Vehicle positioning method and device and vehicle navigation method and device

Abstract

The invention discloses a vehicle positioning method and device and a vehicle navigation method and device, and the vehicle positioning method comprises the steps: obtaining a to-be-recognized region image which comprises a target vehicle; determining an absolute coordinate of a target vehicle in a world coordinate system based on a mapping relation between a pixel coordinate system and the world coordinate system and the to-be-recognized area image; based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle, determining the relative coordinates of the target vehicle in the target parking lot map; and sending the relative coordinates of the target vehicle to a map navigation system to update the position of the target vehicle in the target parking lot map. Through the above mode, the target vehicle of the to-be-identified area image acquired by the image acquisition device is positioned through the visual positioning technology, the high real-time performance and accuracy of vehicle positioning are improved, the effect of "what you see is what you get" is realized, and the position of the target vehicle in the target parking lot map can be updated in real time.

Description

Technical Field

[0001] The present application relates to the field of vehicle positioning technology, and in particular to a vehicle positioning method, a vehicle navigation method and a device. Background Art

[0002] With the increasing number of private cars, the scale of parking lots, especially indoor parking lots in public places such as large shopping malls, airports, and stadiums, is also expanding rapidly. While the expansion of indoor parking lots has brought convenience to parking, it has also brought problems such as difficulty in finding parked vehicles, vacant parking spaces, and entrances and exits due to the lack of understanding of the internal environment of the parking lot. Therefore, indoor parking lot navigation technology has emerged.

[0003] At present, parking lot indoor navigation technology relies on vehicle positioning. Therefore, how to quickly and accurately achieve vehicle positioning has become a technical problem that urgently needs to be solved in this field. Summary of the invention

[0004] Based on this, it is necessary to provide a vehicle positioning method, a vehicle navigation method and a device for the above-mentioned technical problems, so as to solve at least one problem existing in the above-mentioned prior art.

[0005] In a first aspect, the embodiment of the present application is implemented as follows: a vehicle positioning method is provided, comprising:

[0006] Acquire an image of the area to be identified, the image of the area to be identified includes a target vehicle, and the image of the area to be identified is acquired by a target image acquisition device;

[0007] Based on the pre-constructed mapping relationship between the pixel coordinate system and the world coordinate system and the image of the area to be identified, determining the absolute coordinates of the target vehicle in the world coordinate system;

[0008] Obtaining the relative coordinates of the target image acquisition device in the target parking lot map;

[0009] Determine the relative coordinates of the target vehicle in the target parking lot map based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system;

[0010] The relative coordinates of the target vehicle in the target parking lot map are sent to a map navigation system to update the position of the target vehicle in the target parking lot map.

[0011] In one embodiment, the mapping relationship is constructed in the following manner:

[0012] Acquire a calibration image, wherein the calibration image includes a calibration reference object;

[0013] Obtaining coordinate information of each corner point of the calibration reference object;

[0014] Calibrate the target image acquisition device based on the coordinate information of each corner point of the calibration reference object;

[0015] Acquiring the calibrated internal and external parameters of the target image acquisition device;

[0016] Based on the internal and external parameters, the mapping relationship from the pixel coordinate system to the world coordinate system is constructed.

[0017] In one embodiment, the determining the absolute coordinates of the target vehicle in the world coordinate system based on the pre-constructed mapping relationship between the pixel coordinate system and the world coordinate system and the image of the area to be identified includes:

[0018] Acquiring vehicle contour features of the target vehicle based on the image of the area to be identified;

[0019] Based on the vehicle contour features, establishing a vehicle identification frame of the target vehicle;

[0020] Determine the image coordinates of the center point of the vehicle identification frame in the pixel coordinate system;

[0021] Based on the mapping relationship, the image coordinates are converted into the absolute coordinates of the target vehicle in the world coordinate system.

[0022] In one embodiment, determining the relative coordinates of the target vehicle in the target parking lot map based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system includes:

[0023] Determining an offset based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system;

[0024] Based on the offset and the absolute coordinates of the target vehicle in the world coordinate system, the relative coordinates of the target vehicle in the target parking lot map are calculated.

[0025] In one embodiment, after acquiring the image of the area to be identified, the following steps are included:

[0026] Tracking the target vehicle in the image of the area to be identified to obtain current vehicle driving track information of the target vehicle, wherein the current vehicle driving track information includes vehicle information;

[0027] The current vehicle driving trajectory information is reported to the map navigation system, so that the map navigation system updates the cached vehicle driving trajectory information of the target vehicle to the current vehicle driving trajectory information based on the vehicle information.

[0028] In one embodiment, reporting the current vehicle driving trajectory information to the map navigation system includes:

[0029] The current vehicle driving trajectory information is reported to the map navigation system, and the current vehicle driving trajectory information includes a serial number, and the serial number is used to characterize the sending order of different vehicle driving trajectory information, so that the map navigation system determines whether to update the cached vehicle driving trajectory information of the target vehicle based on the sending order.

[0030] In one embodiment, the target image acquisition device communicates with the map navigation system via a user datagram protocol, and reports the relative coordinates of the target vehicle in the target parking lot map to the map navigation system once at a preset interval, so that the map navigation system can update the location of the target vehicle in the parking lot map.

