WO2023226147A1 - 一种自动泊车路沿检测方法、装置、车辆及存储介质 - Google Patents

一种自动泊车路沿检测方法、装置、车辆及存储介质 Download PDF

Info

Publication number
WO2023226147A1
WO2023226147A1 PCT/CN2022/102627 CN2022102627W WO2023226147A1 WO 2023226147 A1 WO2023226147 A1 WO 2023226147A1 CN 2022102627 W CN2022102627 W CN 2022102627W WO 2023226147 A1 WO2023226147 A1 WO 2023226147A1
Authority
WO
WIPO (PCT)
Prior art keywords
curb
coordinates
coordinate
parking space
vehicle
Prior art date
Application number
PCT/CN2022/102627
Other languages
English (en)
French (fr)
Inventor
王德祥
Original Assignee
惠州市德赛西威汽车电子股份有限公司
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 惠州市德赛西威汽车电子股份有限公司 filed Critical 惠州市德赛西威汽车电子股份有限公司
Publication of WO2023226147A1 publication Critical patent/WO2023226147A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/06—Automatic manoeuvring for parking
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • 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
    • G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
    • G01S15/88—Sonar systems specially adapted for specific applications
    • G01S15/93—Sonar systems specially adapted for specific applications for anti-collision purposes
    • G01S15/931—Sonar systems specially adapted for specific applications for anti-collision purposes of land vehicles

