of the parking space to be locked in the world coordinate system. The above is only a specific example. In actual application, it is flexibly set according to user needs and is not limited here.

[0049] Specifically, the vehicle terminal 110 can obtain the target parking space position information corresponding to the multiple data frames input by the visual perception module 120. The visual perception module 120 collects image or video information through a camera, and then obtains the target parking space position information corresponding to each data frame after processing. In addition, the multiple data frames can be but are not limited to continuous multiple data frames.

[0050] Step 302: Perform mean filtering on each data frame according to the standard deviation of the target parking space position information corresponding to each data frame to obtain each key data frame.

[0051] Among them, the vehicle terminal 110 can calculate the standard deviation of the target parking space position information corresponding to each data frame based on the target parking space position information corresponding to the acquired multiple data frames; then, according to the standard deviation of the target parking space position information corresponding to each data frame, each data frame can be subjected to mean filtering processing, thereby obtaining each data frame after mean filtering processing, that is, each key data frame. It can be understood that the process of mean filtering processing is also the process of deleting abnormal frame data in multiple data frames, that is, the key data frame has better stability than the multiple data frames, thereby improving the accuracy of the parking space position information to be locked.

[0052] Step 303: Update the map in real time according to each key frame data frame to obtain the location information of the parking space to be locked.

[0053] The vehicle-mounted terminal 110 can update the map in real time according to each key frame data frame, thereby obtaining the position information of the parking space to be locked, and further improving the accuracy of the real-time updated map and the position information of the parking space to be locked.

[0054] Step 204: determine whether there is a locked parking space based on the location information of the parking space to be locked and the real-time location information of the vehicle.

[0055] The locked parking space is a parking space to be locked that overlaps with the vehicle; it can be understood that the overlap is a partial or complete overlap between the projection area of ​​the vehicle and the area where the parking space to be locked is located. The vehicle terminal 110 can determine whether there is a locked parking space based on the location information of the parking space to be locked and the real-time location information of the vehicle.

[0056] In one embodiment, if Figure 4 As shown, judging whether there is a locked parking space based on the position information of the parking space to be locked and the real-time position information of the vehicle includes steps 401 to 403.

[0057] Step 401, determining the degree of overlap of each parking space to be locked according to the position information of the parking space to be locked and the real-time position information of the vehicle.

[0058] The overlap degree is used to indicate the overlap degree between the area where the corresponding parking space to be locked is located and the projection area of ​​the vehicle. The vehicle terminal 110 can determine the overlap degree of each parking space to be locked according to the location information of the parking space to be locked and the real-time location information of the vehicle.

[0059] In one embodiment, determining the degree of overlap of each parking space to be locked according to the location information of the parking space to be locked and the real-time location information of the vehicle includes:

[0060] Calculate the overlapping area of ​​each parking space to be locked based on the location information of the parking space to be locked and the real-time location information of the vehicle;

[0061] The corresponding overlapping degree is determined according to each overlapping area.

[0062] The overlapping area is the area where the corresponding parking space to be locked is overlapped with the projection area of ​​the vehicle. The vehicle terminal 110 can calculate the overlapping area of ​​each parking space to be locked based on the location information of the parking space to be locked and the real-time location information of the vehicle; then, the corresponding overlapping degree is determined based on each overlapping area, thereby improving the convenience and accuracy of determining the overlapping degree of each parking space to be locked.

[0063] In a specific example, the overlapping degree of the corresponding parking spaces to be locked is determined according to the overlapping area of ​​each parking space to be locked. The overlapping area of ​​the parking spaces to be locked can be directly used to characterize the overlapping degree of the parking spaces to be locked, or the ratio of the overlapping area of ​​the parking spaces to be locked to the area of ​​the area where the parking spaces to be locked are located can be used to characterize the overlapping degree of the parking spaces to be locked. The above is only a specific example, and it can be flexibly set according to user needs in actual applications, and is not limited here.