[0031] In a second aspect, a vehicle navigation method is provided, the method comprising:

[0032] During vehicle navigation, the yaw distance of the target vehicle is determined according to the relative coordinates of the target vehicle in the target parking lot map and the coordinates of the predicted trajectory points in the current navigation route, wherein the relative coordinates of the target vehicle in the target parking lot map are determined according to the vehicle positioning method;

[0033] When the deviation distance is greater than a preset distance, the navigation route is replanned according to the relative coordinates of the target vehicle in the target parking lot map and the navigation end point.

[0034] In a third aspect, a vehicle positioning device is provided, the vehicle positioning device comprising:

[0035] An image acquisition unit, used for acquiring an image of the area to be identified, wherein the image of the area to be identified includes a target vehicle, and the image of the area to be identified is acquired by a target image acquisition device;

[0036] An absolute coordinate determination unit, used to determine the absolute coordinates of the target vehicle in the world coordinate system based on a pre-constructed mapping relationship between the pixel coordinate system and the world coordinate system and the image of the area to be identified;

[0037] An information acquisition unit, used to acquire the relative coordinates of the target image acquisition device in the target parking lot map;

[0038] A relative coordinate determination unit, configured to determine the relative coordinates of the target vehicle in the target parking lot map based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system;

[0039] The position updating unit is used to send the relative coordinates of the target vehicle in the target parking lot map to the map navigation system to update the position of the target vehicle in the target parking lot map.

[0040] In a fourth aspect, a vehicle navigation device is provided, the device comprising:

[0041] A deviation distance determination unit, used to determine the deviation distance of the target vehicle according to the relative coordinates of the target vehicle in the target parking lot map and the coordinates of the predicted trajectory points in the current navigation route during vehicle navigation, wherein the relative coordinates of the target vehicle in the target parking lot map are determined according to the vehicle positioning method;

[0042] The navigation route planning unit is used to re-plan the navigation route according to the relative coordinates of the target vehicle in the target parking lot map and the navigation end point when the deviation distance is greater than a preset distance.

[0043] The above-mentioned vehicle positioning method, vehicle navigation method, and device, the vehicle positioning method is implemented, including: obtaining an image of the area to be identified, the image of the area to be identified includes a target vehicle, and the image of the area to be identified is obtained by a target image acquisition device; based on a pre-constructed mapping relationship between a pixel coordinate system and a world coordinate system and the image of the area to be identified, determining the absolute coordinates of the target vehicle in the world coordinate system; obtaining the relative coordinates of the target image acquisition device in a target parking lot map; based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system, determining the relative coordinates of the target vehicle in the target parking lot map; sending the relative coordinates of the target vehicle in the target parking lot map to a map navigation system to update the position of the target vehicle in the target parking lot map. In the embodiment of the present application, the vehicle is positioned through the visual positioning technology of the target image acquisition device, and the current position of the vehicle is directly converted to the position in the parking lot map. There is no need for the parking lot map to perform positioning, which reduces the time delay problem of information transmission, and can improve the high real-time performance of vehicle positioning. The conversion relationship between the pixel coordinate system and the world coordinate system is directly used to realize the conversion of the vehicle position in the image and the map. There is no need for the map navigation system to convert again, which can improve the accuracy and efficiency of vehicle positioning, achieve a "what you see is what you get" effect, and can update the position of the target vehicle in the target parking lot map in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0045] Figure 1 is a schematic diagram of an application environment of a vehicle positioning method in an embodiment of the present application;

[0046] Figure 2 This is a flow chart of a vehicle positioning method in one embodiment of the present application. Figure 1 ;

[0047] Figure 3 This is a flow chart of a vehicle positioning method in one embodiment of the present application. Figure 2 ;

[0048] Figure 4 This is a flow chart of a vehicle positioning method in one embodiment of the present application. Figure 3 ;

[0049] Figure 5 This is a flow chart of a vehicle positioning method in one embodiment of the present application. Figure 4 ;

[0050] Figure 6 This is a schematic diagram of a scenario of a vehicle navigation method according to an embodiment of the present application;

[0051] Figure 7 It is a structural schematic diagram of a vehicle positioning device according to an embodiment of the present application;

[0052] Figure 8 It is a schematic diagram of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] The vehicle positioning method provided in this embodiment can be applied in Figure 1In the application environment, the client communicates with the map navigation system, and the map navigation system communicates with the image acquisition device. The image acquisition device may include multiple ones, and the target vehicles in their respective shooting areas are collected and identified. At the same time, a calibration reference is set to construct a conversion matrix between the pixel coordinate system and the world coordinate system, and the relative coordinates of the image acquisition device in the parking lot map are obtained to calculate the relative coordinates of the target vehicle in the parking lot map, and send them to the map navigation system for display. There is no need for the map navigation system to locate, which can improve the timeliness and accuracy of the parking lot vehicle positioning and navigation. In addition, the user can send a subscription request to the map navigation system through the client to subscribe to the current location information of the vehicle. The map navigation system can push and display the relative position of the vehicle collected and calculated by the image acquisition device in the client.

[0055] The client includes but is not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The map navigation system can be implemented with an independent server or a server cluster consisting of multiple servers.