Definitions

  • the present application relates to the field of data processing technology, and in particular to an automatic parking curb detection method, device, vehicle and storage medium.
  • the automatic parking system is highly sought after by everyone.
  • the driving assistance system function and the intelligence of automatic parking are becoming more and more important.
  • the automatic parking system has a very important problem in parking space detection, that is, the detection of curb information in the parking space.
  • Curb detection includes the following solutions: 1. Panoramic automatic parking requires continuous deep learning from image recognition. For This type of detection technology is still in the learning and development stage, the technology is not very mature, and the chip requirements are high, and the cost of the chip is also high; 2. From the ultrasonic automatic parking recognition parking space, obstacles of different heights can be scanned in layers as Differentiation, but the accuracy of curb detection is low directly based on the height of the obstacle.
  • This application provides an automatic parking curb detection method, device, vehicle and storage medium to solve the problems of low curb detection accuracy and high cost.
  • an automatic parking curb detection method including:
  • a curb point coordinate set and a target parking space coordinate set are obtained.
  • the curb point coordinate set includes at least one curb point coordinate
  • the target parking space coordinate set includes at least one target parking space of the target parking space. Coordinates, the curb point coordinates are determined based on the curb point distance collected by the curb detection device on the vehicle;
  • the distance between the target parking space and the curb is determined based on the coordinates of each target curb point.
  • an automatic parking curb detection device including:
  • a coordinate acquisition module configured to acquire a curb point coordinate set and a target parking space coordinate set after detecting that the vehicle starts parking.
  • the curb point coordinate set includes at least one curb point coordinate
  • the target parking space coordinate set includes a target parking space coordinate set. At least one target parking space coordinate of the parking space, the curb point coordinates are determined based on the curb point distance collected by the curb detection device on the vehicle;
  • the coordinate conversion module is used to perform coordinate system conversion on the coordinates of each curb point to obtain the candidate curb point coordinates in the vehicle coordinate system at the current moment;
  • a coordinate filtering module configured to filter the candidate curb point coordinates according to the target parking space coordinate set to obtain the target curb point coordinates
  • the curb distance determination module is used to determine the distance between the target parking space and the curb according to the coordinates of each target curb point.
  • a vehicle comprising:
  • Roadside detection device used to collect distances from roadside points
  • the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor, so that the at least one processor can execute the method described in any embodiment of the present application. Automatic parking curb detection method.
  • a computer-readable storage medium stores computer instructions, and the computer instructions are used to implement any of the embodiments of the present application when executed by a processor. Automatic parking curb detection method.
  • a set of curb point coordinates and a set of target parking space coordinates are obtained.
  • the set of curb point coordinates includes at least one coordinate set of curb points.
  • the set of target parking space coordinates including at least one target parking space coordinate of the target parking space; performing coordinate system conversion on each curb point coordinate to obtain candidate curb point coordinates in the vehicle coordinate system at the current moment; and converting each candidate curb point coordinate according to the target parking space coordinate set.
  • the curb point coordinates are filtered to obtain the target curb point coordinates; the distance between the target parking space and the curb is determined based on the target curb point coordinates, which solves the problem of inaccurate curb information detection and high cost during automatic parking. question.
  • the roadside point distance is detected by the roadside detection device, and the roadside point coordinates are determined based on the roadside point distance.
  • the roadside point coordinate set is obtained and the roadside point coordinates are transformed into a coordinate system to obtain the current
  • the candidate curb point coordinates in the vehicle coordinate system at the moment are filtered according to the target parking space coordinate set, and the coordinate points with large errors are removed to obtain the target curb point coordinates, which are determined by the target curb point coordinates.
  • Curb further determine the distance between the target parking space and the curb.
  • the implementation process is simple. It only requires simple mathematical processing of the coordinates of the curb points. There is no need to train the model.
  • the curb detection device only needs to collect the distance of the curb points to determine the coordinates of the curb points. , the detection results are accurate and reliable, without the need for high-cost chips, reducing costs.
  • Figure 1 is a flow chart of an automatic parking curb detection method provided according to Embodiment 1 of the present application.
  • Figure 2 is a flow chart of an automatic parking curb detection method provided according to Embodiment 2 of the present application.
  • Figure 3 is an example diagram showing a vehicle and a coordinate system provided according to Embodiment 2 of the present application;
  • Figure 4 is a schematic diagram showing a target parking space and candidate curb points provided according to Embodiment 2 of the present application;
  • Figure 5 is a schematic diagram showing a target parking space and a target curb point provided according to Embodiment 2 of the present application;
  • Figure 6 is a schematic diagram showing a target parking space and curb provided according to Embodiment 2 of the present application.
  • Figure 7 is a schematic structural diagram of an automatic parking curb detection device provided according to Embodiment 3 of the present application.
  • Figure 8 is a schematic structural diagram of a vehicle that implements the automatic parking curb detection method according to the embodiment of the present application.
  • Figure 1 is a flow chart of an automatic parking curb detection method provided in Embodiment 1 of the present application. This embodiment can be applied to the situation of detecting curbs during the automatic parking process.
  • the method can be based on the automatic parking curb detection method.
  • the automatic parking curb detection device can be implemented in the form of hardware and/or software, and the automatic parking curb detection device can be configured in a vehicle. As shown in Figure 1, the method includes:
  • the curb point coordinate set includes at least one curb point coordinate
  • the target parking space coordinate set includes at least one target parking space coordinate of the target parking space.
  • the curb point coordinates are determined based on the curb point distance collected by the curb detection device on the vehicle.
  • the curb point coordinate set can be specifically understood as a data set that stores curb point coordinates;
  • the target parking space can be specifically understood as a parking space where parking can be performed, and the target parking space coordinates can be specifically understood as the coordinates used to represent the target parking space.
  • the target parking space is usually a rectangular frame. Therefore, the coordinates of the target parking space can be determined by one coordinate and the length and width of the parking space, or by 4 coordinates, or by two diagonal coordinates, etc. A rectangular frame can be uniquely determined.
  • the method is determined; the target parking space coordinate set can be specifically understood as a data set that stores the target parking space coordinates.
  • the curb detection device can specifically be understood as a device used for curb detection, such as an APA ultrasonic probe; the curb point distance can specifically be understood as the distance between the curb point and the curb detection device.
  • a curb detection device is installed on the vehicle to collect the distance between curb points. Since the curb is composed of a large number of curb points, when collecting the curb distance, the curb detection device can collect all the curb points that can be collected. The distance to the curb detection device can also be collected only in the horizontal direction of the curb detection device. This application collects the distance between curb points in the horizontal direction of the curb detection device.
  • the curb point coordinates are determined based on the curb point distance and stored in a curb point coordinate set.
  • the curb point coordinate set can be stored locally in the vehicle or in the server. After detecting that the vehicle starts parking, the curb point coordinate set is obtained from the corresponding storage space. When parking a vehicle, it is necessary to determine the target parking space before parking.
  • the target parking space is found through a 360° panoramic view or the USS ultrasonic system and the target parking space coordinates of the target parking space are stored in the target parking space coordinate set.
  • the target parking space coordinate set can also be stored. Locally in the vehicle or on the server. After detecting that the vehicle starts parking, the coordinate set of the target parking space is obtained.
  • S102 Perform coordinate system conversion on the coordinates of each curb point to obtain candidate curb point coordinates in the vehicle coordinate system at the current moment.
  • the vehicle coordinate system can be specifically understood as a coordinate system established based on the current location of the vehicle.
  • the vehicle coordinate system takes the center point of the rear axle of the vehicle as the origin, and the direction of the front of the vehicle as the positive direction of the Y-axis. Taking the right side of the vehicle as the positive direction of the X-axis, the vehicle coordinate system changes as the vehicle position changes.
  • the candidate curb point coordinates can specifically be understood as the coordinates of the candidate points used to determine the curb.
  • the coordinates of each curb point in this application are the coordinates in the vehicle coordinate system when the vehicle is at different locations. Coordinate transformation is performed on the coordinates of each curb point, and the coordinates in the vehicle coordinate system at different locations are converted to the corresponding coordinates in the vehicle coordinate system of the vehicle's current location.
  • the coordinate conversion method may be to predetermine the coordinate conversion formula, perform coordinate conversion on each curb point coordinate according to the coordinate conversion formula, and obtain candidate curb point coordinates corresponding to each curb point coordinate.
  • the roadside point coordinate set of the present application can store the roadside point coordinates according to time (for example, store the roadside point coordinates within 5 minutes), or store the roadside point coordinates according to the quantity (for example, store 100 roadside point coordinates) ), only the coordinates of the curb points near the target parking space can be stored; it is also possible to store all the coordinates of the curb points, but when performing curb detection (ie, coordinate system conversion), the coordinates of the curb points are obtained according to time or quantity. deal with.
  • the coordinates of the target curb point can be specifically understood as the coordinates of the points constituting the curb.
  • the location of the target parking space can be determined based on the coordinate set of the target parking space, and the coordinates of each candidate curb point can be filtered based on the location of the target parking space. For example, coordinate points that are far away can be filtered out, and coordinate points with large errors can be removed through filtering. , get the coordinates of the target curb point.
  • S104 Determine the distance between the target parking space and the curb according to the coordinates of each target curb point.
  • the curb is determined based on the coordinates of each target curb point, and the distance between the target parking space and the curb is calculated.
  • the distance between the target parking space and the curb can be the distance between the vertex of a parking space in the target parking space and the curb, or it can be the distance between the target parking space and the curb. The distance between the center of the parking space and the curb, etc.
  • Embodiments of the present application provide an automatic parking curb detection method. After detecting that a vehicle starts parking, a curb point coordinate set and a target parking space coordinate set are obtained.
  • the curb point coordinate set includes at least one curb point.
  • Coordinates, the target parking space coordinate set includes at least one target parking space coordinate of the target parking space; perform coordinate system conversion on each of the curb point coordinates to obtain the candidate curb point coordinates in the vehicle coordinate system at the current moment; according to the target
  • the parking space coordinate set filters the coordinates of each candidate curb point to obtain the target curb point coordinates; the distance between the target parking space and the curb is determined based on the coordinates of each target curb point, which solves the problem of curb information during automatic parking. Inaccurate detection and higher costs.
  • the roadside point distance is detected by the roadside detection device, and the roadside point coordinates are determined based on the roadside point distance.
  • the roadside point coordinate set is obtained and the roadside point coordinates are transformed into a coordinate system to obtain the current
  • the candidate curb point coordinates in the vehicle coordinate system at the moment are filtered according to the target parking space coordinate set, and the coordinate points with large errors are removed to obtain the target curb point coordinates, which are determined by the target curb point coordinates.
  • Curb further determine the distance between the target parking space and the curb.
  • the implementation process is simple. It only requires simple mathematical processing of the coordinates of the curb points. There is no need to train the model.