[0064] In a specific example, the overlapping area of ​​each parking space to be locked is calculated based on the location information of the parking space to be locked and the real-time location information of the vehicle, including: determining the bounding box of each parking space to be locked based on the location information of the parking space to be locked; then determining the bounding box of the vehicle based on the real-time location information of the vehicle; calculating the intersection area of ​​the bounding box of each parking space to be locked and the bounding box of the vehicle to obtain the corresponding overlapping area of ​​the parking space to be locked. The above is only a specific example, which can be flexibly set according to user needs in actual applications and is not limited here.

[0065] Step 402: If there is any overlap degree greater than or equal to the overlap degree threshold, the to-be-locked parking space corresponding to the overlap degree greater than the overlap degree threshold is determined as a locked parking space.

[0066] Step 403: If the overlapping degrees are all less than the overlapping degree threshold, it is determined that there is no locked parking space among the parking spaces to be locked.

[0067] Specifically, the degree of overlap of each parking space to be locked is determined according to the position information of the parking space to be locked and the real-time position information of the vehicle; then, in the case that any overlap degree is greater than or equal to the overlap degree threshold, the parking space to be locked corresponding to the overlap degree greater than the overlap degree threshold is determined to be a locked parking space; at the same time, in the case that each overlap degree is less than the overlap degree threshold, it is determined that there is no locked parking space among the parking spaces to be locked, thereby improving the efficiency and accuracy of judging whether there is a locked parking space, and facilitating the initiation of Kalman filtering based on the relative position distance observation value and the relative position distance prediction value.

[0068] Step 206: If there is a locked parking space, obtain the relative position distance observation value and the relative position distance prediction value.

[0069] Among them, the position distance observation value is the relative distance value between the vehicle and the locked parking space in the vehicle coordinate system, and the relative position distance prediction value is the relative distance value between the vehicle and the locked parking space in the world coordinate system. Specifically, the position distance observation value can be determined according to the result of the perceived parking space line input by the visual perception module. The relative position distance prediction value can be determined according to the map updated in real time. Specifically, the vehicle-mounted terminal 110 can obtain the relative position distance observation value and the relative position distance prediction value when there is a locked parking space in each parking space to be locked.

[0070] In a specific example, the vehicle coordinate system can be based on the center of the rear axle of the vehicle as the far point, the centerline of the vehicle as the Y axis (the front of the vehicle is the positive direction of the Y axis), and the straight line perpendicular to the centerline of the vehicle as the X axis (the right side is the positive direction of the X axis). The above is only a specific example, and it can be flexibly set according to user needs in actual applications, and is not limited here.

[0071] Step 208, performing Kalman filtering based on the relative position distance observation value and the relative position distance prediction value to obtain a relative position distance estimation value, so that the vehicle real-time position information is updated according to the relative position distance estimation value.

[0072] Among them, the vehicle-mounted terminal 110 performs Kalman filtering based on the relative position distance observation value and the relative position distance prediction value, thereby completing the fusion processing of the relative position distance observation value and the relative position distance prediction value, and obtaining the relative position distance estimation value, thereby realizing the optimal estimation of the relative distance value between the vehicle and the locked parking space, and updating the real-time position information of the vehicle according to the relative position distance estimation value.

[0073] It is understandable that the real-time position of the vehicle may not be accurate in traditional automatic parking methods in some scenarios such as weather, light, positioning signal strength, and large differences in underground terrain. For example, when the perception vision module, ultrasonic radar, lidar and other sensors receive external interference such as light, weather, and electromagnetic waves, there will be a significant loss of accuracy, which will lead to inaccurate automatic parking paths planned later.

