Obstacle positioning method, parking space generation method, related equipment and medium

Abstract

The invention discloses an obstacle positioning method, a parking space generation method, related equipment and a medium, which are applied to a vehicle with a plurality of radars arranged at the tail of the vehicle, the radars located at the two sides of the tail of the vehicle in the plurality of radars are outer radars, and the normal of the outer radars and the central axis of the vehicle form an angle. The obstacle positioning method comprises the following steps: acquiring side edge detection data of an outer side radar; and determining position information of the side obstacle point of the vehicle based on the side detection data. By means of the mode, the position information of the side obstacle point of the vehicle is determined by obtaining the side detection data of the outer side radar, the obstacle detection range of the vehicle can be widened, and a radar does not need to be additionally arranged on the side of the vehicle to detect the side obstacle.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an obstacle positioning method, a parking space generation method, and related equipment and media. Background Art

[0002] At present, vehicles are usually equipped with several radars. Multiple radars installed at the front and rear of the vehicle are used to detect obstacles behind the vehicle, and multiple radars installed on both sides of the vehicle are used to detect obstacles on both sides of the vehicle, so as to achieve all-round detection of the vehicle. However, this method requires the installation of more radars, which is costly and is not suitable for low-end models. Summary of the invention

[0003] The main technical problem solved by the present application is to provide an obstacle positioning method, a parking space generation method and related equipment and media, which can obtain the side detection data of the outer radar to determine the location information of the side obstacle points of the vehicle, thereby improving the obstacle detection range of the vehicle and eliminating the need to add additional radars on the side of the vehicle to detect side obstacles.

[0004] In order to solve the above technical problems, a technical solution adopted in the present application is: to provide an obstacle locating method, which is applied to a vehicle with multiple radars at the rear of the vehicle, wherein the radars located on both sides of the rear of the vehicle are outer radars, and the normal of the outer radar is at an angle to the central axis of the vehicle. The obstacle locating method includes: obtaining side detection data of the outer radar; based on the side detection data, determining the position information of the side obstacle points of the vehicle.

[0005] Optionally, the angle between the normal line of the outer radar and the center axis of the vehicle is 25-45 degrees.

[0006] Optionally, determining the position information of the side obstacle point of the vehicle based on the side detection data includes: performing triangulation using two adjacent frames of side detection data of the outer radar to obtain the position information of the side obstacle point of the vehicle;

[0007] Optionally, two adjacent frames of side detection data include side detection data at a previous detection moment and side detection data at a current detection moment; two adjacent frames of side detection data of the outer radar are used to perform triangulation to obtain position information of side obstacle points of the vehicle, including: using the side detection data at a previous detection moment to determine a first distance between the outer radar and the side obstacle point; and using the side detection data at a current detection moment to determine a second distance between the outer radar and the side obstacle point; determining first global position information and second global position information corresponding to the outer radar at a previous detection moment and a current detection moment, respectively; and determining the position information of the side obstacle point using the first distance, the second distance, the first global position information, and the second global position information.

[0008] Optionally, the target detection time is any detection time of the outer radar, and the step of determining the global position information of the outer radar at the target detection time includes: obtaining the global position information of the vehicle at the target detection time; using the global position information of the vehicle at the target detection time and the position parameters of the outer radar about the vehicle to determine the global position information of the outer radar at the target detection time.

[0009] And / or, after determining the first global position information and the second global position information corresponding to the outer radar at the last detection moment and the current detection moment respectively, the method also includes: performing at least one of the first check and the second check; wherein the first check step includes: determining the third distance based on the first global position information and the second global position information; in response to the first distance, the second distance and the third distance not satisfying the triangle formation condition, filtering out the side detection data at the last detection moment; the second check step includes: determining the first detection angle and the second detection angle, wherein the first detection angle is the angle between the first side and the second side, the second detection angle is the angle between the second side and the third side, the two endpoints of the first side are the side obstacle point and the outer radar at the last detection moment, the two endpoints of the second side are the outer radar at the last detection moment and the outer radar at the current detection moment, and the two endpoints of the third side are the side obstacle point and the outer radar at the current detection moment; in response to at least one of the first detection angle and the second detection angle exceeding the detection angle range of the outer radar, filtering out the side detection data at the last detection moment.

[0010] Optionally, the method further includes: performing triangulation using detection data from adjacent radar pairs to obtain position information of obstacle points on the rear side of the vehicle.

[0011] To solve the above technical problems, another technical solution adopted in the present application is: to provide a parking space generation method, which is applied to a vehicle with multiple radars installed at the rear of the vehicle, wherein the radars located on both sides of the rear of the vehicle are outer radars, and the normal of the outer radar is at an angle with the central axis of the vehicle. The parking space generation method includes: using the side detection data of the outer radar to determine the position information of several side obstacle points of the vehicle; based on the position information of the several side obstacle points, fitting at least one side obstacle line segment; based on the at least one side obstacle line segment, determining a parking space area for the vehicle.

[0012] Optionally, based on the position information of several side obstacle points, at least one side obstacle line segment is fitted, including: based on the position information of several side obstacle points, each side obstacle point is clustered to obtain several first clustering point clusters; and each first clustering point cluster is respectively fitted to obtain a corresponding side obstacle line segment.

[0013] Optionally, based on the position information of several side obstacle points, each side obstacle point is clustered to obtain several first clustering point clusters, including: determining the distance between the side obstacle points at two adjacent detection moments based on the position information of the side obstacle points at two adjacent detection moments; and determining whether the side obstacle points at two adjacent detection moments are divided into the same clustering point cluster or different clustering point clusters based on whether the distance between the side obstacle points at two adjacent detection moments meets the distance clustering requirements.

