CN114371484A - Vehicle positioning method and device, computer equipment and storage medium - Google Patents

Vehicle positioning method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN114371484A
CN114371484A CN202210004892.7A CN202210004892A CN114371484A CN 114371484 A CN114371484 A CN 114371484A CN 202210004892 A CN202210004892 A CN 202210004892A CN 114371484 A CN114371484 A CN 114371484A
Authority
CN
China
Prior art keywords
dimensional code
vehicle
direction vector
position information
target direction
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210004892.7A
Other languages
Chinese (zh)
Inventor
刘新宇
赵彬
孙中辉
郝值
杨首辰
赵子健
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
FAW Jiefang Automotive Co Ltd
Original Assignee
FAW Jiefang Automotive Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by FAW Jiefang Automotive Co Ltd filed Critical FAW Jiefang Automotive Co Ltd
Priority to CN202210004892.7A priority Critical patent/CN114371484A/en
Publication of CN114371484A publication Critical patent/CN114371484A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G01S17/46—Indirect determination of position data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404—Methods for optical code recognition
    • G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
    • G06K7/1417—2D bar codes

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Electromagnetism (AREA)
  • General Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Toxicology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)

Abstract

The present application relates to a vehicle positioning method, apparatus, computer device, storage medium and computer program product. The method comprises the following steps: if the two-dimensional codes are detected through the laser radar, determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar; determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors; and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector. Utilize laser radar to obtain the two-dimensional code, through discerning and resolving the two-dimensional code, confirm the positional information of two-dimensional code, combine comparatively accurate relative position between vehicle and the two-dimensional code confirmed by laser radar again, calculate the vehicle position.

Description

Vehicle positioning method and device, computer equipment and storage medium
Technical Field
The present application relates to the field of vehicle positioning technologies, and in particular, to a vehicle positioning method and apparatus, a computer device, and a storage medium.
Background
In today's society, vehicles have become an indispensable vehicle for human beings. With the development of modern science and technology, unmanned vehicles gradually enter human lives. The unmanned vehicle is an intelligent vehicle which senses the surrounding environment of the vehicle by using a vehicle-mounted sensor, automatically plans a vehicle route and controls the vehicle to reach a preset target according to the road, vehicle position and obstacle information obtained by sensing.
Vehicle positioning is an indispensable technology in unmanned vehicles, and currently, vehicle positioning is performed by laying two-dimensional codes containing position information on the ground or deploying the two-dimensional codes on guide rails of a personal rapid transit system to position the position of a vehicle. But the two-dimensional code laid on the ground is worn, thereby affecting the positioning result of the vehicle. In addition, in the positioning process, the position information corresponding to the two-dimensional code scanned by the vehicle is directly used as the position information of the vehicle, and the vehicle is generally unlikely to be located at the position of the two-dimensional code, so that the vehicle positioning result is inaccurate.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device, a computer readable storage medium and a computer program product for obtaining an accurate positioning of a vehicle.
In a first aspect, the present application provides a vehicle localization method. The method is applied to a vehicle, the vehicle is provided with a laser radar, a two-dimensional code is arranged on the non-ground part of a lane where the vehicle runs, and the two-dimensional code carries the position information of the two-dimensional code; the method comprises the following steps:
if the two-dimensional codes are detected through the laser radar, determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar;
determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors;
and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector.
In one embodiment, the determining process of the target direction vector includes:
acquiring estimated position information of a vehicle at the current detection moment;
determining two-dimensional code estimated position information corresponding to each direction vector according to the estimated position information of the vehicle at the current detection moment;
and matching the two-dimensional code estimated position information corresponding to each direction vector with the position information of the two-dimensional code in the two-dimensional code information database, and taking the successfully matched direction vector as a target direction vector.
In one embodiment, a vehicle is provided with a camera; the determination process of the target direction vector comprises the following steps:
the method comprises the steps of taking pictures through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by shooting through the camera, identifying each successfully intercepted two-dimensional code image, and taking the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image as a target direction vector.
In one embodiment, a vehicle is provided with a camera; the determination process of the target direction vector comprises the following steps:
photographing through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by the camera, identifying each successfully intercepted two-dimensional code image, forming a first set by the direction vectors corresponding to the successfully intercepted two-dimensional code images, forming a second set by the direction vectors left after the first set is removed from all the direction vectors, and taking the direction vectors in the first set as target direction vectors;
obtaining estimated position information of a vehicle at the current detection time, determining two-dimensional code estimated position information corresponding to each direction vector in the second set according to the estimated position information of the vehicle at the current detection time, matching the two-dimensional code estimated position information corresponding to each direction vector in the second set with position information of two-dimensional codes in a two-dimensional code information database, and taking the successfully matched direction vector in the second set as a target direction vector.
In one of the embodiments, the vehicle is provided with a speedometer; the method for acquiring the estimated position information of the vehicle at the current detection moment comprises the following steps:
acquiring the running distance of the vehicle from the last detection time to the current detection time through the odometer;
and determining the estimated position information of the vehicle at the current detection time according to the actual position information of the vehicle at the last detection time, the driving direction and the driving distance of the vehicle at the last detection time.
In one embodiment, the two-dimensional code carries the direction information of the road where the two-dimensional code is located; after the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image is taken as the target direction vector, the method further comprises the following steps:
converting the two-dimensional code corresponding to each target direction vector into a front view through affine transformation based on the positions of three angle boxes in the two-dimensional code image corresponding to each target direction vector, and obtaining a rotation matrix corresponding to each target direction vector;
and determining the driving direction of the vehicle at the current detection moment according to the rotation matrix corresponding to each target direction vector and the road orientation information carried in the two-dimensional code image corresponding to each target direction vector.