  • the curb detection device only needs to collect the distance of the curb points to determine the coordinates of the curb points. , the detection results are accurate and reliable, without the need for high-cost chips, reducing costs.
  • Figure 2 is a flow chart of an automatic parking curb detection method provided in Embodiment 2 of the present application. This embodiment is refined based on the above embodiment. As shown in Figure 2, the method includes:
  • the global coordinate system can specifically be understood as a coordinate system that includes all coordinate points of the vehicle from searching for a parking space to parking.
  • the origin is determined based on the current position of the vehicle to establish a global coordinate system.
  • the global coordinate system uses the center point of the rear axle of the vehicle at the current position as the origin, with the front direction of the vehicle as the positive direction of the Y-axis, and The right side of the vehicle is the positive direction of the X-axis.
  • the global coordinate system does not change with the position of the vehicle.
  • the initial coordinates of the vehicle can be specifically understood as the position coordinates of the vehicle when it starts the parking space search.
  • the user determines that he needs to park, he starts the vehicle to search for a parking space, for example, through keys, buttons, touch control on the center console, etc. to start the parking space search.
  • the current position of the vehicle is determined, the origin, X-axis and Y-axis are determined based on the current position of the vehicle, and a global coordinate system is established.
  • the initial coordinates of the vehicle are determined based on the information during the vehicle's driving process.
  • the origin of the global coordinate system is the origin
  • the initial coordinate of the vehicle can be (0,0).
  • the curb detection device on the vehicle is controlled to start working, and the distance between the curb points is collected through the curb detection device.
  • the number of roadside detection devices may be one or multiple.
  • the installation position information can be understood as the coordinates of the roadside detection device in the vehicle coordinate system.
  • the curb detection device is installed on the vehicle, and its position is usually fixed. Therefore, the installation location information of the curb detection device on the vehicle is determined. Calculate the curb point coordinates based on the installation location information and the curb point distance. At the same time, the collection time of the curb point distance is used as the collection time of the curb point coordinates. The curb point coordinates and their corresponding collection time are stored in the curb point coordinates. in collection.
  • the distance between the curb points is L
  • the installation position information of the curb detection device is A (X1, Y1).
  • the coordinates of the curb point in the vehicle coordinate system are (X1+ L, Y1).
  • curb point coordinates will be stored in the curb point coordinate set according to time. If the curb point coordinates If the number is greater than the preset number, the data furthest in time will be deleted and new data will be stored.
  • the parking space information to be selected can specifically be understood as available parking space information.
  • the parking space search is started, the parking space is searched. After the parking space is searched, the searched parking space is used as the parking space to be selected, and the information of the parking space to be selected is displayed as the parking space information to be selected.
  • the parking space to be selected can be one parking space or information about multiple parking spaces. This application can also use the 360° panoramic or USS ultrasonic system to search for parking spaces and determine the parking space information to be selected.
  • the 360° panoramic or USS ultrasonic system After detecting a vehicle and starting the parking space search, information is sent to the 360° panoramic or USS ultrasonic system so that the 360° panoramic or USS
  • the ultrasonic system searches for parking spaces and receives 360° panoramic view or at least one candidate parking space information determined by the USS ultrasonic system.
  • the parking space information to be selected can be displayed in text or in the form of pictures, and the user can also be prompted by voice.
  • S204 Receive the target parking space determined by the user, determine the target parking space coordinate set of the target parking space, and control the vehicle to start parking.
  • the user selects the target parking space from the parking space information to be selected, receives the target parking space selected by the user, determines the target parking space coordinate set corresponding to the target parking space, and controls the vehicle to start parking.
  • the curb point coordinate set includes at least one curb point coordinate
  • the target parking space coordinate set includes at least one target parking space coordinate of the target parking space
  • the curb point coordinates are determined based on the curb point distance collected by the curb detection device on the vehicle.
  • the real-time position coordinates of the vehicle can be specifically understood as the coordinates of the real-time position of the vehicle in the global coordinate system, and the coordinates of the vehicle at each time are recorded.
  • the collection time of the curb point coordinate is determined, and the corresponding vehicle real-time position coordinates are determined based on the collection time.
  • the coordinate information of the vehicle in the global coordinate system can be determined based on the body's inertial measurement unit IMU, wheel number pulses, body parameters and other parameters.
  • the vehicle offset angle can be specifically understood as the offset angle of the vehicle relative to the initial position. Calculation is performed based on the vehicle's real-time position coordinates and the vehicle's initial coordinates to determine the vehicle's offset angle in the longitudinal axis direction as the vehicle offset angle.
  • the first conversion formula can be specifically understood as a formula for converting the vehicle coordinate system to the global coordinate system.
  • the global curb point coordinates can be specifically understood as the coordinates of the curb point in the global coordinate system.
  • the vehicle's real-time position coordinates, vehicle offset angle and curb point coordinates are brought into the first conversion formula to calculate the global curb point coordinates.
  • this application provides a first conversion formula: (Take two-dimensional coordinates as an example)
  • X2 x1+(X1+L)*cos(yaw)-Y1*sin(yaw);
  • Y2 y1+(X1+L)*sin(yaw)+Y1*cos(yaw).
  • (x1, y1) is the vehicle's real-time position coordinates
  • yaw is the vehicle offset angle
  • (X1+L, Y1) is the curb point coordinates
  • (X2, Y2) is the global curb point coordinates.
  • the second conversion formula can be specifically understood as a formula for converting the global coordinate system to the vehicle coordinate system.
  • the current vehicle position coordinates can be specifically understood as the position coordinates of the vehicle at the current moment.
  • the candidate curb point coordinates can be specifically understood as the coordinates of the curb point in the vehicle coordinate system at the current moment.
  • the current vehicle position coordinates, vehicle offset angle and global curb point coordinates are brought into the second conversion formula to obtain candidate curb point coordinates in the vehicle coordinate system at the current moment.
  • this application provides a second conversion formula:
  • X3 X2*cos(yaw)+Y2*sin(yaw)–(x2*cos(yaw)+y2*sin(yaw));
  • Y3 X2*sin(yaw)+Y2*cos(yaw)–(-x2*sin(yaw)+y2*cos(yaw)).
  • (X3, Y3) is the candidate curb point coordinates
  • (x2, y2) is the current vehicle position coordinates.
  • Figure 3 provides an example diagram showing a vehicle and a coordinate system.
  • a global coordinate system is established based on the current position A of the vehicle 31.
  • the vehicle coordinate system is established based on the current position coordinate B of the vehicle 31 .
  • the angle between the vehicle 31 at position B (vehicle real-time position coordinates) and the initial position coordinates of the vehicle 31 (point A coordinates) is the vehicle offset angle yaw.
  • Both the global coordinate system and the vehicle coordinate system take the center point of the rear axle of the vehicle as the origin, the front direction of the vehicle is the positive direction of the Y-axis, and the right side of the vehicle is the positive direction of the X-axis.
  • S210 Determine the first coordinate range, the second coordinate range and the reference coordinates according to the target parking space coordinate set, filter the coordinates of each candidate curb point according to the first coordinate range, and compare the coordinates of each candidate curb point within the first coordinate range. as alternative curb point coordinates.
  • the first coordinate range and the second coordinate range are both coordinate value ranges, and are used to filter the coordinates of the roadside points in both horizontal and vertical directions.
  • the reference coordinates can specifically be understood as coordinates used for reference when filtering candidate curb point coordinates.
  • the candidate curb point coordinates can specifically be understood as the coordinates obtained by filtering the candidate curb point coordinates.
  • the location of the target parking space is determined based on the coordinates of the target parking space.
  • the first coordinate range is used for longitudinal filtering
  • the second coordinate range and the reference coordinate are used for horizontal filtering as an example.
  • the coordinate range of the target parking space is used as the second coordinate range (or the abscissa coordinate range of the target parking space is used as the second coordinate range), and the maximum value of the abscissa coordinate of the target parking space is used as the reference coordinate.
  • Compare the first coordinate range with the coordinates of each candidate curb point determine whether the ordinate of each candidate curb point coordinate is within the first coordinate range, and use the coordinates of each candidate curb point within the first coordinate range as candidates Curb point coordinates.
  • this optional embodiment is further optimized as:
  • A1 Filter the coordinates of each candidate curb point according to the second coordinate range, and use the coordinates of each candidate curb point that are not within the second coordinate range as the first curb point coordinates.
  • the first curb point coordinates can be specifically understood as coordinates obtained by horizontally filtering the candidate curb point coordinates. Filter the abscissa coordinates of each candidate curb point coordinate according to the second coordinate range. Taking the second coordinate range as the coordinate range of the target parking space as an example, filter and delete the coordinates within the second coordinate range to obtain the result that is not in the second coordinate range. The coordinates of each candidate curb point within the coordinate range are used as the first curb point coordinates.
  • the first preset distance threshold can be specifically understood as a preset threshold, for example, 1m.
  • A3. Determine the coordinates of the reference curb point based on the coordinates of each first curb point, and determine the horizontal distance between the coordinates of each first curb point and the coordinates of the reference curb point.
  • the coordinates of the reference curb points can be filtered out from the coordinates of each first curb point according to rules such as time and coordinates, or they can be calculated on the coordinates of each first curb point, for example, by calculating average values, minimum values, etc. owned. For example, the collection time of each first curb point is compared, and the coordinates of the first curb point with the latest collection time are determined as the reference curb point coordinates. The horizontal distance between the coordinates of each first curb point and the coordinates of the reference curb point is determined by calculating the absolute value of the difference between the abscissas.
  • A4. Determine the coordinates of each first curb point whose horizontal distance is less than the second preset distance threshold as the target curb point coordinates.
  • the second preset distance threshold can be specifically understood as a preset threshold, for example, 20 cm.
  • the size of each horizontal distance and the second preset distance threshold is determined, and the coordinates of each first curb point whose level is smaller than the second preset distance threshold are determined as target curb point coordinates. Achieve further horizontal filtering.
  • Figure 4 is a schematic diagram showing a target parking space and candidate curb points provided by an embodiment of the present application.
  • the target parking space is 41
  • each candidate curb point 42 (the coordinates of the candidate curb points are candidate curb point coordinates) distributed near the target parking space 41, parking space 43, and parking space 44.
  • the coordinates of each candidate curb point are filtered through the first coordinate range, the second coordinate range, and the reference coordinates to obtain the target curb point 45 (
  • the coordinates of the target curb point are the coordinates of the target curb point).
  • Figure 5 is a schematic diagram showing a target parking space and a target curb point provided by an embodiment of the present application.
  • the similar points in Figure 4 are all candidate curb points 42, which are not marked one by one in the figure, and those skilled in the art can know; correspondingly, the similar points in Figure 5 are all target curb points, They are not marked one by one in the figure, and those skilled in the art can know.
  • the curb is obtained by performing data fitting on the coordinates of each target curb point.
  • the fitting method can be the least squares method, etc.
  • the final filtered target road can be processed by the least squares method.
  • the reference vertex coordinates can specifically be understood as the coordinates of the vertex of the target parking space as the reference point. Determine the four vertices of the target parking space according to the target parking space coordinate set, use any one of the two vertices on the side away from the curb as the reference vertex, and determine the coordinates of this vertex as the reference vertex coordinates.
  • the distance between the target parking space and the curb is also used to plan the path during automatic parking to avoid the vehicle colliding with the curb.
  • Figure 6 is a schematic diagram showing a target parking space and a curb provided by an embodiment of the present application.