[0056] In one embodiment, if Figure 2 As shown, a vehicle positioning method is provided, comprising the following steps:

[0057] In step S110, an image of the area to be identified is obtained, the image of the area to be identified includes a target vehicle, and the image of the area to be identified is acquired by a target image acquisition device;

[0058] In the embodiment of the present application, the target image acquisition device may include multiple ones, and each target image acquisition device may be installed at different positions, and the shooting ranges may be crossed or connected, so as to continuously shoot vehicles traveling in different lane areas, so as to identify and detect the vehicle in each frame of the image, thereby obtaining the vehicle's driving trajectory. It should be noted that the shooting areas between adjacent image acquisition devices may have partially overlapping areas or overlapping boundary lines, so as to integrate the images captured by multiple image acquisition devices, so as to continuously track and shoot the vehicle's driving trajectory and realize continuous positioning of the vehicle.

[0059] Among them, the image acquisition device can be a camera, a camera or other shooting device. Taking a camera as an example, the camera frame rate is set to 12.5FPS, and the overall delay can be controlled at 250ms, that is, during the movement of the real-world vehicle, the user's client can display the positioning coordinates after 250ms, and then locate once every 80ms, that is, the vehicle is stably located at least 12 times per second. The overall delay may include camera-side processing delay, server-side processing delay and network delay. The camera-side processing delay may include ISP imaging, image processing (800w image resize), AI recognition (vehicle positioning time-consuming) and data reporting. The server-side processing delay may include the delay of receiving the positioning data and pushing the data. The network delay may include the network delay from the camera to the map navigation system and the network delay from the map navigation system to the client. In one embodiment, ISP imaging is 80ms, image processing is 30ms, AI recognition is 80ms, data reporting is 20ms, positioning data is received and pushed to 20ms, the network delay from the camera to the map navigation system is 10ms, and the network delay from the map navigation system to the client is 10ms, so the overall delay is 250ms.

[0060] The camera has a resolution of 8 million, a visual range of 25 meters, and a positioning frequency of 12 per second. If the target vehicle is moving at a constant speed, for example, 25 km / h = 6.9 m / s, the target vehicle is tracked within the camera range at 6.9 m ÷ 12 = 0.575 m, that is, 0.575 m is identified and tracked as a physical position. 0.575 m + (6.9 m × (250 ÷ 1000)) = 2.3 m, so when the target vehicle is in the camera field of view and no processing is done on the navigation, the client displays a stable position lag of 2.3 m, which is equivalent to the distance of one berth.

[0061] The camera's recognition is stable. After receiving the positioning data, the client uses inertial navigation to correct the position of the target vehicle and smooth out the error caused by the 2.3m delay, thereby achieving zero error.

[0062] Among them, the target vehicle may include at least one.

[0063] In step S120, based on the pre-constructed mapping relationship between the pixel coordinate system and the world coordinate system and the image of the area to be identified, the absolute coordinates of the target vehicle in the world coordinate system are determined;

[0064] In the embodiment of the present application, the mapping relationship can be determined based on a pre-laid calibration reference object, which can be a calibration plate, which can specifically include a chessboard, a dot calibration plate, an Aruco code calibration plate, etc. Take the Aruco code calibration plate as an example: the Aruco code calibration plate can be laid flat in the shooting area of ​​the image acquisition device in advance. The Aruco code calibration plate is a tool for visual measurement, which consists of a series of Aruco code marks. These codes are usually black and white squares, containing blocks with unique patterns, so that they can be quickly recognized by the computer vision system.

[0065] In the embodiment of the present application, when laying the calibration reference object, the world coordinates of the calibration reference object can be set. For example, taking the Aruco code calibration plate as an example, the world coordinates corresponding to each Aruco code can be configured to determine the correspondence between the corner coordinates of the calibration plate and the world coordinates. Further, based on the correspondence, a camera calibration algorithm (such as Zhang's calibration algorithm or Tsai calibration algorithm, etc.) is used to calculate the internal parameters (such as camera focal length, principal point position and distortion parameters) and external parameters (such as the rotation and translation matrix of the camera) of the lane camera. Based on the internal parameters and external parameters, a mapping relationship between the world coordinate system and the pixel coordinate system can be constructed, wherein the mapping relationship includes but is not limited to conversion equations, comparison tables, and matrix models.

[0066] Optionally, a pixel coordinate system and a world coordinate system can be established respectively with the image acquisition device as the origin, and the first coordinate information of the corner point coordinates of the calibration plate after distortion correction in the pixel coordinate system and the second coordinate information in the world coordinate system are determined, and the mapping relationship between the first coordinate information and the second coordinate information is determined as a mapping relationship from the pixel coordinate system to the world coordinate system.

[0067] It can be understood that 1px (pixel) of the image to be recognized represents a distance of 10cm in the physical world.

[0068] In an embodiment of the present application, based on the collected image of the area to be identified, vehicle detection is performed on the image to be detected to determine whether there is a target vehicle. If there is a target vehicle, the vehicle coordinates of the target vehicle can be obtained based on the pre-constructed pixel coordinate system. Optionally, the vehicle identification frame of the target vehicle can be detected in the image to be detected by the yolo object detection model, and the coordinates of the center point of the vehicle identification frame in the pixel coordinate system are used as the image coordinates of the target vehicle in the pixel coordinate system. Then, based on the mapping relationship, the image coordinates are converted into the absolute coordinates of the target vehicle in the world coordinate system.