In a second aspect, the present application further provides a vehicle positioning device. The device is installed on a vehicle, the vehicle is provided with a laser radar, a two-dimensional code is arranged on the non-ground part of a lane where the vehicle runs, and the two-dimensional code carries the position information of the two-dimensional code; the device comprises:
the first determining module is used for determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar if the two-dimensional code is detected through the laser radar;
the second determining module is used for determining the position information of the two-dimensional code corresponding to each target direction vector, and all the target direction vectors are determined from all the direction vectors;
a third determining module, configured to determine vehicle position information corresponding to each target direction vector according to the location information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determine actual position information of the vehicle at the current detection time according to the vehicle position information corresponding to each target direction vector
In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor realizes the following steps when executing the computer program:
if the two-dimensional codes are detected through the laser radar, determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar;
determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors;
and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
if the two-dimensional codes are detected through the laser radar, determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar;
determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors;
and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
if the two-dimensional codes are detected through the laser radar, determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar;
determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors;
and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector.
According to the vehicle positioning method, the vehicle positioning device, the computer equipment, the storage medium and the computer program product, if the two-dimensional codes are detected through the laser radar, the direction vector between the vehicle and each detected two-dimensional code is determined through the laser radar; determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors; and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector. The two-dimensional code is obtained by utilizing the characteristics of the laser radar different in reflectivity of different metals, the position information of the two-dimensional code is obtained by identifying and analyzing the two-dimensional code, and the vehicle position is calculated by adopting a particle filter algorithm in combination with the relative position between the vehicle determined by the laser radar and the two-dimensional code, which is relatively accurate.
Drawings
FIG. 1 is a diagram of an exemplary vehicle location method;
FIG. 2 is a schematic flow chart diagram of a vehicle location method in one embodiment;
FIG. 3 is a schematic diagram of a two-dimensional code deployment in one embodiment;
FIG. 4 is a schematic diagram of another embodiment of a two-dimensional code;
FIG. 5 is a schematic flow chart diagram of a vehicle location method in one embodiment;
FIG. 6 is a flowchart framework of a vehicle location method in one embodiment;
FIG. 7 is a schematic flow chart diagram of a vehicle location method in another embodiment;
FIG. 8 is a schematic flow chart diagram of a vehicle location method in yet another embodiment;
FIG. 9 is a block diagram showing the construction of a vehicle positioning apparatus according to an embodiment;
FIG. 10 is a diagram showing an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The vehicle positioning method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. The terminal 102 communicates with the server 104 through a network, and specifically, the image or the information of the detected two-dimensional code may be transmitted to the server 104, and the server 104 processes the detected two-dimensional code to obtain the position information of the vehicle. The data storage system may store two-dimensional code images or information that the server 104 needs to process. The data storage system may be integrated on the server 104, or may be located on the cloud or other network server. The terminal 102 is a device for acquiring a two-dimensional code image or information, and may include, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, logistics network devices, and the like, which have a laser radar. The server 104 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud computing services.
In one embodiment, as shown in fig. 2, a vehicle positioning method is provided, for example, when the method is applied to a server configured on a vehicle, the vehicle is provided with a laser radar, and a two-dimensional code is provided on a non-ground part of a lane where the vehicle is traveling, and the two-dimensional code carries location information of the two-dimensional code, and the method includes the following steps:
step 202, if the two-dimensional codes are detected through the laser radar, determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar;
firstly, the precondition for implementing the embodiment of the present application is a specific two-dimensional code deployment manner, which is shown in fig. 3, and includes that two-dimensional codes are deployed on both sides of a road without an isolation zone, and intervals and heights between all the two-dimensional codes are consistent, for example, the intervals are 20m, and the height is 1.5 m; two-dimensional codes are arranged on two sides of a road with an isolation belt and the isolation belt, and the intervals and the heights of all the two-dimensional codes are consistent. The specification of all two-dimensional codes is uniform, the front side and the back side of the two-dimensional codes are attached to a metal plate, a blank is arranged in the middle of each two-dimensional code, a metal with a smooth surface is plated on the surface of the blank area, and the area is a characteristic mark of the two-dimensional code, for example, as shown in fig. 4, the specification of the two-dimensional code is 20cm by 20cm, and a blank area with the size of 5cm by 5cm is arranged in the middle of the two-dimensional code. It can be understood that the coating of the characteristic region is to facilitate the detection of the two-dimensional code by the laser radar, so the coating metal needs to be selected to be smooth metal with high reflectivity.
The two-dimensional code carries information related to vehicle positioning, such as position information of a two-dimensional code deployment place and information of a road where the two-dimensional code is deployed (road orientation, road curvature, road gradient, road speed limit and the like), and the related information can be obtained by identifying the two-dimensional code. And to avoid confusion in the subsequent use of these pieces of relevant information, all the pieces of relevant information are expressed with reference to the same coordinate, for example, in a common northeast coordinate system (a rectangular coordinate system is formed by selecting a position where the zero point of the geographic position, i.e., the position where the longitude, the latitude, and the altitude are both 0, the z-axis coincides with the normal of the ellipsoid, and upward is positive (the sky direction), y coincides with the minor half axis of the ellipsoid (the north direction), and the x-axis coincides with the major half axis of the earth ellipsoid (the east direction)), the position can be expressed by a point (x, y, z) in the northeast coordinate system (also can be regarded as a position vector), and the road orientation can be expressed by an euler angle (pitch, roll, yaw) relative to the northeast coordinate system.
It should be noted that, for whether the two-dimensional code is vertically deployed on a road or obliquely deployed, the two-dimensional code is in an isolation zone or on two sides of the isolation zone; the specific material of the two-dimensional code coating; the information such as the type of the related information carried by the two-dimensional code is not specifically limited in this embodiment.
Specifically, in the vehicle driving process, laser is periodically emitted by the laser radar, then the laser can be reflected after encountering a metal coating of the two-dimensional code feature identification position, and the direction and distance information between the detected two-dimensional code and the laser radar can be known by the reflected signal, so that the direction vector from the laser radar (vehicle) to the two-dimensional code at the current detection moment can be obtained, wherein the moment when the laser radar receives the reflected laser is the current detection moment, and the laser radar is not repeated. Based on the above process, the direction vectors between the vehicle and all the detected two-dimensional codes can be obtained.