  • the relative positions of the target parking space 51 and the curb 52 are as shown in the figure.
  • the coordinates of the parking space vertex A are used as the reference vertex coordinates.
  • the distance between the parking space vertex A and the curb 52 is calculated as the distance between the target parking space and the curb.
  • This application detects the distance between curb points based on the curb detection device, calculates the depth information of the curb, and uses it for automatic parking. It can achieve flexible control of the vehicle, avoid the vehicle hitting the curb, and damage the tire hub, and also control the parking of the vehicle. It's highly flexible.
  • the algorithm detection method has low computing power, can be implemented on low-cost hardware, and has strong scalability.
  • the embodiment of the present application provides an automatic parking curb detection method, which solves the problems of inaccurate curb information detection and high cost during automatic parking.
  • the roadside point distance is detected by the roadside detection device, and the roadside point coordinates are determined based on the roadside point distance.
  • the roadside point coordinate set is obtained and the roadside point coordinates are transformed into a coordinate system to obtain the current
  • the candidate curb point coordinates in the vehicle coordinate system at the moment are filtered according to the target parking space coordinate set, and the coordinate points with large errors are removed to obtain the target curb point coordinates, which are determined by the target curb point coordinates.
  • Curb further determine the distance between the target parking space and the curb.
  • the implementation process is simple.
  • the curb detection device only needs to collect the distance of the curb points to determine the coordinates of the curb points. , the detection results are accurate and reliable, without the need for high-cost chips, reducing costs.
  • Figure 7 is a schematic structural diagram of an automatic parking curb detection device provided in Embodiment 3 of the present application. As shown in Figure 7, the device includes: a coordinate acquisition module 61, a coordinate conversion module 62, a coordinate filtering module 63 and a curb distance determination module 64.
  • the coordinate acquisition module 61 is used to acquire a set of curb point coordinates and a set of target parking space coordinates after detecting that the vehicle starts parking.
  • the set of curb point coordinates includes at least one curb point coordinate
  • the set of target parking space coordinates The set includes at least one target parking space coordinate of the target parking space, and the curb point coordinates are determined based on the curb point distance collected by the curb detection device on the vehicle;
  • the coordinate conversion module 62 is used to perform coordinate system conversion on the coordinates of each curb point to obtain the candidate curb point coordinates in the vehicle coordinate system at the current moment;
  • the coordinate filtering module 63 is used to filter each of the candidate curb point coordinates according to the target parking space coordinate set to obtain the target curb point coordinates;
  • the curb distance determination module 64 is used to determine the distance between the target parking space and the curb according to the coordinates of each target curb point.
  • the embodiment of the present application provides an automatic parking curb detection device, which solves the problems of inaccurate curb information detection and high cost during automatic parking.
  • the roadside point distance is detected by the roadside detection device, and the roadside point coordinates are determined based on the roadside point distance.
  • the roadside point coordinate set is obtained and the roadside point coordinates are transformed into a coordinate system to obtain the current
  • the candidate curb point coordinates in the vehicle coordinate system at the moment are filtered according to the target parking space coordinate set, and the coordinate points with large errors are removed to obtain the target curb point coordinates, which are determined by the target curb point coordinates.
  • Curb further determine the distance between the target parking space and the curb.
  • the implementation process is simple.
  • the curb detection device only needs to collect the distance of the curb points to determine the coordinates of the curb points. , the detection results are accurate and reliable, without the need for high-cost chips, reducing costs.
  • the device also includes:
  • a distance acquisition module used to establish a global coordinate system based on the current location of the vehicle when a vehicle is detected to start a parking space search, determine the initial coordinates of the vehicle, and control the curb detection device on the vehicle to collect the distance from the curb point;
  • a coordinate storage module configured to determine the coordinates of the curb point based on the distance to the curb point and the installation location information of the curb detection device, and store the coordinates of the curb point and its corresponding collection time into the coordinates of the curb point. in collection.
  • the device also includes:
  • the parking space display module is used to obtain and display the parking space information to be selected after a vehicle is detected and the parking space search is started;
  • the parking start module is used to receive the target parking space determined by the user, determine the target parking space coordinate set of the target parking space, and control the vehicle to start parking.
  • the coordinate conversion module 62 includes:
  • a real-time coordinate acquisition unit configured to obtain the real-time position coordinates of the vehicle corresponding to the coordinates of each curb point for each curb point coordinate;
  • An offset angle determination unit configured to determine the vehicle offset angle based on the vehicle's real-time position coordinates and the vehicle's initial coordinates
  • a first coordinate conversion unit configured to convert the curb point coordinates into global curb point coordinates in a global coordinate system in combination with the vehicle real-time position coordinates and the vehicle offset angle according to a preset first conversion formula
  • the second coordinate conversion unit is used to convert the global curb point coordinates into candidate curb point coordinates in the vehicle coordinate system at the current moment according to the preset second conversion formula in combination with the current vehicle position coordinates and the vehicle offset angle.
  • the coordinate filtering module 63 includes:
  • the first filtering unit is configured to determine the first coordinate range, the second coordinate range and the reference coordinates according to the target parking space coordinate set, filter the candidate curb point coordinates according to the first coordinate range, and filter the candidate curb point coordinates in the first coordinate range.
  • the coordinates of each candidate curb point within a coordinate range are used as candidate curb point coordinates;
  • a second filtering unit is configured to filter each of the candidate curb point coordinates according to the second coordinate range and reference coordinates, and determine at least one target curb point coordinate.
  • the second filtering unit is specifically configured to: filter the coordinates of each candidate curb point according to the second coordinate range, and filter each candidate curb point that is not within the second coordinate range.
  • the coordinates are used as the first curb point coordinates; the coordinates of each of the candidate curb points whose horizontal distance from the reference coordinates does not exceed the first preset distance threshold are used as the first curb point coordinates; according to each of the first The roadside point coordinates determine the reference roadside point coordinates, determine the horizontal distance between the first roadside point coordinates and the reference roadside point coordinates; and determine the horizontal distance between each first roadside point whose horizontal distance is less than the second preset distance threshold.
  • the coordinates of the edge points are determined as the coordinates of the target curb points.
  • the curb distance determination module 64 includes:
  • a data fitting unit is used to perform data fitting on the coordinates of each target curb point to determine the curb
  • a reference coordinate determination unit configured to determine the reference vertex coordinates of the target parking space according to the target parking space coordinate set
  • a distance determination unit is used to calculate the distance between the curb and the reference vertex coordinates as the distance between the target parking space and the curb.
  • the automatic parking curb detection device provided by the embodiments of this application can execute the automatic parking curb detection method provided by any embodiment of this application, and has the corresponding functional modules and effects of the execution method.
  • Figure 8 shows a schematic structural diagram of a vehicle that can be used to implement embodiments of the present application.
  • the components shown herein, their connections and relationships, and their functions are examples only and are not intended to limit the implementation of the present application as described and/or claimed herein.
  • the vehicle includes a curb detection device 70 for collecting the distance between curb points.
  • the number of the road edge detection device 70 may be one or multiple.
  • FIG. 8 takes one device as an example.
  • the vehicle includes at least one processor 71, and a memory communicatively connected to the at least one processor 71, such as a read-only memory (ROM) 72, a random access memory (RAM) 73, etc., wherein the memory stores information that can be executed by the at least one processor.
  • the processor 71 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 72 or loaded from the storage unit 78 into the random access memory (RAM) 73 .
  • RAM 73 various programs and data required for vehicle operation can also be stored.
  • the processor 71, the ROM 72 and the RAM 73 are connected to each other via the bus 74.
  • An input/output (I/O) interface 75 is also connected to bus 74 .
  • I/O interface 75 Multiple components in the vehicle are connected to the I/O interface 75, including: input unit 76, such as keyboard, mouse, etc.; output unit 77, such as various types of displays, speakers, etc.; storage unit 78, such as magnetic disk, optical disk, etc.; and a communication unit 79, such as a network card, modem, wireless communication transceiver, etc.
  • the communication unit 79 allows the vehicle to exchange information/data with other devices via computer networks such as the Internet and/or various telecommunications networks.
  • Processor 71 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 71 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processing processor (DSP), and any appropriate processor, controller, microcontroller, etc.
  • the processor 71 performs various methods and processes described above, such as the automatic parking curb detection method.
  • the automatic parking curb detection method may be implemented as a computer program, which is tangibly embodied in a computer-readable storage medium, such as the storage unit 78 .
  • part or all of the computer program may be loaded and/or installed on the vehicle via ROM 72 and/or communication unit 79.
  • processor 71 When the computer program is loaded into RAM 73 and executed by processor 71, one or more steps of the automatic parking curb detection method described above may be performed.
  • the processor 71 may be configured to perform the automatic parking curb detection method in any other suitable manner (eg, by means of firmware).
  • Various implementations of the systems and techniques described above may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip implemented in a system (SOC), complex programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOC system
  • CPLD complex programmable logic device
  • computer hardware firmware, software, and/or combinations thereof.
  • These various embodiments may include implementation in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor
  • the processor which may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • An output device may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • An output device may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
  • Computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that the computer program, when executed by the processor, causes the functions/operations specified in the flowcharts and/or block diagrams to be implemented.
  • a computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device.
  • Computer-readable storage media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing.
  • the computer-readable storage medium may be a machine-readable signal medium.
  • machine-readable storage media would include one or more wire-based electrical connections, laptop disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM portable compact disk read-only memory
  • magnetic storage device or any suitable combination of the above.
  • the systems and techniques described herein may be implemented on a vehicle having: a display device (eg, a CRT (Cathode Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the vehicle.
  • a display device eg, a CRT (Cathode Ray Tube) or LCD (Liquid Crystal Display) monitor
  • a keyboard and pointing device eg, a mouse or a trackball
  • Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and may be provided in any form, including Acoustic input, voice input or tactile input) to receive input from the user.
  • the systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., A user's computer having a graphical user interface or web browser through which the user can interact with implementations of the systems and technologies described herein), or including such backend components, middleware components, or any combination of front-end components in a computing system.
  • the components of the system may be interconnected by any form or medium of digital data communication (eg, a communications network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.
  • Computing systems may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact over a communications network.
  • the relationship of client and server is created by computer programs running on corresponding computers and having a client-server relationship with each other.
  • the server can be a cloud server, also known as cloud computing server or cloud host. It is a host product in the cloud computing service system to solve the problems of difficult management and weak business scalability in traditional physical hosts and VPS. .