[0014] Optionally, after determining a parking area for the vehicle based on at least one side obstacle line segment, the method further includes: determining position information of several parking obstacle points in the parking area using detection data of at least one radar during the process of the vehicle parking in the parking area; and adjusting the size of the parking area based on the position information of the several parking obstacle points.

[0015] Optionally, based on the position information of several parking space obstacle points, the size of the parking space area is adjusted, including: clustering based on the position information of several parking space obstacle points to obtain several second clustering point clusters; fitting each second clustering point cluster to obtain a corresponding parking space obstacle line segment; and adjusting the parking space area to be within the restricted space formed by each parking space obstacle line segment.

[0016] Optionally, after fitting each first cluster point cluster to obtain a corresponding side obstacle line segment, or fitting each second cluster point cluster to obtain a corresponding parking space obstacle line segment, the method further includes: corresponding to each fitted obstacle line segment, counting the distances from each obstacle point in the cluster point cluster corresponding to the obstacle line segment to the obstacle line segment to obtain a distance statistic value; in response to the distance statistic value satisfying the segmentation requirement, selecting an obstacle point whose distance meets a preset distance requirement from the cluster point cluster corresponding to the obstacle line segment as a segmentation point; fitting two new obstacle line segments based on the obstacle points between the segment start point and the segmentation point of the obstacle line segment and the obstacle points between the segmentation point and the segment end point of the obstacle line segment, and for the new two obstacle line segments, re-executing the distance statistics from each obstacle point corresponding to the obstacle line segment to the obstacle line segment to obtain the distance statistic value and subsequent steps, until the distance statistic value of the obstacle line segment does not meet the segmentation requirement.

[0017] Optionally, before the step of determining a parking area for the vehicle based on at least one side obstacle line segment, or adjusting the parking area to be within the restricted space formed by the parking obstacle line segments, at least one of the following steps is further included: selecting abnormal line segments having a length less than a preset length from the obstacle line segments obtained by fitting, and deleting the abnormal line segments; and merging the side obstacle line segments with the parking obstacle line segments on both sides of the parking area obtained by fitting in the parking stage.

[0018] Optionally, before adjusting the size of the parking area based on the position information of several parking space obstacle points, it also includes: spatially clustering the several currently determined parking space obstacle points to obtain a spatial clustering result; finding outliers in the spatial clustering result; in response to the proportion of outliers detected within a preset time period not meeting the requirements of the real obstacle proportion, deleting the outliers.

[0019] Optionally, a parking area is determined for a vehicle based on at least one side obstacle line segment, including: determining a parking space and a parking space type of the parking space based on distances between side obstacle line segments and / or lengths of parking space-related line segments; determining a parking area based on the parking space type of the parking space and positions of side obstacle line segments on the sides of the parking space.

[0020] Optionally, based on the distance between the side obstacle line segments and / or the length of the parking space-related line segments, determining the parking space and the parking space type to which the parking space belongs includes: in response to the distance between two adjacent first side obstacle line segments in the vehicle's forward direction being greater than the vehicle width of the vehicle, and the length of the first side obstacle line segment in the vehicle's forward direction being less than the sum of the vehicle width and a first value, determining that the space between two adjacent first side obstacle line segments is a parking space, and the parking space is a vertical parking space; in response to the distance between two adjacent second side obstacle line segments in the vehicle's forward direction being greater than the vehicle length of the vehicle, and the length of the second side obstacle line segment in the vehicle's forward direction being less than the sum of the vehicle width and a first value; Based on the sum of the vehicle length and the second value, it is determined that the space between two adjacent second side obstacle line segments is a parking space, and the parking space is a parallel parking space; in response to the distance between two adjacent third side obstacle line segments in the direction perpendicular to the vehicle's forward movement is greater than the vehicle width, the third side obstacle line segment far from the vehicle in the two adjacent third side obstacle line segments is determined to be a curb segment, and it is detected whether the side obstacle line segment after the curb segment is a curb segment; in response to the length of at least one continuous curb segment in the vehicle's forward movement is greater than the vehicle length, it is determined that there is a parking space for at least one continuous curb segment, and the parking space is a parallel parking space with a curb.

[0021] And / or, determining the parking area based on the parking space type of the parking space and the position of the side obstacle line segment on the edge of the parking space, including: determining the outer corner point of the parking area based on the position of the side obstacle line segment on the edge of the parking space; determining the inner corner point of the parking area according to the size and outer corner point corresponding to the parking space type; determining the orientation angle of the parking area based on the orientation angle of the side obstacle line segment on the edge of the parking space and the historical heading angle of the vehicle; adjusting the inner and outer corner points of the parking area based on the orientation angle of the parking area.

[0022] Optionally, the position information of the side obstacle point is realized by using the aforementioned obstacle positioning method.

[0023] To solve the above technical problems, another technical solution adopted in the present application is: to provide an electronic device, including a memory and a processor coupled to each other, the memory storing program instructions; the processor is used to execute the program instructions stored in the memory to implement the above obstacle positioning method or parking space generation method.

[0024] In order to solve the above technical problems, another technical solution adopted in the present application is: providing a computer-readable storage medium, which is used to store program instructions, and the program instructions can be executed by a processor to implement the above obstacle positioning method or parking space generation method.