Step 204, determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors;
the target direction vector is a direction vector which can be used for acquiring a relative position between the two-dimensional code and the vehicle. It can be understood that the two-dimensional code detected by the laser radar is not all the two-dimensional code position information that can be obtained, because in actual conditions, there are various errors, for example, the two-dimensional code is sheltered from to cause that the position information carried by the two-dimensional code cannot be identified, the laser radar has a fault to cause that the detected two-dimensional code is not accurate enough, and the like.
Specifically, estimated position information of the two-dimensional codes can be obtained, the estimated position information of each two-dimensional code is matched with a tracking list of the two-dimensional codes, if two-dimensional codes with approximate position information need to be found in the tracking list, the two-dimensional codes are successfully matched, the position information of the two-dimensional codes can be obtained, and direction vectors corresponding to the two-dimensional codes which can be successfully matched are the target direction vectors which can be used for calculating the vehicle position information.
The tracking list of the two-dimensional codes is created to reduce the calculation amount of the two-dimensional code matching process, and is a list of two-dimensional codes that can be successfully tracked in several consecutive detections. It can be understood that the detection frequency of the laser radar is definitely very high, and by combining the deployment condition of the two-dimensional code on the actual road and the speed of the vehicle, most of the two-dimensional codes detected at the last detection time and the current detection time of the laser radar are definitely repeated, so that when the two-dimensional codes detected at the current detection time are matched, the two-dimensional codes can be directly compared with a tracking list of the two-dimensional codes formed at the detection time, so that the position information of most of the two-dimensional codes can be found in a very short time, and most of target direction vectors are determined. In addition, after all target direction vectors at the current detection time are determined, the tracking list of the two-dimensional code can be updated according to the position information of the two-dimensional code corresponding to the determined target direction vectors, wherein the tracking list comprises the position information of the two-dimensional code which is added and the position information of the two-dimensional code which is not tracked successfully for several times is deleted.
And step 206, determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection time according to the vehicle position information corresponding to each target direction vector.
The position information of the two-dimensional code refers to position coordinates of a place where the two-dimensional code is located, so that the position coordinates of a road where the two-dimensional code is located are represented, and when the vehicle runs to the position, the position information of the vehicle can be obtained. For convenience of a subsequent calculation process, the position coordinates of the location where the two-dimensional code is located can be regarded as a vector pointing to the position coordinates from the origin of coordinates, and the vector is stored in the two-dimensional code as the location information of the two-dimensional code. That is, the position information of the vehicle can be calculated from the positional information of the two-dimensional code and the relative vector (direction vector) of the position between the two-dimensional code and the vehicle.
Specifically, the position of a vehicle can be calculated by each target direction vector, and then the vehicle positions obtained by each target direction vector are averaged to determine the actual position information of the vehicle. Actual position information P of the vehicle at the current detection timetThe calculation formula of (a) is as follows:
Figure BDA0003455153070000081
wherein n represents the number of target direction vectors; xnThe position information of the two-dimensional code corresponding to each target direction vector is obtained; t isnFor each target direction vector; f. ofnError of the lidar, i.e. error of the direction vector of the target, fnDistance s from laser radar to two-dimensional codenThe positive correlation, the specific direction and size, is related to the parameters of the lidar itself.
According to the vehicle positioning method provided by the embodiment, if the two-dimensional codes are detected through the laser radar, the direction vector between the vehicle and each detected two-dimensional code is determined through the laser radar; determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors; and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector. In this embodiment, adopt the laser radar of high accuracy to detect the two-dimensional code to through the position information of the whereabouts of a plurality of two-dimensional codes that the radar detected and the relative position between vehicle and each two-dimensional code, confirm the actual position of vehicle, when obtaining more accurate vehicle position, also can not cause wearing and tearing to the two-dimensional code.
In combination with the content of the above embodiments, in one embodiment, referring to fig. 5, the process of determining the target direction vector includes:
step 502, obtaining estimated position information of a vehicle at the current detection moment;
the estimated position information of the vehicle at the current detection time is obtained by predicting the actual position information of the vehicle at the last detection time. When the vehicle is started, the actual position information of the vehicle is obtained by calculating the position of the two-dimensional code obtained by identifying the two-dimensional code detected by the laser radar at the initial detection time, and then the initial vehicle position information can be determined iteratively through a plurality of detection cycles by using a Kalman filtering algorithm, and is used as the actual position information of the vehicle at the first detection time and used as the calculation basis of the estimated position information of the vehicle at the second detection time.
Step 504, determining two-dimensional code estimated position information corresponding to each direction vector according to the estimated position information of the vehicle at the current detection time;
according to the definition of the direction vector, on the premise that the direction vector is known, the position of the two-dimensional code and the position of the vehicle can be known to be one. Therefore, under the condition that the position information of the two-dimensional code is not determined, the position information of the two-dimensional code can be estimated through the estimated position information and the direction vector of the vehicle. From P'tEstimated position information T representing the vehicle at the current detection timenRepresenting the direction vector corresponding to the two-dimensional code, the estimated position information X 'of the two-dimensional code'nThe calculation formula of (c) may be as follows:
X′n＝P′t+Tn
and 506, matching the two-dimensional code estimated position information corresponding to each direction vector with the position information of the two-dimensional code in the two-dimensional code information database, and taking the successfully matched direction vector as a target direction vector.