Abstract

本申请公开了一种自动泊车路沿检测方法、装置、车辆及存储介质，该方法包括：当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合，路沿点坐标集合包括至少一个路沿点坐标，目标车位坐标集合包括目标车位的至少一个目标车位坐标；对各路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标；根据目标车位坐标集合对各候选路沿点坐标进行过滤，得到目标路沿点坐标；根据各目标路沿点坐标确定目标车位与路沿的距离。

Description

一种自动泊车路沿检测方法、装置、车辆及存储介质
本申请要求在2022年05月26日提交中国专利局、申请号为202210585472.2的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请涉及数据处理技术领域，尤其涉及一种自动泊车路沿检测方法、装置、车辆及存储介质。
背景技术
随着汽车行业的蓬勃发展，人们对于汽车功能性、完备性不单单停留在以往的动力性能以及舒适性上，安全辅助性能也顺势站上了汽车舞台，其中，自动泊车系统是受大家追捧的驾驶辅助系统功能，自动泊车的智能性也越来越重要，其中，自动泊车系统在车位检测上，存在一个非常重要的问题，即停车位里面的路沿信息检测问题。
无论是全景自动泊车还是超声波自动泊车，停车位里面的车辆有路沿是非常常见的，路沿检测包括如下方案：1、全景自动泊车从图像识别上，需要不断的深度学习，对于这类检测技术还处于学习开发阶段，技术不是很成熟，而且对于芯片要求较高，芯片所需成本也高；2、从超声波自动泊车识别车位上，可以分层次扫描不同高度的障碍物作为区分，但是直接根据障碍物的高度进行路沿检测，准确度较低。
发明内容
本申请提供了一种自动泊车路沿检测方法、装置、车辆及存储介质，以解决路沿检测准确度较低和成本较高的问题。
根据本申请的一方面，提供了一种自动泊车路沿检测方法，包括：
当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合，所述路沿点坐标集合包括至少一个路沿点坐标，所述目标车位坐标集合包括目标车位的至少一个目标车位坐标，所述路沿点坐标根据所述车辆上的路沿检测装置所采集的路沿点距离确定；
对各所述路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标；
根据所述目标车位坐标集合对各所述候选路沿点坐标进行过滤，得到目标 路沿点坐标；
根据各所述目标路沿点坐标确定目标车位与路沿的距离。
根据本申请的另一方面，提供了自动泊车路沿检测装置，包括：
坐标获取模块，用于当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合，所述路沿点坐标集合包括至少一个路沿点坐标，所述目标车位坐标集合包括目标车位的至少一个目标车位坐标，所述路沿点坐标根据所述车辆上的路沿检测装置所采集的路沿点距离确定；
坐标转换模块，用于对各所述路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标；
坐标过滤模块，用于根据所述目标车位坐标集合对各所述候选路沿点坐标进行过滤，得到目标路沿点坐标；
路沿距离确定模块，用于根据各所述目标路沿点坐标确定目标车位与路沿的距离。
根据本申请的另一方面，提供了一种车辆，所述车辆包括：
路沿检测装置，用于采集路沿点距离；
至少一个处理器；以及
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的计算机程序，所述计算机程序被所述至少一个处理器执行，以使所述至少一个处理器能够执行本申请任一实施例所述的自动泊车路沿检测方法。
根据本申请的另一方面，提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，所述计算机指令用于使处理器执行时实现本申请任一实施例所述的自动泊车路沿检测方法。
本申请实施例的技术方案，当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合，所述路沿点坐标集合包括至少一个路沿点坐标，所述目标车位坐标集合包括目标车位的至少一个目标车位坐标；对各所述路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标；根据所述目标车位坐标集合对各所述候选路沿点坐标进行过滤，得到目标路沿点坐标；根据各所述目标路沿点坐标确定目标车位与路沿的距离，解决了自动泊车时，路沿信息检测不准确以及成本较高的问题。通过路沿检测装置检测路沿点距离，根据路沿点距离确定路沿点坐标，在检测到车辆启动泊车后，获取路沿点坐标集合并对路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路 沿点坐标，根据目标车位坐标集合对各候选路沿点坐标进行过滤，去掉误差较大的坐标点，得到目标路沿点坐标，通过目标路沿点坐标确定路沿，进一步确定目标车位和路沿的距离。本申请在检测路沿过程中，实现过程简单，只需要对路沿点坐标进行简单的数学处理即可，无需训练模型，路沿检测装置只需要采集路沿点距离即可确定路沿点坐标，检测结果准确、可靠，无需高成本的芯片，降低了成本。
附图说明
图1是根据本申请实施例一提供的一种自动泊车路沿检测方法的流程图；
图2是根据本申请实施例二提供的一种自动泊车路沿检测方法的流程图；
图3是根据本申请实施例二提供的一种车辆和坐标系的展示示例图；
图4是根据本申请实施例二提供的一种目标车位和候选路沿点的展示示意图；
图5是根据本申请实施例二提供的一种目标车位和目标路沿点的展示示意图；
图6是根据本申请实施例二提供的一种目标车位和路沿的展示示意图；
图7是根据本申请实施例三提供的一种自动泊车路沿检测装置的结构示意图；
图8是实现本申请实施例的自动泊车路沿检测方法的车辆的结构示意图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方 法、产品或设备固有的其它步骤或单元。
实施例一
图1为本申请实施例一提供了一种自动泊车路沿检测方法的流程图，本实施例可适用于自动泊车过程中对路沿进行检测的情况，该方法可以由自动泊车路沿检测装置来执行，该自动泊车路沿检测装置可以采用硬件和/或软件的形式实现，该自动泊车路沿检测装置可配置于车辆中。如图1所示，该方法包括：
S101、当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合，路沿点坐标集合包括至少一个路沿点坐标，目标车位坐标集合包括目标车位的至少一个目标车位坐标，路沿点坐标根据车辆上的路沿检测装置所采集的路沿点距离确定。
在本实施例中，路沿点坐标集合具体可以理解为存储路沿点坐标的数据集；目标车位具体可以理解为可以进行停车的车位，目标车位坐标具体可以理解为用于表示目标车位的坐标，目标车位通常是矩形框，因此，目标车位坐标可以通过一个坐标以及车位的长、宽确定，也可以通过4个坐标确定，或者两个斜对角的坐标确定等任意可以唯一确定一个矩形框的方式确定；目标车位坐标集合具体可以理解为存储目标车位坐标的数据集。路沿检测装置具体可以理解为用于进行路沿检测的装置，例如APA超声波探头；路沿点距离具体可以理解为路沿点距离路沿检测装置的距离。
具体的，车辆上安装路沿检测装置采集路沿点距离，由于路沿是由大量的路沿点构成，在采集路沿距离时，路沿检测装置可以采集所能采集到的所有路沿点与路沿检测装置之间的距离，也可以仅采集路沿检测装置水平方向的距离，本申请采集路沿检测装置水平方向的路沿点的路沿点距离。根据路沿点距离确定路沿点坐标并存储至路沿点坐标集合中，路沿点坐标集合可以存储在车辆本地也可以存储在服务器。在检测到车辆启动泊车后，从相应的存储空间获取路沿点坐标集合。车辆进行泊车时，需要确定目标车位才可以进行泊车，通过360°全景或者USS超声波系统寻找目标车位并将目标车位的目标车位坐标存储至目标车位坐标集合中，目标车位坐标集合同样可以存储在车辆本地或者服务器。在检测到车辆启动泊车后，获取目标车位坐标集合。
S102、对各路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标。
在本实施例中，车辆坐标系具体可以理解为以车辆当前所在的位置所建立的坐标系，示例性的，车辆坐标系以车辆后轴中心点为原点，以车头朝向 为Y轴正方向，以车辆右侧为X轴正方向，车辆坐标系随着车辆位置改变而改变。候选路沿点坐标具体可以理解为用于确定路沿的候选点的坐标。
本申请中的各路沿点坐标为车辆在不同位置时的车辆坐标系下的坐标。将各路沿点坐标进行坐标转换，将不同位置的车辆坐标系下的坐标转换到当前时刻车辆所处位置的车辆坐标系下对应的坐标。坐标转换的方式可以是预先确定坐标转换公式，根据坐标转换公式对各路沿点坐标进行坐标转换，得到每个路沿点坐标对应的候选路沿点坐标。
本申请是在车辆行驶过程中采集不同的路沿点坐标，在泊车时，只需要确定目标车位附近的路沿点坐标即可，无需对所有的路沿点均进行采集。因此，本申请的路沿点坐标集合可以按照时间存储路沿点坐标(例如，存储5分钟内的路沿点坐标)，或者按照数量存储路沿点坐标(例如，存储100个路沿点坐标)，仅存储目标车位附近的路沿点坐标即可；也可以存储所有的路沿点坐标，但是在进行路沿检测(即进行坐标系转换)时，按照时间或数量获取路沿点坐标进行处理。
S103、根据目标车位坐标集合对各候选路沿点坐标进行过滤，得到目标路沿点坐标。
在本实施例中，目标路沿点坐标具体可以理解为构成路沿的点的坐标。根据目标车位坐标集合可以确定目标车位的位置，根据目标车位的位置对各候选路沿点坐标进行过滤筛选，例如，过滤掉距离较远的坐标点，通过过滤的方式去掉误差较大的坐标点，得到目标路沿点坐标。
S104、根据各目标路沿点坐标确定目标车位与路沿的距离。
在本实例中，根据各目标路沿点坐标确定路沿，计算目标车位与路沿的距离，目标车位与路沿的距离可以是目标车位的一个车位顶点与路沿的距离，也可以是目标车位的车位中心与路沿的距离等。
本申请实施例提供了一种自动泊车路沿检测方法，当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合，所述路沿点坐标集合包括至少一个路沿点坐标，所述目标车位坐标集合包括目标车位的至少一个目标车位坐标；对各所述路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标；根据所述目标车位坐标集合对各所述候选路沿点坐标进行过滤，得到目标路沿点坐标；根据各所述目标路沿点坐标确定目标车位与路沿的距离，解决了自动泊车时，路沿信息检测不准确以及成本较高的问题。通过路沿检测装置检测路沿点距离，根据路沿点距离确定路沿点坐标，在检测到车辆启动泊车后，获取路沿点坐标集合并对路沿点坐标进行坐标系 转换，得到当前时刻的车辆坐标系下的候选路沿点坐标，根据目标车位坐标集合对各候选路沿点坐标进行过滤，去掉误差较大的坐标点，得到目标路沿点坐标，通过目标路沿点坐标确定路沿，进一步确定目标车位和路沿的距离。本申请在检测路沿过程中，实现过程简单，只需要对路沿点坐标进行简单的数学处理即可，无需训练模型，路沿检测装置只需要采集路沿点距离即可确定路沿点坐标，检测结果准确、可靠，无需高成本的芯片，降低了成本。