[0074] In the above-mentioned real-time tracking method of vehicle position information, the position information of the parking space to be locked displayed on the real-time updated map and the real-time position information of the vehicle in the world coordinate system are obtained; wherein, the position information of the parking space to be locked is determined according to each key data frame with high stability obtained after mean filtering of multiple frames of data frames input by the visual perception module 120, and it has high accuracy; then, according to the position information of the parking space to be locked and the real-time position information of the vehicle, it is timely judged whether there is a parking space to be locked that overlaps with the position of the vehicle, that is, the locked parking space; then, when there is a locked parking space, Kalman filtering is started, and the position distance prediction value is Kalman filtered according to the acquired relative position distance observation value and relative position distance prediction value to obtain a relative position distance estimation value, so that the real-time position information of the vehicle is updated according to the relative position distance estimation value, thereby realizing the optimal estimation of the relative distance value between the vehicle and the locked parking space, and also being able to complete the updating of the real-time position information of the vehicle according to the relative position distance estimation value, thereby improving the accuracy of the real-time position information of the vehicle and reducing the error of the real-time position information of the vehicle. The position distance observation value is the relative distance value between the vehicle and the locked parking space in the vehicle coordinate system, and the relative position distance prediction value is the relative distance value between the vehicle and the locked parking space in the world coordinate system. It can be understood that since the vehicle position information needs to be tracked in real time during the path planning process, the above embodiment improves the accuracy of the vehicle's real-time position information while also improving the accuracy of the subsequently planned automatic parking path, thereby improving the success rate of automatic parking and thus improving the user experience.

[0075] In one embodiment, if Figure 5 As shown, the method further includes step 501. Step 501, after acquiring the target parking space position information corresponding to each data frame, storing each data frame in a cache queue in the order of acquisition time.

[0076] In a specific example, storing each data frame in the cache queue in the order of acquisition time may be storing the data frame in the order of the timestamps of the data frames. The above is only a specific example, and it can be flexibly set according to user needs in actual applications, and is not limited here.

[0077] Herein, according to the standard deviation of the target parking space position information corresponding to each data frame, mean filtering is performed on each data frame to obtain each key data frame, including steps 502 to 504.

[0078] Step 502, determining whether the number of data frames in the buffer queue is greater than or equal to a set number of frames.

[0079] Step 503: If the number of data frames in the cache queue is greater than or equal to the set number of frames, the standard deviation is calculated according to the target parking space position information corresponding to each data frame.

[0080] Step 504: in response to the standard deviation being less than the standard deviation threshold, each data frame in the buffer queue is determined as a key data frame.

[0081] Among them, the vehicle terminal 110 is pre-set with a set frame number, and the set frame number is flexibly set according to user needs in actual applications and is not limited here. The vehicle terminal 110 can determine whether the number of data frames in the cache queue is greater than or equal to the set frame number; then, when the number of data frames in the cache queue is greater than or equal to the set frame number, it means that the number of data frames in the cache queue at this time meets the requirements of the set frame number, and the standard deviation can be calculated according to the target parking space position information corresponding to each data frame; then, when the standard deviation is less than the standard deviation threshold, it means that each data frame in the cache queue at this time has good stability, and each data frame in the cache queue can be directly determined as a key data frame, thereby ensuring that the key data frame has good stability, thereby improving the accuracy of the parking space position information to be locked.

[0082] In a specific example, the standard deviation of the target parking space position information is calculated based on the following expression:

[0083]

[0084] Among them, σ is the standard deviation of the target parking space location information; n is the total number of data frames; x i is the target parking space position information corresponding to the i-th data frame; μ is the average value of the target parking space position information corresponding to each data frame. The above is only a specific example, and it can be flexibly set according to user needs in actual application, and is not limited here.

[0085] In one embodiment, if Figure 5 As shown, according to the standard deviation of the target parking space position information corresponding to each data frame, mean filtering is performed on each data frame to obtain each key data frame, and step 505 is also included.

[0086] Step 505, in response to the standard deviation being greater than or equal to the standard deviation threshold, delete the current first frame of data in the cache queue, add a new frame of data after the current last frame of data in the cache queue, and return to the step of calculating the standard deviation according to the target parking space position information corresponding to each data frame.