[0069] In step S130, the relative coordinates of the target image acquisition device in the target parking lot map are obtained;

[0070] In the embodiment of the present application, since different image acquisition devices may be set at different locations, the location of each image acquisition device may be stored when the image acquisition device is deployed. When the parking lot management software creates a high-precision map of the parking lot, it may determine the relative coordinates of the installation location of each camera in the high-precision map and send them to the corresponding image acquisition device.

[0071] In step S140, the relative coordinates of the target vehicle in the target parking lot map are determined based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system;

[0072] In the embodiment of the present application, after the absolute coordinates of the target vehicle in the world coordinate system are obtained, the distance between the target vehicle and the image acquisition device can be calculated based on the absolute coordinates and the coordinates of the image acquisition device. Based on the distance, the offset of the target vehicle relative to the image acquisition device can be obtained, and based on the offset, the relative coordinates of the target vehicle in the target parking lot map, that is, the actual position of the target vehicle in the target parking lot map, can be calculated.

[0073] In one embodiment, the orientation information of the image acquisition device can also be obtained, and the orientation of the target vehicle in the coordinate system can be determined based on the orientation information of the image acquisition device. Based on the distance and orientation between the target vehicle and the image acquisition device, the offset of the target vehicle relative to the image acquisition device can be obtained, and based on the offset, the relative coordinates of the target vehicle in the target parking lot map, that is, the actual position of the target vehicle in the target parking lot map, can be calculated.

[0074] In step S150, the relative coordinates of the target vehicle in the target parking lot map are sent to the map navigation system to update the position of the target vehicle in the target parking lot map.

[0075] In the embodiment of the present application, the target image acquisition device and the map navigation system can communicate via the User Datagram Protocol (UDP), which is connectionless communication, so that the delay is low. The relative coordinates of the target vehicle in the target parking lot map are reported to the map navigation system once every preset time interval. When the user subscribes to the vehicle positioning data of the target vehicle through the client, the map navigation system can update the location of the target vehicle in the parking lot map displayed on the client.

[0076] In one embodiment, after the user subscribes to the vehicle location information from the map navigation system through a client with the corresponding application pre-installed, the user can receive 12 high-precision vehicle positioning data every second, and can display it in the parking lot map in the client, so that the vehicle's position changes can be intuitively seen for better vehicle navigation.

[0077] An embodiment of the present application provides a vehicle positioning method, including: acquiring an image of an area to be identified, the image of the area to be identified including a target vehicle, the image of the area to be identified being acquired by an image acquisition device; determining the absolute coordinates of the target vehicle in the world coordinate system based on a pre-constructed mapping relationship between a pixel coordinate system and a world coordinate system and the image of the area to be identified; acquiring the relative coordinates of a target image acquisition device in a target parking lot map; determining the relative coordinates of the target vehicle in the target parking lot map based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system; and sending the relative coordinates of the target vehicle in the target parking lot map to a map navigation system to update the position of the target vehicle in the target parking lot map. In an embodiment of the present application, the vehicle positioning method can be implemented by a target image acquisition device. The vehicle is positioned through the visual positioning technology of the target image acquisition device, and the current position of the vehicle is directly converted to the position in the parking lot map. There is no need for a parking lot map for positioning, which reduces the time delay problem of information transmission, and can improve the high real-time performance of vehicle positioning. The conversion relationship between the pixel coordinate system and the world coordinate system is directly used to realize the conversion of the vehicle position in the image and the map. There is no need for the map navigation system to convert again, which can improve the accuracy and efficiency of vehicle positioning, achieve a "what you see is what you get" effect, and can update the position of the target vehicle in the target parking lot map in real time.

[0078] See also Figure 3 , the mapping relationship is constructed in the following way:

[0079] In step S210, a calibration image is obtained, wherein the calibration image includes a calibration reference object.

[0080] In step S220, the coordinate information of each corner point of the calibration reference object is obtained;

[0081] In step S230, the target image acquisition device is calibrated based on the coordinate information of each corner point of the calibration reference object;

[0082] In step S240, the internal and external parameters of the calibrated target image acquisition device are obtained;

[0083] In step S250, a mapping relationship from the pixel coordinate system to the world coordinate system is constructed based on the internal and external parameters.

[0084] Optionally, the findCirckesGrid function in the OpenCV graphics library can be called to extract multiple feature points of the calibration reference object to obtain a feature point set. Based on the feature point set, the calibrateCamera function in the OpenCV graphics library can be called to perform linear optimization on the feature points in the feature point set to obtain the calibrated internal and external parameters. The internal and external parameters at least include internal parameters (such as camera focal length, principal point position and distortion parameters) and external parameters (such as rotation and translation matrices of the camera). The calibration reference object is subjected to distortion correction by using the internal and external parameters, and the coordinates of each feature point after distortion correction are obtained as its image coordinates in the pixel coordinate system. Then, the world coordinates of the feature points of the calibration reference object in the world coordinate system can be obtained. Based on the image coordinates and the world coordinates, a transformation matrix between the image coordinates and the world coordinates can be constructed as a mapping relationship.