实施例二
图2为本申请实施例二提供的一种自动泊车路沿检测方法的流程图，本实施例在上述实施例的基础上进行细化。如图2所示，该方法包括：
S201、当检测到车辆启动车位搜索时，根据车辆的当前位置建立全局坐标系，确定车辆初始坐标，并控制车辆上的路沿检测装置采集路沿点距离。
在本实施例中，全局坐标系具体可以理解为包括车辆从搜索车位到泊车过程中全部坐标点的坐标系。以车辆在启动车位搜索时，根据车辆的当前位置确定原点建立全局坐标系，示例性的，全局坐标系以车辆在当前位置的后轴中心点为原点，以车头朝向为Y轴正方向，以车辆右侧为X轴正方向。全局坐标系不随车辆的位置变化而改变。车辆初始坐标具体可以理解为车辆启动车位搜索时的位置坐标。
具体的，用户在确定需要进行停车时，启动车辆进行车位搜索，例如，通过按键、按钮、中控台触摸控制等方式启动车位搜索。当检测到车辆启动车位搜索时，确定车辆的当前位置，根据车辆的当前位置确定原点、X轴和Y轴，建立全局坐标系，同时根据车辆行驶过程中的信息确定车辆初始坐标，当车辆作为全局坐标系的原点时，车辆初始坐标可以是(0,0)。当检测到车辆启动车位搜索时，控制车辆上的路沿检测装置启动工作，通过路沿检测装置采集路沿点距离。路沿检测装置的数量可以是一个也可以是多个。
S202、根据路沿点距离和路沿检测装置的安装位置信息确定路沿点坐标，并将路沿点坐标及其对应的采集时间存储至路沿点坐标集合中。
具体的，安装位置信息具体可以理解为路沿检测装置在车辆坐标系下的坐标。路沿检测装置安装在车辆上，通常情况下位置固定，因此，车辆上的路沿检测装置的安装位置信息是确定的。根据安装位置信息和路沿点距离计算路沿点坐标，同时将路沿点距离的采集时间作为路沿点坐标的采集时间，将路沿点坐标及其对应的采集时间存储至路沿点坐标集合中。
示例性的，路沿点距离为L，路沿检测装置的安装位置信息A(X1，Y1)， 以右侧路沿为例，此时确定车辆坐标系下的路沿点坐标为(X1+L,Y1)。
需要知道的是，如果本申请中的路沿点坐标集合中未存储预设数量的路沿点坐标，则将路沿点坐标按照时间存储到路沿点坐标集合中，如果路沿点坐标的数量大于预设数量，则删除时间上最远的数据，将新数据存储进去。
S203、当检测到车辆启动车位搜索后，获取待选车位信息并展示。
在本实施例中，待选车位信息具体可以理解为可停车的车位信息。当检测到车辆启动车位搜索后，对车位进行搜索，在搜索到车位后，将搜索到的车位作为待选车位，将待选车位的信息作为待选车位信息进行展示。待选车位可以是一个车位，也可以是多个车位的信息。本申请进行车位搜索确定待选车位信息也可以通过360°全景或者USS超声波系统实现，例如，在检测到车辆启动车位搜索后，向360°全景或者USS超声波系统发送信息，以便360°全景或者USS超声波系统进行车位搜索，并接收360°全景或者USS超声波系统确定的至少一个待选车位信息。待选车位信息可通过文字展示，也可以通过图片的形式进行展示，同时还可以语音提示用户。
S204、接收用户确定的目标车位，确定目标车位的目标车位坐标集合并控制车辆启动泊车。
向用户展示待选车位信息后，用户从各待选车位信息中选择目标车位，接收用户选择的目标车位，确定目标车位对应的目标车位坐标集合，控制车辆启动泊车。
S205、当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合。
其中，路沿点坐标集合包括至少一个路沿点坐标，目标车位坐标集合包括目标车位的至少一个目标车位坐标，路沿点坐标根据车辆上的路沿检测装置所采集的路沿点距离确定。
S206、针对每个路沿点坐标，获取路沿点坐标对应的车辆实时位置坐标。
在本实施例中，车辆实时位置坐标具体可以理解为车辆在全局坐标系下的实时位置的坐标，记录车辆在各时刻的坐标。针对每个路沿点坐标，确定路沿点坐标的采集时间，根据采集时间确定相应的车辆实时位置坐标。
本申请中车辆在全局坐标系下的坐标信息可根据车身的惯性测量单元IMU、轮数脉冲和车身参数等参数确定。
S207、根据车辆实时位置坐标与车辆初始坐标确定车辆偏移角度。
在本实施例中，车辆偏移角度具体可以理解为车辆相对初始位置的偏移角 度。根据车辆实时位置坐标与车辆初始坐标进行计算，确定车辆在纵轴方向的偏移角度，作为车辆偏移角度。
S208、根据预设的第一转换公式结合车辆实时位置坐标和车辆偏移角度将路沿点坐标转换为全局坐标系下的全局路沿点坐标。
在本实施例中，第一转换公式具体可以理解为车辆坐标系到全局坐标系转换的公式。全局路沿点坐标具体可以理解为路沿点在全局坐标系下的坐标。
将车辆实时位置坐标、车辆偏移角度和路沿点坐标带入到第一转换公式，计算得到全局路沿点坐标。
示例性的，本申请提供一种第一转换公式：(以二维坐标为例)
X2＝x1+(X1+L)*cos(yaw)-Y1*sin(yaw)；
Y2＝y1+(X1+L)*sin(yaw)+Y1*cos(yaw)。
其中，(x1，y1)为车辆实时位置坐标，yaw为车辆偏移角度；(X1+L，Y1)为路沿点坐标，(X2，Y2)为全局路沿点坐标。
S209、根据预设的第二转换公式结合当前车辆位置坐标和车辆偏移角度将全局路沿点坐标转换为当前时刻的车辆坐标系下的候选路沿点坐标。
在本实施例中，第二转换公式具体可以理解为全局坐标系到车辆坐标系转换的公式。当前车辆位置坐标具体可以理解为车辆在当前时刻的位置坐标。候选路沿点坐标具体可以理解为路沿点在当前时刻的车辆坐标系下的坐标。
将当前车辆位置坐标、车辆偏移角度和全局路沿点坐标带入到第二转换公式中，得到当前时刻的车辆坐标系下的候选路沿点坐标。
示例性的，本申请提供一种第二转换公式：
X3＝X2*cos(yaw)+Y2*sin(yaw)–(x2*cos(yaw)+y2*sin(yaw))；
Y3＝X2*sin(yaw)+Y2*cos(yaw)–(-x2*sin(yaw)+y2*cos(yaw))。
其中，(X3，Y3)为候选路沿点坐标，(x2，y2)为当前车辆位置坐标。
示例性的，图3提供一种车辆和坐标系的展示示例图，如图3所示，车辆31启动车位搜索时，根据车辆31的当前位置A建立全局坐标系，车辆31在行驶过程中，根据车辆31的当前位置坐标B建立车辆坐标系。车辆31在B位置(车辆实时位置坐标)时与车辆31的初始位置坐标(A点坐标)之间的夹角为车辆偏移角度yaw。全局坐标系和车辆坐标系均以车辆后轴中心点为原点，车头方向为Y轴正方向，车辆右侧为X轴正方向。
S210、根据目标车位坐标集合确定第一坐标范围、第二坐标范围和参考坐 标，根据第一坐标范围对各候选路沿点坐标进行过滤，将在第一坐标范围内的各候选路沿点坐标作为备选路沿点坐标。
在本实施例中，第一坐标范围和第二坐标范围均为坐标的取值范围，用于从横向和纵向两个方向对路沿点的坐标进行过滤。参考坐标具体可以理解为用于在对候选路沿点坐标过滤时进行参考的坐标。备选路沿点坐标具体可以理解为对候选路沿点坐标进行筛选得到的坐标。
具体的，根据目标车位坐标确定目标车位所在的位置，以目标车位在车辆的右侧为例，以第一坐标范围用于进行纵向过滤，第二坐标范围和参考坐标进行横向过滤为例。根据目标车位坐标确定纵坐标范围，将纵坐标范围作为第一坐标范围。将目标车位的坐标范围作为第二坐标范围(或者将目标车位的横坐标范围作为第二坐标范围)，将目标车位的横坐标的最大值作为参考坐标。将第一坐标范围与各候选路沿点坐标进行比较，确定各候选路沿点坐标的纵坐标是否在第一坐标范围内，将在第一坐标范围内的各候选路沿点坐标作为备选路沿点坐标。
S211、根据第二坐标范围和参考坐标对各备选路沿点坐标进行过滤，确定至少一个目标路沿点坐标。
根据第二坐标范围和参考坐标对各备选路沿点坐标的横坐标进行筛选，过滤掉距离目标车位较远的坐标点，以及在目标车位中的坐标点，得到至少一个目标路沿点坐标。
作为本实施例的一个可选实施例，本可选实施例进一步优化为：
A1、根据第二坐标范围对各备选路沿点坐标进行过滤，将不在第二坐标范围内的各备选路沿点坐标作为第一路沿点坐标。
在本实施例，第一路沿点坐标具体可以理解为对备选路沿点坐标进行横向过滤得到的坐标。根据第二坐标范围对各备选路沿点坐标的横坐标进行过滤，以第二坐标范围为目标车位的坐标范围为例，对处于第二坐标范围内的坐标进行过滤删除，得到不在第二坐标范围内的各备选路沿点坐标，将此部分坐标作为第一路沿点坐标。
A2、将与参考坐标的水平距离不超过第一预设距离阈值的各备选路沿点坐标作为第一路沿点坐标。
在本实施例中，第一预设距离阈值具体可以理解为预先设置的阈值，例如，1m。确定各备选路沿点坐标与参考坐标的水平距离，例如，计算横坐标的差值的绝对值作为水平距离，将与水平距离不超过第一预设距离阈值的各备选路沿点坐标作为第一路沿点坐标。实现横向的粗过滤。
A3、根据各第一路沿点坐标确定参考路沿点坐标，确定各第一路沿点坐标与参考路沿点坐标的水平距离。
参考路沿点坐标可以是从各第一路沿点坐标中按照时间、坐标等规则筛选出的，也可以是对各第一路沿点坐标进行运算、例如，计算平均值、最小值等方式得到的。示例性的，比较各第一路沿点的采集时间，将采集时间最新的第一路沿点坐标确定为参考路沿点坐标。通过计算横坐标的差值的绝对值确定各第一路沿点坐标与参考路沿点坐标的水平距离。
A4、将水平距离小于第二预设距离阈值的各第一路沿点坐标确定为目标路沿点坐标。
在本实施例中，第二预设距离阈值具体可以理解为预先设置的阈值，例如，20cm。判断各水平距离与第二预设距离阈值的大小，将水平小于第二预设距离阈值的各第一路沿点坐标确定为目标路沿点坐标。实现横向的进一步过滤。
示例性的，图4为本申请实施例提供的一种目标车位和候选路沿点的展示示意图，如图4所示，目标车位为41，各候选路沿点42(候选路沿点的坐标为候选路沿点坐标)分布在目标车位41、车位43和车位44附近，通过第一坐标范围、第二坐标范围和参考坐标对各候选路沿点坐标进行过滤，得到目标路沿点45(目标路沿点的坐标为目标路沿点坐标)。图5为本申请实施例提供的一种目标车位和目标路沿点的展示示意图。需要知道的是，图4中类似的点均为候选路沿点42，图中未进行一一标注，本领域技术人员可以知晓；相应的，图5中类似的点均为目标路沿点，图中未进行一一标注，本领域技术人员可以知晓。
S212、对各目标路沿点坐标进行数据拟合，确定路沿。