[0087] Among them, when the standard deviation of the vehicle terminal 110 is greater than or equal to the standard deviation threshold, it means that the data frames in the cache queue do not have good stability at this time, and the data frames in the cache queue cannot be directly determined as key data frames, but it is necessary to delete the current first frame of the data frame in the cache queue, add a new frame of data frame after the current last frame of the data frame in the cache queue, and return to the step of calculating the standard deviation according to the target parking space position information corresponding to each data frame, and judge the size relationship between the standard deviation and the standard deviation threshold again to ensure that the key data frame has good stability. It also achieves the deletion of abnormal frame data in the cache queue, thereby improving the accuracy of the parking space position information to be locked.

[0088] In one embodiment, if Figure 5 As shown, according to the standard deviation of the target parking space position information corresponding to each data frame, mean filtering is performed on each data frame to obtain each key data frame, and step 506 is also included.

[0089] Step 506: If the number of data frames is less than the set number of frames, a new data frame is added after the last data frame in the cache queue, so that the number of data frames in the cache queue is greater than or equal to the set number of frames.

[0090] Among them, the vehicle terminal 110 can determine whether the number of data frames in the cache queue is greater than or equal to the set number of frames; then, when the number of data frames in the cache queue is less than the set number of frames, it means that the number of data frames in the cache queue at this time does not meet the requirements of the set number of frames, so that a new data frame is added after the current last frame of data in the cache queue, so that the number of data frames in the cache queue is greater than or equal to the set number of frames, which means that the number of data frames in the cache queue meets the requirements of the set number of frames, thereby improving the convenience of real-time tracking of vehicle location information.

[0091] In a specific example, the new data frame can be added after the current last data frame in the cache queue by cyclically adding a new data frame after the current last data frame in the cache queue until the number of data frames is greater than or equal to the set number of frames; or it can be calculated that the target frame number difference between the set number of frames and the number of data frames, and the new data frames with the same number as the target frame number difference are added after the current last data frame in the cache queue. The above are only specific examples, which can be flexibly set according to user needs in actual applications and are not limited here.

[0092] In one of the embodiments, the above method also includes: performing mean filtering processing on each data frame according to the standard deviation of the target parking space position information corresponding to each data frame, and before obtaining each key data frame, performing deformed parking space filtering processing on the target parking space position information corresponding to each data frame to obtain the standard parking space position information of the corresponding data frame.

[0093] Among them, according to the standard deviation of the target parking space position information corresponding to each data frame, each data frame is subjected to mean filtering processing to obtain each key data frame, including:

[0094] According to the standard deviation of the standard parking space position information corresponding to each data frame, each data frame is subjected to mean filtering processing to obtain each key frame.

[0095] Among them, the parking spaces to be locked include standard parking spaces and deformed parking spaces. Standard parking spaces are parking spaces that meet the parking space design specifications in national standards. Deformed parking spaces are parking spaces that do not meet the parking space design specifications in national standards; for example, parking spaces whose size does not meet the parking space design specifications in national standards or whose parking space ground flatness does not meet the parking space design specifications in national standards. Standard parking space location information includes parking space location information of each standard parking space in the world coordinate system.

[0096] Specifically, before performing mean filtering on each of the data frames, the vehicle-mounted terminal 110 may perform deformed parking space filtering on the target parking space position information corresponding to each data frame, thereby obtaining standard parking space position information of the corresponding data frame; then, according to the standard deviation of the standard parking space position information corresponding to each data frame, mean filtering is performed on each data frame to obtain each key frame, thereby eliminating the adverse effects of deformed parking spaces before performing mean filtering on each data frame, further improving the stability of each key frame, and further improving the accuracy of the parking space position information to be locked.