[0085] See also Figure 4 , based on a pre-constructed mapping relationship between a pixel coordinate system and a world coordinate system, determining the absolute coordinates of the target vehicle in the world coordinate system, including:

[0086] In step S310, a vehicle profile feature of a target vehicle is obtained;

[0087] In step S320, a vehicle identification frame of the target vehicle is established based on the vehicle contour features;

[0088] In step S330, the image coordinates of the center point of the vehicle identification frame in the pixel coordinate system are determined;

[0089] In step S340 , based on the mapping relationship, the image coordinates are converted into absolute coordinates of the target vehicle in the world coordinate system.

[0090] Optionally, the image to be identified can be input into a pre-built target detection model, such as a YOLO model, for detection to determine whether the target vehicle exists, and when it is determined that the target vehicle exists, the vehicle contour features of the target vehicle can be identified, and the vehicle identification frame of the target vehicle can be obtained through the chassis regression model, and the pixel coordinate values ​​of each corner point of the vehicle identification frame can be obtained. Based on the pixel coordinate values ​​between each corner point, the pixel coordinate value of the center point of the vehicle identification frame is calculated and used as the image coordinate of the target vehicle in the pixel coordinate system. Then, based on the mapping relationship between the pre-built pixel coordinate system and the world coordinate system, the image coordinates can be converted to world coordinates to obtain the absolute coordinates of the target vehicle in the world coordinate system.

[0091] See also Figure 5In one embodiment of the present application, based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system, the relative coordinates of the target vehicle in the target parking lot map are determined, including:

[0092] In step S410, based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system, the offset of the target vehicle is determined;

[0093] In step S420 , the relative coordinates of the target vehicle in the target parking lot map are calculated based on the offset and the absolute coordinates of the target vehicle in the world coordinate system.

[0094] Optionally, by detecting the target vehicle in the collected image of the area to be identified, the distance between the target vehicle and the target image acquisition device is determined based on the absolute coordinates of the target vehicle in the world coordinate system and the relative coordinates of the target image acquisition device in the target parking lot map. Based on the distance, the offset of the target vehicle relative to the target image acquisition device, that is, the offset coordinates, can be obtained, and then the relative coordinates of the target vehicle in the target parking lot map can be calculated by combining the offset coordinates and the absolute coordinates of the target image acquisition device in the world coordinate system through translation, rotation and scaling. As an implementation method, the distance between the target image acquisition device and the target vehicle can be determined by determining the position of the target image acquisition device in the image coordinate system and converting it into the absolute coordinates in the world coordinate system based on the mapping relationship, and then, according to the absolute coordinates of the target vehicle in the world coordinate system, the distance between the two can be determined.

[0095] In one embodiment, the orientation information of the image acquisition device may also be obtained, and the orientation information may specifically include the pitch angle and azimuth angle of the target image acquisition device when capturing the image of the area to be identified. Based on the pitch angle, azimuth angle, and the distance between the target vehicle and the target image acquisition device, the offset of the target vehicle relative to the target image acquisition device, i.e., the offset coordinates, may be obtained, and then the relative coordinates of the target vehicle in the target parking lot map may be calculated by combining the offset coordinates and the absolute coordinates of the target image acquisition device in the world coordinate system through translation, rotation, and scaling.

[0096] Exemplarily, the distance is D, the pitch angle is a, and the direction angle is b, then the offset coordinates (x1, y1, z1) can be expressed as, x1 = D*sina, y1 = D*cosb, z1 = D*sina*cosb. For example, the absolute coordinates of the target image acquisition device in the world coordinate system are (x2, y2, z2), then combined with the offset coordinates, the relative coordinates (x3, y3, z3) of the target vehicle in the target parking lot map can be calculated. That is, x3 = x1 + x2, y3 = y1 + y2, z3 = z1 + z2.

[0097] Optionally, a conversion matrix between the relative coordinate system and the absolute coordinate system can be established by calibrating the reference object. The conversion matrix includes an offset, that is, a rotation amount and a translation amount. Based on the conversion matrix, the absolute coordinates of the target vehicle are converted into relative coordinates in the relative coordinate system.

[0098] In one embodiment of the present application, after acquiring the image of the area to be identified, the following steps are included:

[0099] Tracking a target vehicle in the image of the area to be identified to obtain current vehicle driving track information of the target vehicle, where the current vehicle driving track information includes vehicle information;

[0100] The current vehicle driving trajectory information is reported to the map navigation system, so that the map navigation system updates the cached vehicle driving trajectory information of the target vehicle to the current vehicle driving trajectory information based on the vehicle information.

[0101] The vehicle information may specifically include one or any combination of a license plate number, a vehicle color, a vehicle type, and a vehicle model.

[0102] The vehicle driving trajectory information may specifically include the ID of the target image acquisition device, the vehicle ID, the vehicle information, and the current location of the vehicle, that is, its relative coordinates in the parking lot map.

[0103] Optionally, the target image acquisition device can detect the vehicle information of the target vehicle in each image of the area to be identified in real time, calculate its relative coordinates in the parking lot map, and track the target vehicle, integrating the obtained vehicle information and relative coordinate information into the current driving trajectory information of the target vehicle. The current driving trajectory information is reported to the map navigation system by asynchronous message communication. After the map navigation system obtains the current driving trajectory information, it can first query the cached vehicle driving trajectory information based on vehicle information, such as vehicle number, vehicle ID, etc., and compare it with the current vehicle driving trajectory information. If the current vehicle driving trajectory information is sent later than the cached vehicle driving trajectory information, the cached vehicle driving trajectory information can be updated to the current vehicle driving trajectory information, thereby updating the icon position of the target vehicle in the parking lot map. Otherwise, the current vehicle driving trajectory information is discarded. So that the map navigation system only caches the latest position of each vehicle.