The two-dimension code information database is a database for storing all two-dimension codes and all information carried by the two-dimension codes, so that the estimated position information of the two-dimension codes can be matched with the position information of each two-dimension code in the two-dimension code information database without difficulty. And the successfully matched target direction vector can simultaneously determine the position information of the two-dimensional code corresponding to the target direction vector. Specifically, when matching the estimated position information of the two-dimensional code with the position information of each two-dimensional code in the two-dimensional code information database, a difference between the estimated position information of the two-dimensional code and the position information of each two-dimensional code is calculated, for example, the estimated position information of the two-dimensional code is (x)0,y0,z0) The position information of the first two-dimensional code is (x)1,y1,z1) The concrete formula is as follows:
Figure BDA0003455153070000091
and selecting the position information of the two-dimensional code with the minimum difference with the estimated position information of the two-dimensional code, wherein the difference value is within a preset range, the two-dimensional code finds the position information of one pair, and the direction vector corresponding to the two-dimensional code is taken as the target direction vector.
The vehicle positioning method provided by the embodiment, the determining process of the target direction vector, includes: acquiring estimated position information of a vehicle at the current detection moment; determining two-dimensional code estimated position information corresponding to each direction vector according to the estimated position information of the vehicle at the current detection moment; and matching the two-dimensional code estimated position information corresponding to each direction vector with the position information of the two-dimensional code in the two-dimensional code information database, and taking the successfully matched direction vector as a target direction vector. The two-dimensional code is obtained by utilizing the characteristics of the laser radar different in reflectivity of different metals, the position information of the two-dimensional code is obtained by identifying and analyzing the two-dimensional code, and the vehicle position is calculated by adopting a particle filter algorithm in combination with the relative position between the vehicle determined by the laser radar and the two-dimensional code, which is relatively accurate.
In combination with the above embodiments, in one embodiment, a vehicle is provided with a camera; the determination process of the target direction vector comprises the following steps:
the method comprises the steps of taking pictures through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by shooting through the camera, identifying each successfully intercepted two-dimensional code image, and taking the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image as a target direction vector.
At the moment when the laser radar detects the two-dimensional code, the camera can be triggered to photograph all the two-dimensional codes, and the obtained picture is used as a two-dimensional code picture at the current detection moment; and identifying the two-dimensional code image to obtain all information carried by the two-dimensional code.
It should be noted that, according to the direction vector of the two-dimensional code and the photographing parameter information of the camera itself, the position of the two-dimensional code corresponding to the direction vector is projected into the photo, and the corresponding two-dimensional code image is cut to obtain the two-dimensional code image. In addition, generally, the camera and the laser radar can be installed at the same position of the vehicle, so that the relative distance between the camera and the laser radar is not available, or the relative distance is small and can be ignored, when the direction vector of the two-dimensional code is used for projection, the error is small, and projection can be directly performed, but when the camera and the laser radar are installed at a certain distance, the position relative vector between the camera and the laser radar needs to be referred to, and the position of the two-dimensional code is projected. In combination with the range of the laser radar and the shooting range of the camera, not all the two-dimensional codes detected by the laser radar can find corresponding two-dimensional code images in the pictures shot by the camera, so that only the direction vectors which can find the corresponding two-dimensional code images and can successfully identify the two-dimensional code images need to be used as target direction vectors.
According to the vehicle positioning method provided by the embodiment, the camera is used for shooting, the two-dimensional code image corresponding to each direction vector is intercepted from the image shot by the camera, each successfully intercepted two-dimensional code image is identified, and the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image is used as the target direction vector. The two-dimensional code is obtained by utilizing the characteristics of the laser radar different in reflectivity of different metals, the position information of the two-dimensional code is obtained by identifying and analyzing the two-dimensional code, and the vehicle position is calculated by adopting a particle filter algorithm in combination with the relative position between the vehicle determined by the laser radar and the two-dimensional code, which is relatively accurate.
In combination with the above embodiments, in one embodiment, a vehicle is provided with a camera; the determination process of the target direction vector comprises the following steps:
photographing through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by the camera, identifying each successfully intercepted two-dimensional code image, forming a first set by the direction vectors corresponding to the successfully intercepted two-dimensional code images, forming a second set by the direction vectors left after the first set is removed from all the direction vectors, and taking the direction vectors in the first set as target direction vectors;
obtaining estimated position information of a vehicle at the current detection time, determining two-dimensional code estimated position information corresponding to each direction vector in the second set according to the estimated position information of the vehicle at the current detection time, matching the two-dimensional code estimated position information corresponding to each direction vector in the second set with position information of two-dimensional codes in a two-dimensional code information database, and taking the successfully matched direction vector in the second set as a target direction vector.
In the present embodiment, it is considered that the range of the laser radar is greater than the distance at which the camera effectively recognizes the two-dimensional code, so that not all of the two-dimensional codes detected by the laser radar are necessarily recognized by the camera. The direction vectors corresponding to all the two-dimensional codes detected by the laser radar are a total set, the number of the direction vectors in the total set is m, the number of the target direction vectors in the first set is n, and the number of the direction vectors in the second set is m-n.
The embodiment provides a method for determining the target direction vector with higher accuracy by combining with an actual application scene. Firstly, in terms of purpose, the purpose of determining the target direction vector is to obtain accurate location information of the two-dimensional code for example, and then calculate the actual location information of the vehicle, so it is easy to understand that the more target direction vectors are determined, the more location information of the two-dimensional code can be correspondingly used to participate in the calculation. And combining two modes of identifying the two-dimension code image and matching the two-dimension code image with a two-dimension code information database to screen out more target direction vectors.
Specifically, referring to fig. 6, if the laser radar scans the feature identifier, a direction vector T from the vehicle to the two-dimensional code is obtainedn(ii) a Using a camera to take a picture according to the direction vector T of the two-dimensional codenAnd projecting the position of the two-dimensional code into the photo, and cutting the corresponding two-dimensional code image. Then, identifying the positions of three corner boxes of the two-dimensional code in the cut image to obtain the position information of the two-dimensional code; when no image or two-dimensional code corresponding to the two-dimensional code can not be normally identified, judging whether the two-dimensional code is in the tracking list or not according to the estimated position information of the two-dimensional code, if so, indicating that the two-dimensional code really exists, and acquiring the position information of the two-dimensional code. If the corresponding two-dimensional code image is not found and the matching is not successful in the tracking list, the laser radar is indicated to have some faults or clutter, the signal is ignored, the corresponding direction vector is not adopted any more, and the laser scanning is returned to continue.