[0097] In one embodiment, obtaining target parking space position information corresponding to multiple frames of data input by visual perception includes:

[0098] Obtaining the initial parking space position information corresponding to each data frame;

[0099] The initial parking space position information corresponding to each data frame is converted from the vehicle coordinate system to the world coordinate system to obtain the target parking space position information corresponding to each data frame.

[0100] The initial parking space position information includes the parking space position information of each parking space to be locked in the vehicle coordinate system. The vehicle terminal 110 can obtain the initial parking space position information corresponding to each data frame; then, the initial parking space position information corresponding to each data frame is converted from the vehicle coordinate system to the world coordinate system to obtain the target parking space position information corresponding to each data frame, thereby improving the convenience of real-time tracking of vehicle position information.

[0101] In one embodiment, if Figure 6 As shown, the above method also includes step 601.

[0102] Step 601: if there is no locked parking space, the position information of the parking space to be locked and the real-time position information of the vehicle are updated, and the process returns to the step of determining whether there is a locked parking space based on the position information of the parking space to be locked and the real-time position information of the vehicle.

[0103] Among them, when there is no locked parking space among the parking spaces to be locked, the vehicle-mounted terminal 110 needs to update the position information of the parking space to be locked and the real-time position information of the vehicle, and return to the step of determining whether there is a locked parking space based on the position information of the parking space to be locked and the real-time position information of the vehicle until there is a locked parking space, thereby improving the convenience and real-time nature of determining the locked parking space.

[0104] In one embodiment, the method further comprises:

[0105] The current automatic parking path is updated according to the relative position distance estimation value to obtain an updated automatic parking path, so that the vehicle can automatically park according to the updated automatic parking path.

[0106] Among them, the vehicle-mounted terminal 110 can update the current automatic parking path according to the relative position distance estimation value to obtain an updated automatic parking path, so that the vehicle can automatically park according to the updated automatic parking path, thereby improving the accuracy of the subsequently planned automatic parking path, and thus improving the success rate of automatic parking.

[0107] It should be understood that although Figure 2-6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-6 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0108] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a real-time tracking method for vehicle location information is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0109] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0110] In a second aspect, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of any method in the above method embodiments are implemented.

[0111] In a third aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any method in the above method embodiments are implemented.

[0112] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0113] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A real-time tracking method for vehicle position information, characterized in that: The method comprises: Acquire the position information of the parking space to be locked displayed on the real-time updated map and the real-time position information of the vehicle in the world coordinate system; wherein the position information of the parking space to be locked is determined according to each key data frame obtained after performing mean filtering on multiple frames of data input by the visual perception module; According to the position information of the parking space to be locked and the real-time position information of the vehicle, it is determined whether there is a locked parking space, and the locked parking space is a parking space to be locked that overlaps with the position of the vehicle; If the locked parking space exists, a relative position distance observation value and a relative position distance prediction value are obtained, wherein the position distance observation value is a relative distance value between the vehicle and the locked parking space in the vehicle coordinate system, and the relative position distance prediction value is a relative distance value between the vehicle and the locked parking space in the world coordinate system; Kalman filtering is performed based on the relative position distance observation value and the relative position distance prediction value to obtain a relative position distance estimation value, so that the real-time position information of the vehicle is updated according to the relative position distance estimation value.

2. The method according to claim 1, characterized in that The step of obtaining the location information of the parking space to be locked displayed on the map updated in real time includes: Acquire the target parking space position information corresponding to each of the data frames; the target parking space position information includes the parking space position information of each of the parking spaces to be locked in the world coordinate system; According to the standard deviation of the target parking space position information corresponding to each of the data frames, mean filtering is performed on each of the data frames to obtain each of the key data frames; The map is updated in real time according to each of the key frame data frames to obtain the location information of the parking space to be locked.