[0104] It should be noted that the target image acquisition device can calculate the relative coordinates of the current target vehicle in the parking lot map once every 80 milliseconds, that is, it can send the current vehicle driving trajectory information to the map navigation system once every 80 milliseconds.

[0105] Furthermore, the current vehicle driving trajectory information is reported to the map navigation system, including:

[0106] The current vehicle driving trajectory information is reported to the map navigation system. The current vehicle driving trajectory information includes a serial number, which is used to characterize the sending order of different vehicle driving trajectory information, so that the map navigation system determines whether to update the cached vehicle driving trajectory information of the target vehicle based on the sending order.

[0107] Since each reported vehicle driving trajectory information is accompanied by a corresponding serial number, the serial number can determine the order of the reported vehicle driving trajectory information. Therefore, by comparing the serial number of the current vehicle driving trajectory information with the serial number of the cached vehicle driving trajectory information, it can be determined whether the sending order of the current vehicle driving trajectory information is later than the cached vehicle driving trajectory information. If so, the cached vehicle driving trajectory information can be updated to the current vehicle driving trajectory information, thereby updating the icon position of the target vehicle in the parking lot map. Otherwise, the current vehicle driving trajectory information is discarded.

[0108] Exemplarily, for the target vehicle, each time a vehicle driving trajectory information is generated, the previous vehicle driving trajectory information can be increased by 1, and the initial serial number can be 1. For example, if the serial number of the previous vehicle driving trajectory information is 1111, then the serial number of the current vehicle driving trajectory information is 11111. The serial number of the vehicle driving trajectory information sent for the first time can be 1. By comparing the difference between the number of characters of different serial numbers, their order can be determined.

[0109] In the embodiment of the present application, the vehicle is positioned through the visual positioning technology of the target image acquisition device, and the current position of the vehicle is directly converted to the position in the parking lot map without the need for information transmission, which can improve the high real-time performance of vehicle positioning. The conversion relationship between the pixel coordinate system and the world coordinate system is directly used to realize the conversion of the vehicle position in the image and the map, without the need for the map navigation system to convert again, which can improve the accuracy and efficiency of vehicle positioning.

[0110] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0111] In one embodiment, a vehicle navigation method is provided, the vehicle navigation method comprising:

[0112] During vehicle navigation, the yaw distance of the target vehicle is determined based on the relative coordinates of the target vehicle in the target parking lot map and the coordinates of the predicted trajectory points in the current navigation route, and the relative coordinates of the target vehicle in the target parking lot map are determined based on the above-mentioned vehicle positioning method;

[0113] When the deviation distance is greater than the preset distance, the navigation route is replanned according to the relative coordinates of the target vehicle in the target parking lot map and the navigation end point.

[0114] In this way, it is possible to quickly and accurately determine whether the vehicle is yawed based on the real-time positioning pushed by the target image acquisition device, and re-plan the navigation route when the vehicle yaws to achieve the effect of rapid deviation correction.

[0115] In one embodiment, a navigation route can be planned based on a navigation start point and a navigation end point, wherein the navigation start point can be a location point input by a user or a location point where a target vehicle is located, and the navigation end point can be a location point input by a user. Figure 6During the vehicle navigation process, the vehicle may deviate. For example, when the vehicle is at an intersection, it deviates due to taking the wrong route. The deviation distance of the target vehicle can be determined based on the relative coordinates of the target vehicle in the target parking lot map (the coordinates of the actual vehicle driving trajectory points) and the coordinates of the predicted trajectory points in the current navigation route (the coordinates of the position points corresponding to the navigation vehicle logo), wherein the predicted trajectory points can be determined every preset time period, and the predicted trajectory points can be determined based on the navigation trajectory of the current navigation route, the driving speed of the target vehicle, and the preset time period. When the deviation distance is greater than the preset distance, it can be determined that the vehicle has deviated (for example, it has taken the wrong route). Therefore, the navigation route can be replanned based on the relative coordinates of the target vehicle in the target parking lot map and the navigation end point, thereby achieving the effect of rapid deviation correction. The preset distance is, for example, 3 meters, 5 meters, etc. Of course, the preset distance can also be other values, which are not specifically limited here.

[0116] In the embodiment of the present application, the vehicle navigation method can be implemented by a map navigation system.

[0117] In one embodiment, a vehicle positioning device is provided, which corresponds one-to-one with the vehicle positioning method in the above embodiment. Figure 7 As shown, the vehicle positioning device includes an image acquisition unit 10, an absolute coordinate determination unit 20, an information acquisition unit 30, a relative coordinate determination unit 40 and a position update unit 50. Each functional module is described in detail as follows:

[0118] An image acquisition unit 10 is used to acquire an image of the area to be identified, the image of the area to be identified includes a target vehicle, and the image of the area to be identified is acquired by a target image acquisition device;

[0119] An absolute coordinate determination unit 20, configured to determine the absolute coordinates of the target vehicle in the world coordinate system based on a pre-constructed mapping relationship between the pixel coordinate system and the world coordinate system and the image of the area to be identified;

[0120] An information acquisition unit 30, used to acquire the relative coordinates of the target image acquisition device in the target parking lot map;

[0121] A relative coordinate determination unit 40, for determining the relative coordinates of the target vehicle in the target parking lot map based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system;

[0122] The position updating unit 50 is used to send the relative coordinates of the target vehicle in the target parking lot map to the map navigation system to update the position of the target vehicle in the target parking lot map.