It should be noted that, due to other traffic participants and obstacles on the road, the two-dimensional code identified by the camera may be blocked, which results in being unable to identify; if wanting to discern clearly the two-dimensional code and need the distance nearer, it is less to use the camera discernment alone to lead to the two-dimensional code quantity of discerning to be less, the information that can be used to the calculation is less, the positioning accuracy and the robustness that obtain are all relatively poor, and laser radar's range finding distance is far away, the two-dimensional code quantity that can obtain the information through the matching is more, the two-dimensional code information that obtains through the tracking matching is more accurate, the vehicle position of calculating from this is more accurate, so establish two-dimensional code tracking list.
In the vehicle positioning method provided by this embodiment, a camera is used for photographing, a two-dimensional code image corresponding to each direction vector is captured from an image captured by the camera, each successfully captured two-dimensional code image is identified, direction vectors corresponding to the successfully captured and successfully identified two-dimensional code images form a first set, direction vectors remaining after the first set is removed from all direction vectors form a second set, and the direction vectors in the first set are all used as target direction vectors; obtaining estimated position information of a vehicle at the current detection time, determining two-dimensional code estimated position information corresponding to each direction vector in the second set according to the estimated position information of the vehicle at the current detection time, matching the two-dimensional code estimated position information corresponding to each direction vector in the second set with position information of two-dimensional codes in a two-dimensional code information database, and taking the successfully matched direction vector in the second set as a target direction vector. The two-dimensional code is obtained by utilizing the characteristics of the laser radar, which are different in reflectivity of different metals, and the position information of the two-dimensional code is obtained by identifying and analyzing the two-dimensional code, so that the influence caused by errors can be better reduced, and the positioning precision and robustness are improved.
In connection with the above embodiment, with reference to fig. 7, the vehicle is provided with a odometer; the method for acquiring the estimated position information of the vehicle at the current detection moment comprises the following steps:
step 702, acquiring a running distance of a vehicle from a last detection time to a current detection time through a milemeter;
wherein the driving distance of the vehicle is determined by a difference between a reading of the odometer at the last detection time and a reading at the current detection time. In other embodiments, the driving distance from the last detection time to the current detection time of the vehicle can be obtained through other acceleration or mileage sensors.
Step 704, determining the estimated position information of the vehicle at the current detection time according to the actual position information of the vehicle at the last detection time, the driving direction and the driving distance of the vehicle at the last detection time.
The actual position information of the vehicle at the last detection time and the driving direction of the vehicle at the last detection time can be obtained at the current detection time, and the driving route of the vehicle can be ideally a straight line due to the fact that the duration between the two detection times is short, so that the estimated position information of the vehicle at the current detection time can be calculated through the following formula:
P′t＝Pt-1+St·Ht-1
wherein S istThe distance traveled by the vehicle from the last detection time to the current detection time, Ht-1The driving direction of the vehicle at the last detection moment.
According to the method provided by the embodiment of the application, the running distance from the last detection time to the current detection time of the vehicle is obtained through the odometer; and determining the estimated position information of the vehicle at the current detection time according to the actual position information of the vehicle at the last detection time, the driving direction and the driving distance of the vehicle at the last detection time. The estimated position information of the two-dimensional code is determined through the relative position relation between the vehicle and the two-dimensional code embodied by the direction vector, so that the accurate target direction vector is determined, and the positioning precision and robustness are improved.
With reference to the content of the above embodiment, in one embodiment, the two-dimensional code carries the direction information of the road where the two-dimensional code is located; referring to fig. 8, after the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image is taken as the target direction vector, the method further includes:
step 802, converting the two-dimensional code corresponding to each target direction vector into a front view through affine transformation based on the positions of three angle boxes in the two-dimensional code image corresponding to each target direction vector, and obtaining a rotation matrix corresponding to each target direction vector;
affine transformation, also called affine mapping, refers to a process in which, in geometry, one vector space is linearly transformed once and then translated into another vector space. An affine transformation is a linear transformation between two-dimensional coordinates to two-dimensional coordinates. It keeps the 'straightness' (straight lines are still straight lines after transformation) and 'parallelism' (relative position relation between two-dimensional graphs is kept unchanged, parallel lines are still parallel lines, and position sequence of points on the straight lines is unchanged). An arbitrary affine transformation can be represented in the form of a multiplication by a matrix (linear transformation) plus a vector (translation). The rotation matrix may represent a transformation between two coordinate systems.
In this embodiment, the two-dimensional code image captured by the camera is a picture in a coordinate system with the camera (vehicle) as an origin, and is mostly an irregular quadrilateral, and the two-dimensional code deployed on the road is a front view (with a known size) in the coordinate system with the two-dimensional code as the origin, so that a relative position change between the two coordinate systems (that is, between the vehicle and the road where the two-dimensional code is located) can be represented by a rotation matrix between the two-dimensional code image and the front view of the two-dimensional code.
In general, in three-dimensional space, the relative position change between two coordinate systems is expressed by Euler angle, and is realized by rotating matrix
Figure BDA0003455153070000141
Calculating the Euler angle
Figure BDA0003455153070000142
The process of (2) is as follows:
θx＝atan2(r32,r33)
Figure BDA0003455153070000143
θz＝atan2(r21,r11)
and step 804, determining the driving direction of the vehicle at the current detection moment according to the rotation matrix corresponding to each target direction vector and the road orientation information carried in the two-dimensional code image corresponding to each target direction vector.