在确定各目标路沿点坐标后，通过对各目标路沿点坐标进行数据拟合得到路沿，拟合方式可以是最小二乘法等，通过最小二乘法可以将最终过滤处理后的各目标路沿点坐标拟合成路沿直线方程(y＝kx+b)。
S213、根据目标车位坐标集合确定目标车位的参考顶点坐标。
在本实施例中，参考顶点坐标具体可以理解为目标车位作为参考点的顶点的坐标。根据目标车位坐标集合确定目标车位的四个顶点，将远离路沿一侧的两个顶点中的任意一个作为参考顶点，将此顶点的坐标确定为参考顶点坐标。
S214、计算路沿与参考顶点坐标的距离，作为目标车位与路沿的距离。
根据点与直线之间的距离的计算公式计算路沿与参考顶点坐标之间的距离，将此距离作为目标车位与路沿的距离。目标车位与路沿的距离也用于自 动泊车时规划路径，避免车辆碰撞路沿。
示例性的，图6为本申请实施例提供的一种目标车位和路沿的展示示意图，目标车位51与路沿52的相对位置如图所示，将车位顶点A的坐标作为参考顶点坐标，计算车位顶点A与路沿52的距离，作为目标车位与路沿的距离。
本申请基于路沿检测装置探测路沿点距离，计算出路沿的深度信息，并用于自动泊车，可以做到车辆的灵活控制，避免车辆撞击路沿，损坏轮胎轮毂，而且对车辆泊车控制来说灵活性高。算法检测方法算力小，能在低成本硬件实施，可扩展性强。
本申请实施例提供了一种自动泊车路沿检测方法，解决了自动泊车时，路沿信息检测不准确以及成本较高的问题。通过路沿检测装置检测路沿点距离，根据路沿点距离确定路沿点坐标，在检测到车辆启动泊车后，获取路沿点坐标集合并对路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标，根据目标车位坐标集合对各候选路沿点坐标进行过滤，去掉误差较大的坐标点，得到目标路沿点坐标，通过目标路沿点坐标确定路沿，进一步确定目标车位和路沿的距离。本申请在检测路沿过程中，实现过程简单，只需要对路沿点坐标进行简单的数学处理即可，无需训练模型，路沿检测装置只需要采集路沿点距离即可确定路沿点坐标，检测结果准确、可靠，无需高成本的芯片，降低了成本。
实施例三
图7为本申请实施例三提供的一种自动泊车路沿检测装置的结构示意图。如图7所示，该装置包括：坐标获取模块61、坐标转换模块62、坐标过滤模块63和路沿距离确定模块64。
其中，坐标获取模块61，用于当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合，所述路沿点坐标集合包括至少一个路沿点坐标，所述目标车位坐标集合包括目标车位的至少一个目标车位坐标，所述路沿点坐标根据所述车辆上的路沿检测装置所采集的路沿点距离确定；
坐标转换模块62，用于对各所述路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标；
坐标过滤模块63，用于根据所述目标车位坐标集合对各所述候选路沿点坐标进行过滤，得到目标路沿点坐标；
路沿距离确定模块64，用于根据各所述目标路沿点坐标确定目标车位与 路沿的距离。
本申请实施例提供了一种自动泊车路沿检测装置，解决了自动泊车时，路沿信息检测不准确以及成本较高的问题。通过路沿检测装置检测路沿点距离，根据路沿点距离确定路沿点坐标，在检测到车辆启动泊车后，获取路沿点坐标集合并对路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标，根据目标车位坐标集合对各候选路沿点坐标进行过滤，去掉误差较大的坐标点，得到目标路沿点坐标，通过目标路沿点坐标确定路沿，进一步确定目标车位和路沿的距离。本申请在检测路沿过程中，实现过程简单，只需要对路沿点坐标进行简单的数学处理即可，无需训练模型，路沿检测装置只需要采集路沿点距离即可确定路沿点坐标，检测结果准确、可靠，无需高成本的芯片，降低了成本。
可选的，该装置还包括：
距离采集模块，用于当检测到车辆启动车位搜索时，根据车辆的当前位置建立全局坐标系，确定车辆初始坐标，并控制所述车辆上的路沿检测装置采集路沿点距离；
坐标存储模块，用于根据所述路沿点距离和所述路沿检测装置的安装位置信息确定路沿点坐标，并将所述路沿点坐标及其对应的采集时间存储至路沿点坐标集合中。
可选的，该装置还包括：
车位展示模块，用于当检测到车辆启动车位搜索后，获取待选车位信息并展示；
泊车启动模块，用于接收用户确定的目标车位，确定所述目标车位的目标车位坐标集合并控制车辆启动泊车。
可选的，坐标转换模块62包括：
实时坐标获取单元，用于针对每个路沿点坐标，获取所述路沿点坐标对应的车辆实时位置坐标；
偏移角度确定单元，用于根据所述车辆实时位置坐标与车辆初始坐标确定车辆偏移角度；
第一坐标转换单元，用于根据预设的第一转换公式结合所述车辆实时位置坐标和车辆偏移角度将所述路沿点坐标转换为全局坐标系下的全局路沿点坐标；
第二坐标转换单元，用于根据预设的第二转换公式结合当前车辆位置坐标和车辆偏移角度将所述全局路沿点坐标转换为当前时刻的车辆坐标系下的 候选路沿点坐标。
可选的，坐标过滤模块63包括：
第一过滤单元，用于根据所述目标车位坐标集合确定第一坐标范围、第二坐标范围和参考坐标，根据所述第一坐标范围对各所述候选路沿点坐标进行过滤，将在第一坐标范围内的各候选路沿点坐标作为备选路沿点坐标；
第二过滤单元，用于根据所述第二坐标范围和参考坐标对各所述备选路沿点坐标进行过滤，确定至少一个目标路沿点坐标。
可选的，第二过滤单元具体用于：根据所述第二坐标范围对各所述备选路沿点坐标进行过滤，将不在所述第二坐标范围内的各所述备选路沿点坐标作为第一路沿点坐标；将与所述参考坐标的水平距离不超过第一预设距离阈值的各所述备选路沿点坐标作为第一路沿点坐标；根据各所述第一路沿点坐标确定参考路沿点坐标，确定各所述第一路沿点坐标与所述参考路沿点坐标的水平距离；将水平距离小于第二预设距离阈值的各所述第一路沿点坐标确定为目标路沿点坐标。
可选的，路沿距离确定模块64包括：
数据拟合单元，用于对各所述目标路沿点坐标进行数据拟合，确定路沿；
参考坐标确定单元，用于根据所述目标车位坐标集合确定目标车位的参考顶点坐标；
距离确定单元，用于计算所述路沿与所述参考顶点坐标的距离，作为目标车位与路沿的距离。
本申请实施例所提供的自动泊车路沿检测装置可执行本申请任意实施例所提供的自动泊车路沿检测方法，具备执行方法相应的功能模块和效果。
实施例四
图8示出了可以用来实施本申请的实施例的车辆的结构示意图。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本申请的实现。
如图8所示，车辆包括路沿检测装置70，用于采集路沿点距离。路沿检测装置70的数量可以是一个，也可以是多个，图8以一个为例。车辆包括至少一个处理器71，以及与至少一个处理器71通信连接的存储器，如只读存储器(ROM)72、随机访问存储器(RAM)73等，其中，存储器存储有可被至少一个处理器执行的计算机程序，处理器71可以根据存储在只读存储器 (ROM)72中的计算机程序或者从存储单元78加载到随机访问存储器(RAM)73中的计算机程序，来执行各种适当的动作和处理。在RAM 73中，还可存储车辆操作所需的各种程序和数据。处理器71、ROM 72以及RAM 73通过总线74彼此相连。输入/输出(I/O)接口75也连接至总线74。
车辆中的多个部件连接至I/O接口75，包括：输入单元76，例如键盘、鼠标等；输出单元77，例如各种类型的显示器、扬声器等；存储单元78，例如磁盘、光盘等；以及通信单元79，例如网卡、调制解调器、无线通信收发机等。通信单元79允许车辆通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
处理器71可以是各种具有处理和计算能力的通用和/或专用处理组件。处理器71的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的处理器、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。处理器71执行上文所描述的各个方法和处理，例如自动泊车路沿检测方法。
在一些实施例中，自动泊车路沿检测方法可被实现为计算机程序，其被有形地包含于计算机可读存储介质，例如存储单元78。在一些实施例中，计算机程序的部分或者全部可以经由ROM 72和/或通信单元79而被载入和/或安装到车辆上。当计算机程序加载到RAM 73并由处理器71执行时，可以执行上文描述的自动泊车路沿检测方法的一个或多个步骤。备选地，在其他实施例中，处理器71可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行自动泊车路沿检测方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、复杂可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本申请的方法的计算机程序可以采用一个或多个编程语言的任何组合来编写。这些计算机程序可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器，使得计算机程序当由处理器执行时使流程图 和/或框图中所规定的功能/操作被实施。计算机程序可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本申请的上下文中，计算机可读存储介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的计算机程序。计算机可读存储介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。备选地，计算机可读存储介质可以是机器可读信号介质。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在车辆上实施此处描述的系统和技术，该车辆具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给车辆。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)、区块链网络和互联网。
计算系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，又称为云计算服务器或云主机，是云计算服务体系中的一项主机产品，以解决了传统物理主机与VPS中，存在的管理难度大，业务扩展性弱的 缺陷。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本申请中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本申请的技术方案所期望的结果，本文在此不进行限制。