[0123] In one embodiment of the present application, the absolute coordinate determination unit 20 is further used to:

[0124] Acquire a calibration image, wherein the calibration image includes a calibration reference object;

[0125] Obtain the coordinate information of each corner point of the calibration reference object;

[0126] Calibrate the target image acquisition device based on the coordinate information of each corner point of the calibration reference object;

[0127] Acquire the internal and external parameters of the calibrated target image acquisition device;

[0128] Based on the internal and external parameters, a mapping relationship from the pixel coordinate system to the world coordinate system is constructed.

[0129] In one embodiment of the present application, the absolute coordinate determination unit 20 is further used to:

[0130] Acquire vehicle contour features of the target vehicle based on the image of the area to be identified;

[0131] Based on the vehicle contour features, a vehicle identification frame of the target vehicle is established;

[0132] Determine the image coordinates of the center point of the vehicle identification frame in the pixel coordinate system;

[0133] Based on the mapping relationship, the image coordinates are converted into the absolute coordinates of the target vehicle in the world coordinate system.

[0134] In one embodiment of the present application, the relative coordinate determination unit 40 is further used for:

[0135] Determine the offset of the target vehicle based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system;

[0136] Based on the offset and the absolute coordinates of the target vehicle in the world coordinate system, the relative coordinates of the target vehicle in the target parking lot map are calculated.

[0137] In one embodiment of the present application, the vehicle driving trajectory information updating unit is used to:

[0138] Tracking a target vehicle in the image of the area to be identified to obtain current vehicle driving track information of the target vehicle, where the current vehicle driving track information includes vehicle information;

[0139] The current vehicle driving trajectory information is reported to the map navigation system, so that the map navigation system updates the cached vehicle driving trajectory information of the target vehicle to the current vehicle driving trajectory information based on the vehicle information.

[0140] In one embodiment of the present application, the vehicle driving trajectory information updating unit is further used to:

[0141] The current vehicle driving trajectory information is reported to the map navigation system. The current vehicle driving trajectory information includes a serial number, which is used to characterize the sending order of different vehicle driving trajectory information, so that the map navigation system determines whether to update the cached vehicle driving trajectory information of the target vehicle based on the sending order.

[0142] In one embodiment of the present application, the target image acquisition device communicates with the map navigation system via the User Datagram Protocol, and reports the relative coordinates of the target vehicle in the target parking lot map to the map navigation system once at a preset interval, so that the map navigation system can update the location of the target vehicle in the parking lot map.

[0143] In the embodiment of the present application, the vehicle is positioned through the visual positioning technology of the target image acquisition device, and the current position of the vehicle is directly converted to the position in the parking lot map. There is no need for the parking lot map to perform positioning, which reduces the time delay problem of information transmission, and can improve the high real-time performance of vehicle positioning. The conversion relationship between the pixel coordinate system and the world coordinate system is directly used to realize the conversion of the vehicle position in the image and the map. There is no need for the map navigation system to convert again, which can improve the accuracy and efficiency of vehicle positioning.

[0144] The specific definition of the vehicle positioning device can be found in the definition of the vehicle positioning method above, which will not be repeated here. Each module in the above-mentioned vehicle positioning device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0145] In one embodiment, a vehicle navigation device is provided, which corresponds to the vehicle navigation method in the above embodiment. The vehicle navigation device includes a deviation distance determination unit and a navigation route planning unit. Each functional module is described in detail as follows:

[0146] A deviation distance determination unit is used to determine the deviation distance of the target vehicle according to the relative coordinates of the target vehicle in the target parking lot map and the coordinates of the predicted trajectory points in the current navigation route during the vehicle navigation process, wherein the relative coordinates of the target vehicle in the target parking lot map are determined according to the above-mentioned vehicle positioning method;

[0147] The navigation route planning unit is used to re-plan the navigation route according to the relative coordinates of the target vehicle in the target parking lot map and the navigation end point when the deviation distance is greater than the preset distance.

[0148] The specific definition of the vehicle navigation device can be found in the definition of the vehicle navigation method above, which will not be repeated here. Each module in the above-mentioned vehicle navigation device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0149] In one embodiment, a computer device is provided. The computer device may be a terminal device, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, and a network interface 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 readable storage medium. The readable storage medium stores computer-readable instructions. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, a vehicle positioning method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0150] In an embodiment of the present application, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the steps of the vehicle positioning method described above are implemented.

[0151] In an embodiment of the application, a readable storage medium is provided, which stores computer-readable instructions. When the computer-readable instructions are executed by a processor, the steps of the vehicle positioning method as described above are implemented.

[0152] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they may 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 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of 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), etc.