It can be understood that, knowing the orientation of the road and the relative orientation between the road and the vehicle, the orientation of the vehicle in the basic coordinate system (the coordinate system that determines the location information of all the two-dimensional codes and the orientation of the road) can be easily found, specifically:
Figure BDA0003455153070000144
where n denotes the number of target direction vectors, AiThe direction of the road of the two-dimensional code corresponding to each target direction vector is determined; thetaiAn Euler angle corresponding to each target direction vector; deltaiThe angle error of the laser radar is positively correlated with the angular resolution of the laser radar.
In the method provided by the embodiment of the application, based on the positions of three angle boxes in the two-dimensional code image corresponding to each target direction vector, the two-dimensional code corresponding to each target direction vector is converted into a front view through affine transformation, and a rotation matrix corresponding to each target direction vector is obtained; and determining the driving direction of the vehicle at the current detection moment according to the rotation matrix corresponding to each target direction vector and the road orientation information carried in the two-dimensional code image corresponding to each target direction vector. Through the relative relation of waking up between vehicle and the two-dimensional code, the direction of travel of vehicle is acquireed, assists and obtains more accurate vehicle position information.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the application also provides a vehicle positioning device for realizing the vehicle positioning method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so the specific limitations in one or more embodiments of the vehicle positioning device provided below can be referred to the limitations on the vehicle positioning method in the above, and are not described again here.
In one embodiment, as shown in fig. 9, a vehicle positioning device is provided, the device is installed on a vehicle, the vehicle is provided with a laser radar, a two-dimensional code is arranged on the non-ground part of a lane where the vehicle runs, and the two-dimensional code carries the position information of the two-dimensional code; the device comprises:
a first determining module 901, configured to determine, if a two-dimensional code is detected by a laser radar, a direction vector between a vehicle and each detected two-dimensional code by the laser radar;
a second determining module 902, configured to determine location information of the two-dimensional code corresponding to each target direction vector, where all the target direction vectors are determined from all the direction vectors;
the third determining module 903 is configured to determine vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determine actual position information of the vehicle at the current detection time according to the vehicle position information corresponding to each target direction vector.
In one embodiment, the second determining module 902 is further configured to:
acquiring estimated position information of a vehicle at the current detection moment;
determining two-dimensional code estimated position information corresponding to each direction vector according to the estimated position information of the vehicle at the current detection moment;
and matching the two-dimensional code estimated position information corresponding to each direction vector with the position information of the two-dimensional code in the two-dimensional code information database, and taking the successfully matched direction vector as a target direction vector.
In one embodiment, the second determining module 902 is further configured to:
the method comprises the steps of taking pictures through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by shooting through the camera, identifying each successfully intercepted two-dimensional code image, and taking the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image as a target direction vector.
In one embodiment, the second determining module 902 is further configured to:
photographing through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by the camera, identifying each successfully intercepted two-dimensional code image, forming a first set by the direction vectors corresponding to the successfully intercepted two-dimensional code images, forming a second set by the direction vectors left after the first set is removed from all the direction vectors, and taking the direction vectors in the first set as target direction vectors;
obtaining estimated position information of a vehicle at the current detection time, determining two-dimensional code estimated position information corresponding to each direction vector in the second set according to the estimated position information of the vehicle at the current detection time, matching the two-dimensional code estimated position information corresponding to each direction vector in the second set with position information of two-dimensional codes in a two-dimensional code information database, and taking the successfully matched direction vector in the second set as a target direction vector.
In one embodiment, the second determining module 902 is further configured to:
acquiring the running distance of the vehicle from the last detection time to the current detection time through the odometer;
and determining the estimated position information of the vehicle at the current detection time according to the actual position information of the vehicle at the last detection time, the driving direction and the driving distance of the vehicle at the last detection time.
In one embodiment, the vehicle localization apparatus further comprises a fourth determination module for:
converting the two-dimensional code corresponding to each target direction vector into a front view through affine transformation based on the positions of three angle boxes in the two-dimensional code image corresponding to each target direction vector, and obtaining a rotation matrix corresponding to each target direction vector;
and determining the driving direction of the vehicle at the current detection moment according to the rotation matrix corresponding to each target direction vector and the road orientation information carried in the two-dimensional code image corresponding to each target direction vector.
The various modules in the vehicle locating device described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured 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, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing all road related information carried by the two-dimensional code. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a vehicle localization method.
Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
the method is applied to a vehicle, the vehicle is provided with a laser radar, a two-dimensional code is arranged on the non-ground part of a lane where the vehicle runs, and the two-dimensional code carries the position information of the two-dimensional code; the method comprises the following steps:
if the two-dimensional codes are detected through the laser radar, determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar;
determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors;
and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring estimated position information of a vehicle at the current detection moment;
determining two-dimensional code estimated position information corresponding to each direction vector according to the estimated position information of the vehicle at the current detection moment;
and matching the two-dimensional code estimated position information corresponding to each direction vector with the position information of the two-dimensional code in the two-dimensional code information database, and taking the successfully matched direction vector as a target direction vector.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
the method comprises the steps of taking pictures through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by shooting through the camera, identifying each successfully intercepted two-dimensional code image, and taking the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image as a target direction vector.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
photographing through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by the camera, identifying each successfully intercepted two-dimensional code image, forming a first set by the direction vectors corresponding to the successfully intercepted two-dimensional code images, forming a second set by the direction vectors left after the first set is removed from all the direction vectors, and taking the direction vectors in the first set as target direction vectors;
obtaining estimated position information of a vehicle at the current detection time, determining two-dimensional code estimated position information corresponding to each direction vector in the second set according to the estimated position information of the vehicle at the current detection time, matching the two-dimensional code estimated position information corresponding to each direction vector in the second set with position information of two-dimensional codes in a two-dimensional code information database, and taking the successfully matched direction vector in the second set as a target direction vector.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring the running distance of the vehicle from the last detection time to the current detection time through the odometer;
and determining the estimated position information of the vehicle at the current detection time according to the actual position information of the vehicle at the last detection time, the driving direction and the driving distance of the vehicle at the last detection time.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
converting the two-dimensional code corresponding to each target direction vector into a front view through affine transformation based on the positions of three angle boxes in the two-dimensional code image corresponding to each target direction vector, and obtaining a rotation matrix corresponding to each target direction vector;
and determining the driving direction of the vehicle at the current detection moment according to the rotation matrix corresponding to each target direction vector and the road orientation information carried in the two-dimensional code image corresponding to each target direction vector.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
if the two-dimensional codes are detected through the laser radar, determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar;
determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors;
and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring estimated position information of a vehicle at the current detection moment;
determining two-dimensional code estimated position information corresponding to each direction vector according to the estimated position information of the vehicle at the current detection moment;
and matching the two-dimensional code estimated position information corresponding to each direction vector with the position information of the two-dimensional code in the two-dimensional code information database, and taking the successfully matched direction vector as a target direction vector.