Claims (10)

  1. 一种自动泊车路沿检测方法，包括：
    当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合，所述路沿点坐标集合包括至少一个路沿点坐标，所述目标车位坐标集合包括目标车位的至少一个目标车位坐标，所述路沿点坐标根据所述车辆上的路沿检测装置所采集的路沿点距离确定；
    对各所述路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标；
    根据所述目标车位坐标集合对各所述候选路沿点坐标进行过滤，得到目标路沿点坐标；
    根据各所述目标路沿点坐标确定目标车位与路沿的距离。
  2. 根据权利要求1所述的方法，在所述当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合之前，包括：
    当检测到车辆启动车位搜索时，根据车辆的当前位置建立全局坐标系，确定车辆初始坐标，并控制所述车辆上的路沿检测装置采集路沿点距离；
    根据所述路沿点距离和所述路沿检测装置的安装位置信息确定路沿点坐标，并将所述路沿点坐标及其对应的采集时间存储至路沿点坐标集合中。
  3. 根据权利要求1所述的方法，在所述当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合之前，包括：
    当检测到车辆启动车位搜索后，获取待选车位信息并展示；
    接收用户确定的目标车位，确定所述目标车位的目标车位坐标集合并控制车辆启动泊车。
  4. 根据权利要求2所述的方法，其中，所述对各所述路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标，包括：
    针对每个路沿点坐标，获取所述路沿点坐标对应的车辆实时位置坐标；
    根据所述车辆实时位置坐标与车辆初始坐标确定车辆偏移角度；
    根据预设的第一转换公式结合所述车辆实时位置坐标和车辆偏移角度将所述路沿点坐标转换为全局坐标系下的全局路沿点坐标；
    根据预设的第二转换公式结合当前车辆位置坐标和车辆偏移角度将所述全局路沿点坐标转换为当前时刻的车辆坐标系下的候选路沿点坐标。
  5. 根据权利要求1所述的方法，其中，根据所述目标车位坐标集合对各所 述候选路沿点坐标进行过滤，得到目标路沿点坐标，包括：
    根据所述目标车位坐标集合确定第一坐标范围、第二坐标范围和参考坐标，根据所述第一坐标范围对各所述候选路沿点坐标进行过滤，将在第一坐标范围内的各候选路沿点坐标作为备选路沿点坐标；
    根据所述第二坐标范围和参考坐标对各所述备选路沿点坐标进行过滤，确定至少一个目标路沿点坐标。
  6. 根据权利要求5所述的方法，其中，所述根据所述第二坐标范围对各所述备选路沿点坐标进行过滤，确定至少一个目标路沿点坐标，包括：
    根据所述第二坐标范围对各所述备选路沿点坐标进行过滤，将不在所述第二坐标范围内的各所述备选路沿点坐标作为第一路沿点坐标；
    将与所述参考坐标的水平距离不超过第一预设距离阈值的各所述备选路沿点坐标作为第一路沿点坐标；
    根据各所述第一路沿点坐标确定参考路沿点坐标，确定各所述第一路沿点坐标与所述参考路沿点坐标的水平距离；
    将水平距离小于第二预设距离阈值的各所述第一路沿点坐标确定为目标路沿点坐标。
  7. 根据权利要求1所述的方法，其中，所述根据各所述目标路沿点坐标确定目标车位与路沿的距离，包括：
    对各所述目标路沿点坐标进行数据拟合，确定路沿；
    根据所述目标车位坐标集合确定目标车位的参考顶点坐标；
    计算所述路沿与所述参考顶点坐标的距离，作为目标车位与路沿的距离。
  8. 一种自动泊车路沿检测装置，包括：
    坐标获取模块，用于当检测到车辆启动泊车后，获取路沿点坐标集合和目标车位坐标集合，所述路沿点坐标集合包括至少一个路沿点坐标，所述目标车位坐标集合包括目标车位的至少一个目标车位坐标，所述路沿点坐标根据所述车辆上的路沿检测装置所采集的路沿点距离确定；
    坐标转换模块，用于对各所述路沿点坐标进行坐标系转换，得到当前时刻的车辆坐标系下的候选路沿点坐标；
    坐标过滤模块，用于根据所述目标车位坐标集合对各所述候选路沿点坐标进行过滤，得到目标路沿点坐标；
    路沿距离确定模块，用于根据各所述目标路沿点坐标确定目标车位与路沿 的距离。
  9. 一种车辆，包括：
    路沿检测装置，用于采集路沿点距离；
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的计算机程序，所述计算机程序被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-7中任一项所述的自动泊车路沿检测方法。
  10. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，所述计算机指令用于使处理器执行时实现权利要求1-7中任一项所述的自动泊车路沿检测方法。
PCT/CN2022/102627 2022-05-26 2022-06-30 一种自动泊车路沿检测方法、装置、车辆及存储介质 WO2023226147A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210585472.2A CN115743159A (zh) 2022-05-26 2022-05-26 一种自动泊车路沿检测方法、装置、车辆及存储介质
CN202210585472.2 2022-05-26

Publications (1)

Publication Number Publication Date
WO2023226147A1 true WO2023226147A1 (zh) 2023-11-30

Family

ID=85349476

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/102627 WO2023226147A1 (zh) 2022-05-26 2022-06-30 一种自动泊车路沿检测方法、装置、车辆及存储介质

Country Status (2)

Country Link
CN (1) CN115743159A (zh)
WO (1) WO2023226147A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190251842A1 (en) * 2018-02-15 2019-08-15 Robert Bosch Gmbh System and method for distributed parking area map generation and parking area service using in-vehicle sensors
CN110293964A (zh) * 2019-06-25 2019-10-01 重庆长安汽车股份有限公司 自动泊车融合车位判断方法、系统、计算机可读存储介质及车辆
CN110435638A (zh) * 2019-06-28 2019-11-12 惠州市德赛西威汽车电子股份有限公司 一种泊车位自动跟踪方法
CN110673107A (zh) * 2019-08-09 2020-01-10 北京智行者科技有限公司 基于多线激光雷达的路沿检测方法及装置
CN113051765A (zh) * 2021-03-31 2021-06-29 中国科学院合肥物质科学研究院 一种基于虚拟场景变换的智能驾驶车辆车路在环测试方法
CN114170579A (zh) * 2020-08-21 2022-03-11 广州汽车集团股份有限公司 一种路沿检测方法、装置及汽车

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190251842A1 (en) * 2018-02-15 2019-08-15 Robert Bosch Gmbh System and method for distributed parking area map generation and parking area service using in-vehicle sensors
CN110293964A (zh) * 2019-06-25 2019-10-01 重庆长安汽车股份有限公司 自动泊车融合车位判断方法、系统、计算机可读存储介质及车辆
CN110435638A (zh) * 2019-06-28 2019-11-12 惠州市德赛西威汽车电子股份有限公司 一种泊车位自动跟踪方法
CN110673107A (zh) * 2019-08-09 2020-01-10 北京智行者科技有限公司 基于多线激光雷达的路沿检测方法及装置
CN114170579A (zh) * 2020-08-21 2022-03-11 广州汽车集团股份有限公司 一种路沿检测方法、装置及汽车
CN113051765A (zh) * 2021-03-31 2021-06-29 中国科学院合肥物质科学研究院 一种基于虚拟场景变换的智能驾驶车辆车路在环测试方法

Also Published As

Publication number Publication date
CN115743159A (zh) 2023-03-07

Similar Documents

Publication Publication Date Title
WO2018177026A1 (zh) 确定道路边沿的装置和方法
KR20190082065A (ko) 포인트 클라우드 데이터를 처리하기 위한 방법 및 장치
EP3825903A1 (en) Method, apparatus and storage medium for detecting small obstacles
KR102083482B1 (ko) 라이다 기반의 차량주행 가능영역 검출장치 및 방법
EP3957955A2 (en) Vehicle locating method and apparatus, electronic device, storage medium and computer program product
CN112836633A (zh) 停车位检测方法以及停车位检测系统
EP3968266B1 (en) Obstacle three-dimensional position acquisition method and apparatus for roadside computing device
JP2017068700A (ja) 物体検出装置、物体検出方法、及びプログラム
CN114966734A (zh) 一种结合多线激光雷达的双向深度视觉惯性位姿估计方法
WO2024066943A1 (zh) 应用于车辆的智能泊车车辆定位的方法
CN114323033B (zh) 基于车道线和特征点的定位方法、设备及自动驾驶车辆
WO2023155387A1 (zh) 多传感器目标检测方法、装置、电子设备以及存储介质
CN111402161A (zh) 点云障碍物的去噪方法、装置、设备和存储介质
WO2021017211A1 (zh) 一种基于视觉的车辆定位方法、装置及车载终端
WO2023088486A1 (zh) 车道线提取方法、装置、车辆及存储介质
JP2016177718A (ja) 物体検出装置、物体検出方法および情報処理プログラム
US20200193184A1 (en) Image processing device and image processing method
WO2022116831A1 (zh) 定位方法、装置、电子设备及可读存储介质
JP6199693B2 (ja) 車間距離測定装置、車間距離測定方法、およびプログラム
WO2023226147A1 (zh) 一种自动泊车路沿检测方法、装置、车辆及存储介质
CN116543032B (zh) 冲击物测距方法、装置、测距设备及存储介质
WO2023241556A1 (zh) 泊车控制方法、装置、设备和存储介质
CN116772858A (zh) 车辆定位方法、装置、定位设备及存储介质
JP2009229180A (ja) ナビゲーション装置
CN114333390B (zh) 共享车辆停放事件的检测方法、装置及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22943339

Country of ref document: EP

Kind code of ref document: A1