[0153] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0154] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A vehicle positioning method, characterized in that: The method comprises: Acquire an image of the area to be identified, the image of the area to be identified includes a target vehicle, and the image of the area to be identified is acquired by a target image acquisition device; Based on the pre-constructed mapping relationship between the pixel coordinate system and the world coordinate system and the image of the area to be identified, determining the absolute coordinates of the target vehicle in the world coordinate system; Obtaining the relative coordinates of the target image acquisition device in the target parking lot map; Determine the relative coordinates of the target vehicle in the target parking lot map based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system; The relative coordinates of the target vehicle in the target parking lot map are sent to a map navigation system to update the position of the target vehicle in the target parking lot map.

2. The vehicle positioning method according to claim 1, characterized in that: The mapping relationship is constructed in the following way: Acquire a calibration image, wherein the calibration image includes a calibration reference object; Obtaining coordinate information of each corner point of the calibration reference object; Calibrate the target image acquisition device based on the coordinate information of each corner point of the calibration reference object; Acquiring the calibrated internal and external parameters of the target image acquisition device; Based on the internal and external parameters, the mapping relationship from the pixel coordinate system to the world coordinate system is constructed.

3. The vehicle positioning method according to claim 1, characterized in that: The determining the absolute coordinates of the target vehicle in the world coordinate system based on the pre-constructed mapping relationship between the pixel coordinate system and the world coordinate system and the image of the area to be identified includes: Acquiring vehicle contour features of the target vehicle based on the image of the area to be identified; Based on the vehicle contour features, establishing a vehicle identification frame of the target vehicle; Determine the image coordinates of the center point of the vehicle identification frame in the pixel coordinate system; Based on the mapping relationship, the image coordinates are converted into the absolute coordinates of the target vehicle in the world coordinate system.

4. The vehicle positioning method according to claim 1, characterized in that: The determining the relative coordinates of the target vehicle in the target parking lot map based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system includes: Determining an offset based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system; Based on the offset and the absolute coordinates of the target vehicle in the world coordinate system, the relative coordinates of the target vehicle in the target parking lot map are calculated.

5. The vehicle positioning method according to claim 1, characterized in that: After the image of the area to be identified is obtained, the following steps are included: Tracking the target vehicle in the image of the area to be identified to obtain current vehicle driving track information of the target vehicle, wherein the current vehicle driving track information includes vehicle information; The current vehicle driving trajectory information is reported to the map navigation system, so that the map navigation system updates the cached vehicle driving trajectory information of the target vehicle to the current vehicle driving trajectory information based on the vehicle information.

6. The vehicle positioning method according to claim 5, characterized in that: The step of reporting the current vehicle driving trajectory information to the map navigation system includes: The current vehicle driving trajectory information is reported to the map navigation system, and the current vehicle driving trajectory information includes a serial number, and the serial number is used to characterize the sending order of different vehicle driving trajectory information, so that the map navigation system determines whether to update the cached vehicle driving trajectory information of the target vehicle based on the sending order.

7. The vehicle positioning method according to any one of claims 1 to 6, characterized in that: The target image acquisition device communicates with the map navigation system via a user datagram protocol and reports the relative coordinates of the target vehicle in the target parking lot map to the map navigation system once at a preset interval, so that the map navigation system can update the location of the target vehicle in the parking lot map.

8. A vehicle navigation method, characterized in that: The method comprises: During vehicle navigation, determining the yaw distance of the target vehicle according to the relative coordinates of the target vehicle in the target parking lot map and the coordinates of the predicted trajectory points in the current navigation route, wherein the relative coordinates of the target vehicle in the target parking lot map are determined according to the vehicle positioning method according to any one of claims 1 to 7; When the deviation distance is greater than a preset distance, the navigation route is replanned according to the relative coordinates of the target vehicle in the target parking lot map and the navigation end point.

9. A vehicle positioning device, characterized in that: The device comprises: An image acquisition unit, used for acquiring an image of the area to be identified, wherein the image of the area to be identified includes a target vehicle, and the image of the area to be identified is acquired by a target image acquisition device; An absolute coordinate determination unit, used to determine the absolute coordinates of the target vehicle in the world coordinate system based on a pre-constructed mapping relationship between the pixel coordinate system and the world coordinate system and the image of the area to be identified; An information acquisition unit, used to acquire the relative coordinates of the target image acquisition device in the target parking lot map; A relative coordinate determination unit, configured to determine the relative coordinates of the target vehicle in the target parking lot map based on the relative coordinates of the target image acquisition device in the target parking lot map and the absolute coordinates of the target vehicle in the world coordinate system; The position updating unit is used to send the relative coordinates of the target vehicle in the target parking lot map to the map navigation system to update the position of the target vehicle in the target parking lot map.

10. A vehicle navigation device, characterized in that: The device comprises: a yaw distance determination unit, used to determine the yaw distance of the target vehicle during vehicle navigation according to the relative coordinates of the target vehicle in the target parking lot map and the coordinates of the predicted trajectory points in the current navigation route, wherein the relative coordinates of the target vehicle in the target parking lot map are determined according to the vehicle positioning method according to any one of claims 1 to 7; The navigation route planning unit is used to re-plan the navigation route according to the relative coordinates of the target vehicle in the target parking lot map and the navigation end point when the deviation distance is greater than a preset distance.

Images