In one embodiment, the computer program when executed by the processor further performs the steps of:
the method comprises the steps of taking pictures through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by shooting through the camera, identifying each successfully intercepted two-dimensional code image, and taking the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image as a target direction vector.
In one embodiment, the computer program when executed by the processor further performs the steps of:
photographing through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by the camera, identifying each successfully intercepted two-dimensional code image, forming a first set by the direction vectors corresponding to the successfully intercepted two-dimensional code images, forming a second set by the direction vectors left after the first set is removed from all the direction vectors, and taking the direction vectors in the first set as target direction vectors;
obtaining estimated position information of a vehicle at the current detection time, determining two-dimensional code estimated position information corresponding to each direction vector in the second set according to the estimated position information of the vehicle at the current detection time, matching the two-dimensional code estimated position information corresponding to each direction vector in the second set with position information of two-dimensional codes in a two-dimensional code information database, and taking the successfully matched direction vector in the second set as a target direction vector.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring the running distance of the vehicle from the last detection time to the current detection time through the odometer;
and determining the estimated position information of the vehicle at the current detection time according to the actual position information of the vehicle at the last detection time, the driving direction and the driving distance of the vehicle at the last detection time.
In one embodiment, the computer program when executed by the processor further performs the steps of:
converting the two-dimensional code corresponding to each target direction vector into a front view through affine transformation based on the positions of three angle boxes in the two-dimensional code image corresponding to each target direction vector, and obtaining a rotation matrix corresponding to each target direction vector;
and determining the driving direction of the vehicle at the current detection moment according to the rotation matrix corresponding to each target direction vector and the road orientation information carried in the two-dimensional code image corresponding to each target direction vector.
In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:
if the two-dimensional codes are detected through the laser radar, determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar;
determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors;
and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring estimated position information of a vehicle at the current detection moment;
determining two-dimensional code estimated position information corresponding to each direction vector according to the estimated position information of the vehicle at the current detection moment;
and matching the two-dimensional code estimated position information corresponding to each direction vector with the position information of the two-dimensional code in the two-dimensional code information database, and taking the successfully matched direction vector as a target direction vector.
In one embodiment, the computer program when executed by the processor further performs the steps of:
the method comprises the steps of taking pictures through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by shooting through the camera, identifying each successfully intercepted two-dimensional code image, and taking the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image as a target direction vector.
In one embodiment, the computer program when executed by the processor further performs the steps of:
photographing through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by the camera, identifying each successfully intercepted two-dimensional code image, forming a first set by the direction vectors corresponding to the successfully intercepted two-dimensional code images, forming a second set by the direction vectors left after the first set is removed from all the direction vectors, and taking the direction vectors in the first set as target direction vectors;
obtaining estimated position information of a vehicle at the current detection time, determining two-dimensional code estimated position information corresponding to each direction vector in the second set according to the estimated position information of the vehicle at the current detection time, matching the two-dimensional code estimated position information corresponding to each direction vector in the second set with position information of two-dimensional codes in a two-dimensional code information database, and taking the successfully matched direction vector in the second set as a target direction vector.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring the running distance of the vehicle from the last detection time to the current detection time through the odometer;
and determining the estimated position information of the vehicle at the current detection time according to the actual position information of the vehicle at the last detection time, the driving direction and the driving distance of the vehicle at the last detection time.
In one embodiment, the computer program when executed by the processor further performs the steps of:
converting the two-dimensional code corresponding to each target direction vector into a front view through affine transformation based on the positions of three angle boxes in the two-dimensional code image corresponding to each target direction vector, and obtaining a rotation matrix corresponding to each target direction vector;
and determining the driving direction of the vehicle at the current detection moment according to the rotation matrix corresponding to each target direction vector and the road orientation information carried in the two-dimensional code image corresponding to each target direction vector.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims (10)

1. The vehicle positioning method is characterized in that the method is applied to a vehicle, the vehicle is provided with a laser radar, a two-dimensional code is arranged on the non-ground part of a lane where the vehicle runs, and the two-dimensional code carries the position information of the two-dimensional code; the method comprises the following steps:
if the two-dimensional codes are detected through the laser radar, determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar;
determining the position information of the two-dimensional code corresponding to each target direction vector, wherein all the target direction vectors are determined from all the direction vectors;
and determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector.
2. The method of claim 1, wherein the determining of the target direction vector comprises:
acquiring estimated position information of the vehicle at the current detection moment;
determining two-dimensional code estimated position information corresponding to each direction vector according to the estimated position information of the vehicle at the current detection moment;
and matching the two-dimensional code estimated position information corresponding to each direction vector with the position information of the two-dimensional code in the two-dimensional code information database, and taking the successfully matched direction vector as a target direction vector.
3. The method of claim 1, wherein the vehicle is provided with a camera; the determination process of the target direction vector comprises the following steps:
the camera shoots, the two-dimensional code image corresponding to each direction vector is intercepted from the image shot by the camera, each successfully intercepted two-dimensional code image is identified, and the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image is used as a target direction vector.