3. The method according to claim 2, characterized in that The method further comprises: after acquiring the target parking space position information corresponding to each of the data frames, storing each of the data frames in a cache queue in the order of acquisition time; Wherein, the method of performing mean filtering on each of the data frames according to the standard deviation of the target parking space position information corresponding to each of the data frames to obtain each key data frame includes: Determine whether the number of data frames in the cache queue is greater than or equal to a set number of frames; If the number of data frames in the cache queue is greater than or equal to the set number of frames, the standard deviation is calculated according to the target parking space position information corresponding to each of the data frames; In response to the standard deviation being less than a standard deviation threshold, each of the data frames in the cache queue is determined as the key data frame.

4. The method according to claim 3, characterized in that The method further comprises: performing mean filtering on each of the data frames according to the standard deviation of the target parking space position information corresponding to each of the data frames to obtain each key data frame; In response to the standard deviation being greater than or equal to the standard deviation threshold, the current first frame of data in the cache queue is deleted, a new frame of data is added after the current last frame of data in the cache queue, and the process returns to the step of calculating the standard deviation according to the target parking space position information corresponding to each of the data frames.

5. The method according to claim 3, characterized in that: The method further comprises: performing mean filtering on each of the data frames according to the standard deviation of the target parking space position information corresponding to each of the data frames to obtain each key data frame; If the number of data frames is less than the set number of frames, a new data frame is added after the current last data frame in the cache queue, so that the number of data frames in the cache queue is greater than or equal to the set number of frames.

6. The method according to claim 2, characterized in that The method further comprises: before performing mean filtering on each of the data frames according to the standard deviation of the target parking space position information corresponding to each of the data frames to obtain each key data frame, performing abnormal parking space filtering on the target parking space position information corresponding to each of the data frames to obtain standard parking space position information of the corresponding data frame; the standard parking space position information includes parking space position information of each standard parking space in the world coordinate system; Wherein, the method of performing mean filtering on each of the data frames according to the standard deviation of the target parking space position information corresponding to each of the data frames to obtain each key data frame includes: According to the standard deviation of the standard parking space position information corresponding to each of the data frames, mean filtering is performed on each of the data frames to obtain each of the key frames.

7. The method according to claim 2, characterized in that The step of obtaining the target parking space position information corresponding to the multiple frames of data input by visual perception includes: Acquire initial parking space position information corresponding to each of the data frames; the initial parking space position information includes parking space position information of each of the parking spaces to be locked in the vehicle coordinate system; The initial parking space position information corresponding to each of the data frames is subjected to coordinate transformation from the vehicle coordinate system to the world coordinate system to obtain the target parking space position information corresponding to each of the data frames.

8. The method according to claim 1, characterized in that The determining whether there is a locked parking space according to the position information of the parking space to be locked and the real-time position information of the vehicle includes: Determining the degree of overlap of each of the parking spaces to be locked according to the location information of the parking spaces to be locked and the real-time location information of the vehicle; wherein the degree of overlap is used to characterize the degree of overlap between the area where the corresponding parking spaces to be locked are located and the projection area of ​​the vehicle; If any of the overlapping degrees is greater than or equal to the overlapping degree threshold, the parking space to be locked corresponding to the overlapping degree greater than the overlapping degree threshold is determined as the locked parking space; if each of the overlapping degrees is less than the overlapping degree threshold, it is determined that the locked parking space does not exist among the parking spaces to be locked.

9. The method according to claim 7, characterized in that: The step of determining the degree of overlap of each parking space to be locked according to the location information of the parking space to be locked and the real-time location information of the vehicle comprises: Calculating according to the position information of the parking space to be locked and the real-time position information of the vehicle to obtain the overlapping area of ​​each parking space to be locked; wherein the overlapping area is the overlapping area of ​​the area where the corresponding parking space to be locked is located and the projection area of ​​the vehicle; The corresponding overlapping degree is determined according to each overlapping area.

10. The method according to claim 1, characterized in that The method further comprises: The current automatic parking path is updated according to the relative position distance estimation value to obtain an updated automatic parking path, so that the vehicle automatically parks according to the updated automatic parking path.

11. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 10 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.