[0025] The above scheme adjusts the installation angle of the outer radar so that the normal of the outer radar is at an angle with the central axis of the vehicle. In this way, the side detection data of the outer radar can be obtained to determine the position information of the side obstacle points of the vehicle, which can improve the obstacle detection range of the vehicle and there is no need to add additional radars on the side of the vehicle to detect side obstacles. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic diagram of the arrangement of the rear radar provided by this application;

[0027] Figure 2 It is a flowchart of an embodiment of an obstacle positioning method provided by the present application;

[0028] Figure 3 is a flow chart of another embodiment of the obstacle locating method provided by the present application;

[0029] Figure 4 It is a schematic diagram of the principle of timing triangulation provided by this application;

[0030] Figure 5 It is a flow chart of an embodiment of a method for time-series triangulation of side obstacle points provided by the present application;

[0031] Figure 6 is a flow chart of an embodiment of a parking space generation method provided by the present application;

[0032] Figure 7 is a flow chart of an embodiment of a method for determining a parking space area provided by the present application;

[0033] Figure 8 is a schematic diagram of the three types of parking spaces provided in this application;

[0034] Fig. 9 is a schematic diagram of the fusion of side obstacle line segments and parking space obstacle line segments provided by the present application;

[0035] Fig.10It is a schematic diagram of a framework of an embodiment of an electronic device provided by the present application;

[0036] Fig.11 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium provided by the present application. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and effect of the present application clearer and more specific, the present application is further described in detail below with reference to the accompanying drawings and examples.

[0038] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0039] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C, it can mean including any one or more elements selected from the set consisting of A, B and C. "Several" means at least one. The terms "first", "second", etc. in the specification and claims of this article and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0040] See also Figure 1 , Figure 1 Schematic diagram of the layout of the rear radar provided by this application. Figure 1 As shown, radars A, B, C and D are arranged at the rear of the vehicle (four radars are used for exemplary illustration in the figure). Among the multiple radars, radar A and radar D located on both sides of the rear of the vehicle are outer radars, and the radars located between the two outer radars A and D are inner radars B and C. For example, radars A, B, C and D are all UPA (Ultrasonic Parking Assistant) radars.

[0041] In the related art, the normals of the four radars A, B, C and D are parallel to the central axis of the vehicle, that is, the four radars A, B, C and D are only used to detect obstacles behind the vehicle (especially low-end models). In this embodiment, the installation angle of the outer radar is adjusted so that the normal of the outer radar is at an angle with the central axis of the vehicle. Exemplarily, the angle between the normal of the outer radar and the central axis of the vehicle is 25-45 degrees. In this way, the outer radar can detect obstacles on the side of the vehicle, and form a certain overlapping detection area with the adjacent inner radar to form a triangulation relationship with the adjacent inner radar to detect obstacles behind the vehicle. With this radar arrangement, only the installation angle of the outer radar needs to be adjusted to improve the obstacle detection range of the vehicle while ensuring the detection accuracy of the rear obstacles, and there is no need to add additional radars on the side of the vehicle, so the cost is low.

[0042] See also Figure 2 , Figure 2 1 is a flow chart of an embodiment of an obstacle location method provided by the present application. The method is applied to a vehicle with multiple radars at the rear, where the normal of the outer radars among the multiple radars is at an angle to the central axis of the vehicle. Figure 2 As shown, the method comprises the following steps:

[0043] S21: Acquire the side detection data of the outer radar.

[0044] S22: Determine the position information of the side obstacle point of the vehicle based on the side detection data.

[0045] In this embodiment, by adjusting the installation angle of the outer radar so that the normal of the outer radar is at an angle with the central axis of the vehicle, the side detection data of the outer radar can be obtained to determine the position information of the side obstacle points of the vehicle, thereby improving the obstacle detection range of the vehicle and eliminating the need to add additional radars on the side of the vehicle to detect side obstacles.

[0046] See also Figure 3 , Figure 3 FIG. 1 is a flow chart of another embodiment of the obstacle location method provided by the present application. Figure 3 As shown, the method comprises the following steps:

[0047] S31: Acquire side detection data of the outer radar.

[0048] The side detection data of the outer radar includes the time interval from when the outer radar sends a detection wave signal to when it receives an echo signal.

[0049] S32: Perform triangulation using two adjacent frames of side detection data from the outer radar to obtain position information of the side obstacle point of the vehicle.

[0050] The two adjacent frames of side edge detection data include the side edge detection data at the previous detection moment and the side edge detection data at the current detection moment.

[0051] In this embodiment, it is considered that the measurements of the same side obstacle point by the outer radar at different detection times constitute a triangular relationship in time sequence, and thus the position information of the side obstacle point is determined.

[0052] Figure 4 Schematic diagram of the principle of timing triangulation provided by this application. Figure 4 As shown, the positions of the outer radar at time (k-1) and time k are point a and point b respectively, point O is the side obstacle point, and point a, point b and point O form a triangular relationship in time sequence.

[0053] Figure 5 FIG. 1 is a flow chart of an embodiment of a method for time-series triangulation of side obstacle points provided by the present application. Figure 5 As shown, the method comprises the following steps:

[0054] S501: Determine a first distance between the outer radar and the side obstacle point using the side detection data at the previous detection time; and determine a second distance between the outer radar and the side obstacle point using the side detection data at the current detection time.

[0055] In step S501, the first distance between the outer radar and the side obstacle point at the previous detection moment can be calculated using the side detection data at the previous detection moment and the propagation speed of the detection signal. The second distance between the outer radar and the side obstacle point at the current detection moment can be calculated using the side detection data at the current detection moment and the propagation speed of the detection signal. Both the first distance and the second distance are direct distances detected by the outer radar in the self-transmitting and self-receiving mode.

[0056] S502: Determine the first global position information and the second global position information corresponding to the outer radar at the previous detection time and the current detection time, respectively.

[0057] The target detection time is any detection time of the outer radar, and the step of determining the global position information of the outer radar at the target detection time includes: obtaining the global position information of the vehicle at the target detection time; using the global position information of the vehicle at the target detection time and the position parameters of the outer radar about the vehicle to determine the global position information of the outer radar at the target detection time.

[0058] Among them, the position parameters of the outer radar relative to the vehicle are the local coordinates of the outer radar relative to the vehicle. The global position information of the outer radar at the time of target detection can be calculated by the following formula:

[0059] X r =Xv +d*cos(θ)

[0060] Y r =Y v +d*sin(θ)

[0061] Where, (d*cosθ, d*sinθ) are the local coordinates of the outer radar relative to the vehicle, d and θ are the horizontal distance and deflection angle of the outer radar relative to the vehicle reference point (such as the center point of the vehicle, the center point of the rear axle), respectively; (X v , Y v ) is the global position information of the vehicle at the time of target detection.

[0062] In step S502, the global position information of the vehicle at the last detection time and the global position information at the current detection time can be obtained respectively, and then the first global position information of the outer radar at the last detection time and the second global position information at the current detection time can be calculated respectively using the above calculation formula.

[0063] In practical applications, the detection time of the side radar and the positioning time of the vehicle's global position information are not aligned in the time dimension. In order to improve the accuracy of the determined global position information of the side radar and further improve the accuracy of the positioning of the side obstacle point, the acquired vehicle global position information can be fitted (e.g., linear fitting) to obtain a fitting function, and the vehicle global position information corresponding to each detection time can be determined using the fitting function, so that each detection time of the side radar has the vehicle global position information of the corresponding detection time, thereby achieving synchronization in the time dimension.

[0064] S503: Determine the position information of the side obstacle point by using the first distance at the last detection moment, the second distance at the current detection moment, the first global position information of the outer radar at the last detection moment, and the second global position information of the outer radar at the current detection moment.

[0065] Specifically, a set of equations about the coordinates of the side obstacle points can be constructed using the first distance at the last detection moment, the second distance at the current detection moment, the first global position information of the outer radar at the last detection moment, and the second global position information of the outer radar at the current detection moment, and then the position information of the side obstacle points can be solved.

[0066] Optionally, after determining the first global position information and the second global position information corresponding to the outer radar at the previous detection moment and the current detection moment respectively, at least one of the first check and the second check needs to be performed to filter out noise data.

[0067] In one embodiment, the first check includes the following steps:

[0068] Step 1: Determine a third distance based on the first global position information at the last detection moment and the second global position information at the current detection moment.

[0069] The third distance is the distance between the position point where the outer radar is located at the last detection moment and the position point where the outer radar is located at the current detection moment.

[0070] Step 2: In response to the first distance, the second distance and the third distance not satisfying the triangle formation condition, filtering out the side detection data at the last detection moment.

[0071] Among them, the conditions for forming a triangle include: the sum of any two sides is greater than the third side.

[0072] In step 2, the first distance, the second distance and the third distance can be used as the three sides of the triangle respectively, and then the three sides are verified to see whether they meet the above triangle formation conditions. If they do not meet the triangle formation conditions, the side detection data at the previous detection time is filtered out as noise data.

[0073] In one embodiment, the second check includes the following steps:

[0074] Step 1: determine a first detection angle and a second detection angle.

[0075] Among them, the first detection angle is the angle between the first side and the second side, the second detection angle is the angle between the second side and the third side, the two endpoints of the first side are the side obstacle point and the outer radar at the last detection moment, the two endpoints of the second side are the outer radar at the last detection moment and the outer radar at the current detection moment, and the two endpoints of the third side are the side obstacle point and the outer radar at the current detection moment.

[0076] Step 2: In response to at least one of the first detection angle and the second detection angle exceeding the detection angle range of the outer radar, filtering out the side detection data at the last detection moment.

[0077] The detection angle range of the outer radar refers to the horizontal FOV angle of the outer radar.

[0078] In this embodiment, by using two adjacent frames of side detection data of the outer radar to perform triangulation, accurate position information of the side obstacle point can be determined and the tailing phenomenon can be reduced.

[0079] In this embodiment, the detection data of the adjacent radar pairs can also be used to perform triangulation to obtain the position information of the obstacle point on the rear side of the vehicle.

[0080] Please refer again Figure 1, four radars, radar A, radar B, radar C and radar D, exist in three adjacent radar pairs, radar A and radar B, radar B and radar C, radar C and radar D. The detection data of adjacent radar pairs include direct detection data of each radar in the adjacent radar pair in the self-transmitting and self-receiving mode, and indirect detection data of each radar in the self-transmitting and self-receiving mode. For example, the detection data of the adjacent radar pair, radar A and radar B, includes direct detection data of radar A, direct detection data of radar B, indirect detection data sent by radar A and received by radar B, and indirect detection data sent by radar B and received by radar A.

[0081] The process of performing triangulation using detection data from adjacent radar pairs may refer to the relevant description of the prior art and will not be described in detail in this embodiment.

[0082] See also Figure 6 , Figure 6 1 is a flow chart of an embodiment of a parking space generation method provided by the present application. Figure 6 As shown, the method comprises the following steps:

[0083] S61: Using the side detection data of the outer radar, determine the position information of several side obstacle points of the vehicle.

[0084] For details on determining the location information of side obstacle points, please refer to the above Figures 2 to 5 The illustrated embodiments will not be described in detail here.

[0085] S62: Based on the position information of a plurality of side obstacle points, at least one side obstacle line segment is obtained by fitting.

[0086] In this embodiment, based on the position information of several side obstacle points, each side obstacle point is clustered to obtain several first cluster point clusters; each first cluster point cluster is fitted to obtain a corresponding side obstacle line segment. Each first cluster point cluster includes several corresponding side obstacle points. The side obstacle points belonging to the same first cluster point cluster can be considered as points on the same side obstacle, and the side obstacle points belonging to different first cluster point clusters can be considered as points on different side obstacles.

[0087] In one embodiment, each side obstacle point may be clustered based on a distance clustering algorithm. Specifically, based on the position information of the side obstacle points at two adjacent detection moments, the distance between the side obstacle points at two adjacent detection moments is determined; based on whether the distance between the side obstacle points at two adjacent detection moments meets the distance clustering requirements, it is determined whether the side obstacle points at two adjacent detection moments are divided into the same clustering point cluster or different clustering point clusters. If the distance between the side obstacle points at two adjacent detection moments meets the distance clustering requirements, the side obstacle points at two adjacent detection moments are divided into the same clustering point cluster. If the distance between the side obstacle points at two adjacent detection moments does not meet the distance clustering requirements, the side obstacle points at two adjacent detection moments are divided into different clustering point clusters. Among them, the distance clustering requirement is that the distance between the side obstacle points at two adjacent detection moments is less than or equal to the distance threshold.

[0088] In one embodiment, only one corresponding side obstacle line segment is fitted for each first cluster point cluster and used for subsequent generation of parking space areas.

[0089] In another embodiment, after fitting a corresponding side obstacle line segment for each first cluster point cluster, line segment detection is further performed to further subdivide the initially generated side obstacle line segment to further improve the side obstacle depiction effect. Specifically, performing line segment detection on the initially generated side obstacle line segment may include the following steps:

[0090] Step 1: For each fitted side obstacle line segment, the distances from each side obstacle point corresponding to the side obstacle line segment to the side obstacle line segment are counted to obtain a distance statistical value.

[0091] Exemplarily, the distance statistic value is the mean absolute error corresponding to the distance from each side obstacle point to the side obstacle line segment.

[0092] Step 2: In response to the distance statistics satisfying the segmentation requirement, a side obstacle point whose distance meets the preset distance requirement is selected from the side obstacle points corresponding to the side obstacle line segment as a segmentation point.

[0093] Exemplarily, the segmentation requirement is that the distance statistic value is greater than or equal to a set threshold.

[0094] Exemplarily, the preset distance requirement is the farthest distance from the side obstacle line segment.

[0095] Step three, based on the side obstacle points between the first point of the side obstacle line segment and the segmentation point, and the side obstacle points between the segmentation point and the end point of the side obstacle line segment, two new side obstacle line segments are fitted, and for the two new side obstacle line segments, the distances from each side obstacle point corresponding to the side obstacle line segment to the side obstacle line segment are re-executed to obtain the distance statistics value and subsequent steps, until the distance statistics value of the side obstacle line segment does not meet the segmentation requirements.

[0096] Optionally, after fitting to obtain at least one side obstacle line segment, an abnormal line segment having a length less than a preset length is selected from the at least one side obstacle line segment, and the abnormal line segment is deleted to improve the accuracy of the subsequently generated parking space area.

[0097] S63: Determine a parking space area for the vehicle based on at least one side obstacle line segment.

[0098] Figure 7 FIG. 1 is a flow chart of an embodiment of a method for determining a parking space area provided by the present application. Figure 7 As shown, the method comprises the following steps:

[0099] S701: Determine a parking space and a parking space type of the parking space based on the distance between side obstacle line segments and / or the length of parking space related line segments.

[0100] Figure 8 is a schematic diagram of three types of parking spaces provided in this application. The three types of parking spaces specifically include vertical parking spaces, parallel parking spaces, and parallel parking spaces with curbs.

[0101] In one embodiment, when the second distance between two adjacent first side obstacle line segments in the vehicle forward direction is greater than the vehicle width, and the length of the first side obstacle line segment in the vehicle forward direction is less than the sum of the vehicle width and the first value, it is determined that the space between the two adjacent first side obstacle line segments is a parking space, and the parking space is a vertical parking space. The first value is set according to actual conditions.

[0102] In another embodiment, when the second distance between two adjacent second side obstacle line segments in the vehicle forward direction is greater than the vehicle length, and the length of the second side obstacle line segment in the vehicle forward direction is less than the sum of the vehicle length and the second value, the space between the two adjacent second side obstacle line segments is determined to be a parking space, and the parking space is a parallel parking space. The second value is set according to actual conditions.

[0103] In another embodiment, when the second distance between two adjacent third side obstacle line segments in the direction perpendicular to the vehicle's forward direction is greater than the vehicle width, the third side obstacle line segment far from the vehicle among the two adjacent third side obstacle line segments is determined to be a curb line segment, and whether the side obstacle line segment after the curb line segment is a curb line segment is detected. When the length of at least one continuous curb line segment in the vehicle's forward direction is greater than the vehicle length, it is determined that there is a parking space for at least one continuous curb line segment, and the parking space is a parallel parking space with a curb.

[0104] S702: Determine a parking space area based on the parking space type of the parking space and the position of the side obstacle line segment on the edge of the parking space.

[0105] Step S702 may further include the following steps:

[0106] Step 1: Determine the outer corner point of the parking area based on the position of the side obstacle line segment on the edge of the parking space.

[0107] For example, the coordinates of the two end points of the two side obstacle segments on the edge of the parking space close to the parking space are integrated to select the two outer corner points of the parking area.

[0108] Step 2: Determine the inner corner point of the parking area according to the size and outer corner point corresponding to the parking type.

[0109] After determining the two outer corner points of the parking area, the coordinates of the two inner corner points can be obtained according to the preset size corresponding to the parking space type.

[0110] Step three, based on the orientation angle of the side obstacle line segment on the edge of the parking space and the historical heading angle of the vehicle, determine the orientation angle of the parking area.

[0111] The orientation angle of the side obstacle line segment refers to the angle between the side obstacle line segment and the reference line, and the orientation angle of the parking area refers to the angle between the outer boundary of the parking area and the reference line. Exemplarily, the reference line is the straight line where the x-axis of the global coordinate system is located.

[0112] In step 3, the orientation angle of the side obstacle line segment and the historical heading angle of the vehicle can be combined to determine the orientation angle of the parking area, which can be determined by the following formula:

[0113] Vhicle_space=Vhicle_heading+k*Segment_heading

[0114] Among them, Vehicle_space and Vehicle_heading represent the orientation angle of the parking area, the historical heading angle of the vehicle, and the orientation angle of the side obstacle segment respectively; Segment_heading represents the comprehensive value of the orientation angles of two adjacent side obstacle segments (such as average value, weighted value, etc.); the coefficient k can be set according to actual conditions; the coefficient k is used to adjust the degree of influence of the orientation angle of the side obstacle segment on the orientation angle of the parking area.

[0115] Step 4: Based on the orientation angle of the parking area, adjust the inner and outer corner points of the parking area.

[0116] S703: When the vehicle is parked in the parking area, use the detection data of at least one radar to determine the position information of several parking obstacle points in the parking area.

[0117] The parking space obstacle point refers to an obstacle point located within the parking space area or outside the parking space area.

[0118] In step S703 , the detection data of at least one radar includes at least one of the following: time series triangulation data of an outer radar and triangulation data of an adjacent radar pair.

[0119] Optionally, before executing step S704, noise point filtering may be performed on a plurality of parking space obstacle points, and valid points may be screened out from the acquired plurality of parking space obstacle points.

[0120] Step 1: spatially cluster the currently determined parking space obstacle points to obtain spatial clustering results.

[0121] The clustering results obtained by spatial clustering include a number of clustering point clusters and a number of outliers. For example, a number of parking space obstacle points can be spatially clustered by using a dbscan algorithm.

[0122] Step 2: Find outliers in the spatial clustering results.

[0123] Step three: in response to the proportion of outliers detected within a preset time period not meeting the requirement of the proportion of real obstacles, the outliers are deleted.

[0124] When the proportion of outliers detected within the preset time period meets the requirement of the proportion of real obstacles, it means that the outlier is a small obstacle that actually exists, so the outlier is retained. When the proportion of outliers detected within the preset time period does not meet the requirement of the proportion of real obstacles, it means that the outlier is not a small obstacle that actually exists, so the outlier can be deleted.

[0125] The requirement for the percentage of real obstacles is that the percentage of detected obstacles is greater than or equal to the percentage threshold. The preset time period and percentage threshold can be set according to actual needs.

[0126] In steps 1 to 3, usually dense points are obstacles with relatively high confidence, but outliers cannot be determined to be not obstacles. For example, they may be small obstacles that actually exist. By further combining the screening judgment in the time dimension and detecting whether the outliers are continuously generated, the finally generated parking space obstacle points can be made more accurate and reliable, which is conducive to the adjustment and update of the parking space area.

[0127] S704: Adjust the size of the parking area based on the position information of the plurality of parking obstacle points.

[0128] In one implementation, the size of the parking area may be adjusted directly based on the position information of a plurality of parking obstacle points.

[0129] When a parking obstacle point is detected inside the parking area, the corresponding boundary of the parking area is shrunk inward so that the parking obstacle point is located outside the adjusted parking area to avoid collision with the parking obstacle point when the vehicle is parked in the parking area, thereby improving the reliability of vehicle parking.

[0130] When a parking obstacle point is detected outside the parking area, the parking obstacle point closest to the parking space boundary can be detected, and the parking space boundary can be expanded outward to a preset safety distance to reduce the difficulty of parking and increase the parking success rate.

[0131] In another embodiment, based on the position information of several parking space obstacle points, at least one parking space obstacle line segment is fitted, and the parking space area is adjusted using the at least one parking space obstacle line segment. This embodiment may include the following steps:

[0132] Step 1: clustering is performed based on the position information of a plurality of parking space obstacle points to obtain a plurality of second clustering point clusters.

[0133] Exemplarily, a plurality of parking space obstacle points may be clustered by using a dbscan algorithm to obtain a plurality of second clustering point clusters.

[0134] Step 2: Fit each second cluster point cluster to obtain a corresponding parking space obstacle line segment.

[0135] In one implementation, only one parking space obstacle line segment obtained by fitting each second cluster point cluster is used for subsequent adjustment and update of the parking space area.

[0136] In another embodiment, after fitting a corresponding parking space obstacle line segment for each second cluster point cluster, line segment detection is further performed to further subdivide the initially generated parking space obstacle line segment to further improve the depiction effect of the parking space obstacle. Specifically, performing line segment detection on the initially generated parking space obstacle line segment may include the following sub-steps:

[0137] Sub-step 1: for each parking space obstacle line segment obtained by fitting, the distances from various cluster points corresponding to the parking space obstacle line segment to the parking space obstacle line segment are counted to obtain a distance statistical value.

[0138] Sub-step 2: In response to the distance statistics satisfying the segmentation requirement, a parking space obstacle point whose distance meets the preset distance requirement is selected from each parking space obstacle point corresponding to the parking space obstacle line segment as a segmentation point.

[0139] In sub-step three, two new parking space obstacle line segments are fitted based on the parking space obstacle points between the first point and the segmentation point of the parking space obstacle line segment and the parking space obstacle points between the segmentation point and the end point of the parking space obstacle line segment, and for the two new parking space obstacle line segments, the distances from each parking space obstacle point corresponding to the parking space obstacle line segment to the parking space obstacle line segment are re-executed to obtain the distance statistics value and subsequent steps, until the distance statistics value of the parking space obstacle line segment does not meet the segmentation requirements.

[0140] Step 3: Adjust the parking area to be within the restricted space formed by the obstacle line segments of each parking space.

[0141] Optionally, in this embodiment, the side obstacle line segments may be merged with the parking space obstacle line segments on both sides of the parking space area obtained by fitting during the parking phase.

[0142] See also Fig. 9 , Fig. 9 is a schematic diagram of the fusion of side obstacle line segments and parking space obstacle line segments provided by this application. Fig. 9 As shown, when the side obstacle line segment and the parking space obstacle line segment are merged, if there is an intersection between the side obstacle line segment and the parking space obstacle line segment, the redundant part outside the boundary formed by the side obstacle line segment and the parking space obstacle line segment is trimmed.

[0143] In this embodiment, at least one side obstacle line segment is obtained by fitting the side obstacle points detected by the outer radar, which can better characterize the side obstacles on both sides of the vehicle, making the parking space area searched based on the at least one side obstacle line segment more accurate.

[0144] Moreover, the obstacle positioning and parking space generation of the present application can be adapted to low-end models that only have four UPA radars installed at the rear of the vehicle. There is no need to add additional side radars, which is low-cost and can enable low-end models to also realize parking space detection and automatic parking functions.

[0145] See also Fig.10 , Fig.10 1 is a schematic diagram of a framework of an electronic device according to an embodiment of the present application. In this embodiment, the electronic device 100 includes a memory 101 and a processor 102 .

[0146] The processor 102 may also be referred to as a CPU (Central Processing Unit). The processor 102 may be an integrated circuit chip having signal processing capabilities. The processor 102 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. A general-purpose processor may be a microprocessor or the processor 102 may also be any conventional processor 102, etc.

[0147] The memory 101 in the electronic device 100 is used to store program instructions required for the processor 102 to run.

[0148] The processor 102 is used to execute program instructions to implement the obstacle positioning method and parking space generation method in this application.

[0149] See also Fig.11 , Fig.11 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium provided by the present application. The computer-readable storage medium 110 of the embodiment of the present application stores program instructions 111, and when the program instructions 111 are executed, the obstacle positioning method and parking space generation method provided by the present application are implemented. Among them, the program instructions 111 can form a program file and be stored in the above-mentioned computer-readable storage medium 110 in the form of a software product, so that a computer device (which can be a personal computer, a server, or a network device, etc.) executes all or part of the steps of each implementation method of the present application. The aforementioned computer-readable storage medium 110 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, and a tablet.

[0150] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0151] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0152] In the several embodiments provided in the present application, it should be understood that the disclosed methods, devices and systems can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0154] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0155] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0156] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An obstacle positioning method, characterized in that: The method is applied to a vehicle with multiple radars at the rear, wherein the radars located on both sides of the rear of the vehicle are outer radars, and the normal of the outer radar is at an angle to the central axis of the vehicle. The method includes: Acquiring side detection data of the outer radar; Based on the side detection data, position information of the side obstacle point of the vehicle is determined.

2. The method according to claim 1, characterized in that The angle between the normal line of the outer radar and the center axis of the vehicle is 25-45 degrees.

3. The method according to claim 1, characterized in that The determining, based on the side detection data, the position information of the side obstacle point of the vehicle comprises: The position information of the side obstacle point of the vehicle is obtained by performing triangulation using two adjacent frames of side detection data of the outer radar.

4. The method according to claim 3, characterized in that The two adjacent frames of side detection data include the side detection data at the previous detection moment and the side detection data at the current detection moment; The method of performing triangulation using two adjacent frames of side detection data of the outer radar to obtain the position information of the side obstacle point of the vehicle includes: Determine a first distance between the outer radar and the side obstacle point using the side detection data at the previous detection time; and determine a second distance between the outer radar and the side obstacle point using the side detection data at the current detection time; Determine the first global position information and the second global position information corresponding to the outer radar at the previous detection time and the current detection time respectively; The position information of the side obstacle point is determined by using the first distance, the second distance, the first global position information, and the second global position information.

5. The method according to claim 4, characterized in that The target detection time is any detection time of the outer radar, and the step of determining the global position information of the outer radar at the target detection time includes: Acquiring global position information of the vehicle at the target detection moment; Determine and obtain the global position information of the outer radar at the time of target detection by using the global position information of the vehicle at the time of target detection and the position parameter of the outer radar with respect to the vehicle; And / or, after determining the first global position information and the second global position information corresponding to the outer radar at the previous detection moment and the current detection moment, respectively, the method further comprises: performing at least one of a first check and a second check; The first verification step includes: determining a third distance based on the first global position information and the second global position information; in response to the first distance, the second distance and the third distance not satisfying a triangle formation condition, filtering out the side detection data at the last detection moment; The second verification step includes: determining a first detection angle and a second detection angle, wherein the first detection angle is the angle between the first side and the second side, the second detection angle is the angle between the second side and the third side, the two endpoints of the first side are the side obstacle point and the outer radar at the previous detection moment, the two endpoints of the second side are the outer radar at the previous detection moment and the outer radar at the current detection moment, and the two endpoints of the third side are the side obstacle point and the outer radar at the current detection moment; in response to at least one of the first detection angle and the second detection angle exceeding the detection angle range of the outer radar, filtering out the side detection data at the previous detection moment.

6. The method according to claim 1, characterized in that The method further comprises: The detection data of the adjacent radar pairs are used to perform triangulation to obtain the position information of the obstacle point on the rear side of the vehicle.

7. A parking space generation method, characterized in that: The method is applied to a vehicle with multiple radars at the rear, wherein the radars located on both sides of the rear of the vehicle are outer radars, and the normal of the outer radar is at an angle to the central axis of the vehicle. The method includes: Determine the position information of several side obstacle points of the vehicle by using the side detection data of the outside radar; Based on the position information of the plurality of side obstacle points, fitting at least one side obstacle line segment; A parking space area is determined for the vehicle based on the at least one side obstacle line segment.

8. The method according to claim 7, characterized in that The fitting of obtaining at least one side obstacle line segment based on the position information of the plurality of side obstacle points includes: Based on the position information of the plurality of side obstacle points, clustering the plurality of side obstacle points to obtain a plurality of first clustering point clusters; Each of the first clustering points is fitted to obtain a corresponding side obstacle line segment.

9. The method according to claim 8, characterized in that The step of clustering the side obstacle points based on the position information of the side obstacle points to obtain a plurality of first clustering point clusters includes: Determine the distance between the side obstacle points at two adjacent detection moments based on the position information of the side obstacle points at two adjacent detection moments; Based on whether the distance between the side obstacle points at two adjacent detection moments meets the distance clustering requirement, it is determined whether the side obstacle points at two adjacent detection moments are divided into the same cluster point cluster or different cluster point clusters.

10. The method according to claim 7, characterized in that After determining a parking space area for the vehicle based on the at least one side obstacle line segment, the method further includes: During the process of the vehicle parking in the parking area, using detection data of at least one of the radars to determine position information of a plurality of parking obstacle points in the parking area; Based on the position information of the plurality of parking space obstacle points, the size of the parking space area is adjusted.

11. The method according to claim 10, characterized in that The adjusting the size of the parking area based on the position information of the plurality of parking space obstacle points includes: Clustering is performed based on the position information of the plurality of parking space obstacle points to obtain a plurality of second clustering point clusters; Fit each of the second clustering point clusters to obtain a corresponding parking space obstacle line segment; The parking space area is adjusted to be within the restricted space formed by the parking space obstacle line segments.

12. The method according to claim 8 or 11, characterized in that: After fitting each of the first clustering point clusters to obtain a corresponding side obstacle line segment, or fitting each of the second clustering point clusters to obtain a corresponding parking space obstacle line segment, the method further includes: For each obstacle line segment obtained by fitting, the distances from each obstacle point in the cluster point cluster corresponding to the obstacle line segment to the obstacle line segment are counted to obtain a distance statistical value; In response to the distance statistics satisfying the segmentation requirement, selecting an obstacle point whose distance meets the preset distance requirement from the cluster point cluster corresponding to the obstacle line segment as a segmentation point; Based on the obstacle points between the first point of the obstacle line segment and the segmentation point and the obstacle points between the segmentation point and the last point of the obstacle line segment, two new obstacle line segments are fitted, and for the two new obstacle line segments, the distance statistics from each obstacle point corresponding to the obstacle line segment to the obstacle line segment are re-executed to obtain a distance statistics value and subsequent steps, until the distance statistics value of the obstacle line segment does not meet the segmentation requirement.

13. The method according to claim 7 or 11, characterized in that: Before determining a parking space area for the vehicle based on the at least one side obstacle line segment, or before adjusting the parking space area to be within the restricted space formed by the parking space obstacle line segments, at least one of the following steps is further included: Among the obstacle line segments obtained by fitting, select abnormal line segments whose length is less than a preset length, and delete the abnormal line segments; The side obstacle line segments are merged with the parking space obstacle line segments on both sides of the parking space area obtained by fitting during the parking phase.

14. The method according to claim 10, characterized in that Before adjusting the size of the parking area based on the position information of the plurality of parking space obstacle points, the method further includes: Perform spatial clustering on several currently determined parking space obstacle points to obtain spatial clustering results; Find outliers in the spatial clustering results; In response to the proportion of the outliers detected within a preset time period not meeting a requirement for the proportion of real obstacles, the outliers are deleted.

15. The method according to claim 7, characterized in that The step of determining a parking space area for the vehicle based on the at least one side obstacle line segment includes: Determine a parking space and a parking space type of the parking space based on the distance between the side obstacle line segments and / or the length of the parking space related line segments; The parking space area is determined based on the parking space type of the parking space and the position of the side obstacle line segment on the edge of the parking space.

16. The method according to claim 15, characterized in that The determining of the parking space and the parking space type to which the parking space belongs based on the distance between the side obstacle line segments and / or the length of the parking space related line segments includes: In response to a distance between two adjacent first side obstacle line segments in a forward direction of the vehicle being greater than a vehicle width of the vehicle, and a length of the first side obstacle line segment in the forward direction of the vehicle being less than a sum of the vehicle width and a first value, determining that a space between the two adjacent first side obstacle line segments is a parking space, and the parking space is a vertical parking space; In response to the distance between two adjacent second side obstacle line segments in the vehicle forward direction being greater than the vehicle length of the vehicle, and the length of the second side obstacle line segment in the vehicle forward direction being less than the sum of the vehicle length and a second value, determining that the space between the two adjacent second side obstacle line segments is a parking space, and the parking space is a parallel parking space; In response to the distance between two adjacent third side obstacle line segments in the direction perpendicular to the vehicle's advancing direction being greater than the vehicle width, determining that the third side obstacle line segment far from the vehicle among the two adjacent third side obstacle line segments is a curb segment, and detecting whether the side obstacle line segment after the curb segment is a curb segment; in response to the length of at least one continuous curb segment in the vehicle's advancing direction being greater than the vehicle length, determining that there is a parking space for at least one continuous curb segment, and the parking space is a parallel parking space with a curb; And / or, determining the parking space area based on the parking space type of the parking space and the position of the side obstacle line segment on the edge of the parking space includes: Determining the outer corner point of the parking space area based on the position of the side obstacle line segment on the edge of the parking space; Determining an inner corner point of the parking space area according to the size corresponding to the parking space type and the outer corner point; Determining the orientation angle of the parking space area based on the orientation angle of the side obstacle line segment on the edge of the parking space and the historical heading angle of the vehicle; Based on the orientation angle of the parking area, inner and outer corner points of the parking area are adjusted.

17. The method according to claim 7, characterized in that The position information of the side obstacle point is determined using any method of claims 2 to 5.

18. An electronic device, characterized in that: comprising a memory and a processor coupled to each other, The memory stores program instructions; The processor is used to execute program instructions stored in the memory to implement the method described in any one of claims 1-6 or any one of claims 7-17.

19. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program instructions, and the program instructions can be executed by a processor to implement the method of any one of claims 1-6 or any one of claims 7-17.

Images