4. The method of claim 1, wherein the vehicle is provided with a camera; the determination process of the target direction vector comprises the following steps:
the method comprises the steps of taking pictures through a camera, intercepting a two-dimensional code image corresponding to each direction vector in an image obtained by the camera, identifying each successfully intercepted two-dimensional code image, forming a first set by the direction vectors corresponding to the successfully intercepted and successfully identified two-dimensional code images, forming a second set by the direction vectors left after the first set is removed from all the direction vectors, and taking the direction vectors in the first set as target direction vectors;
obtaining the estimated position information of the vehicle at the current detection time, determining the two-dimensional code estimated position information corresponding to each direction vector in the second set according to the estimated position information of the vehicle at the current detection time, matching the two-dimensional code estimated position information corresponding to each direction vector in the second set with the position information of the two-dimensional code in the two-dimensional code information database, and taking the successfully matched direction vector in the second set as a target direction vector.
5. A method according to claim 2 or 4, characterized in that the vehicle is provided with a speedometer; the obtaining of the estimated position information of the vehicle at the current detection time includes:
acquiring the running distance of the vehicle from the last detection time to the current detection time through the odometer;
and determining the estimated position information of the vehicle at the current detection time according to the actual position information of the vehicle at the last detection time, the driving direction of the vehicle at the last detection time and the driving distance.
6. The method according to claim 3, wherein the two-dimensional code carries information of the direction of the road where the two-dimensional code is located; after the direction vector corresponding to the successfully intercepted and successfully identified two-dimensional code image is taken as the target direction vector, the method further comprises the following steps:
converting the two-dimensional code corresponding to each target direction vector into a front view through affine transformation based on the positions of three angle boxes in the two-dimensional code image corresponding to each target direction vector, and obtaining a rotation matrix corresponding to each target direction vector;
and determining the driving direction of the vehicle at the current detection moment according to the rotation matrix corresponding to each target direction vector and the road orientation information carried in the two-dimensional code image corresponding to each target direction vector.
7. A vehicle positioning device is characterized in that the device is installed on a vehicle, the vehicle is provided with a laser radar, a two-dimensional code is arranged on the non-ground part of a lane where the vehicle runs, and the two-dimensional code carries the position information of the two-dimensional code; the device comprises:
the first determining module is used for determining a direction vector between the vehicle and each detected two-dimensional code through the laser radar if the two-dimensional code is detected through the laser radar;
the second determining module is used for determining the position information of the two-dimensional code corresponding to each target direction vector, and all the target direction vectors are determined from all the direction vectors;
and the third determining module is used for determining vehicle position information corresponding to each target direction vector according to the position information of the two-dimensional code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment according to the vehicle position information corresponding to each target direction vector.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
CN202210004892.7A 2022-01-04 2022-01-04 Vehicle positioning method and device, computer equipment and storage medium Pending CN114371484A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210004892.7A CN114371484A (en) 2022-01-04 2022-01-04 Vehicle positioning method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210004892.7A CN114371484A (en) 2022-01-04 2022-01-04 Vehicle positioning method and device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114371484A true CN114371484A (en) 2022-04-19

Family

ID=81141545

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210004892.7A Pending CN114371484A (en) 2022-01-04 2022-01-04 Vehicle positioning method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114371484A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115148031A (en) * 2022-06-23 2022-10-04 清华大学深圳国际研究生院 Multi-sensor high-precision positioning method for parking lot inspection vehicle
CN115619869A (en) * 2022-12-14 2023-01-17 广东瑞仕格科技有限公司 Positioning method and device of automatic guided transport vehicle and automatic guided transport vehicle

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115148031A (en) * 2022-06-23 2022-10-04 清华大学深圳国际研究生院 Multi-sensor high-precision positioning method for parking lot inspection vehicle
CN115148031B (en) * 2022-06-23 2023-08-08 清华大学深圳国际研究生院 Multi-sensor high-precision positioning method for parking lot inspection vehicle
CN115619869A (en) * 2022-12-14 2023-01-17 广东瑞仕格科技有限公司 Positioning method and device of automatic guided transport vehicle and automatic guided transport vehicle

Similar Documents

Publication Publication Date Title
JP7398506B2 (en) Methods and systems for generating and using localization reference data
US11530924B2 (en) Apparatus and method for updating high definition map for autonomous driving
US11112252B2 (en) Sensor fusion for accurate localization
KR102671067B1 (en) Method and apparatus for generating road surface, method and apparatus for processing point cloud data, computer program and computer readable recording medium
CN109975773B (en) Millimeter wave radar calibration method, device, equipment and storage medium
JP2018124787A (en) Information processing device, data managing device, data managing system, method, and program
CN114371484A (en) Vehicle positioning method and device, computer equipment and storage medium
JP2009294214A (en) Method and system for navigation based on topographic structure
US7840075B2 (en) Marine radar system with three-dimensional memory
US20120176494A1 (en) System and method for virtual range estimation
CN112805766B (en) Apparatus and method for updating detailed map
EP2052208A2 (en) Determining the location of a vehicle on a map
JP6552448B2 (en) Vehicle position detection device, vehicle position detection method, and computer program for vehicle position detection
CN111353510B (en) Multi-sensor target detection method, multi-sensor target detection device, computer equipment and storage medium
JP2018189463A (en) Vehicle position estimating device and program
CN116608847A (en) Positioning and mapping method based on area array laser sensor and image sensor
JPWO2018212287A1 (en) Measuring device, measuring method and program
CN114067556B (en) Environment sensing method, device, server and readable storage medium
CN116380088B (en) Vehicle positioning method and device, vehicle and storage medium
Schütz et al. Multiple extended objects tracking with object-local occupancy grid maps
US20230322236A1 (en) Vehicle pose assessment
CN116465393A (en) Synchronous positioning and mapping method and device based on area array laser sensor
JP2023068009A (en) Map information creation method
US20220089166A1 (en) Motion state estimation method and apparatus
EP3767233A1 (en) A method and system for navigation of a vehicle

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination