Region boundary determination method and device, computer equipment and storage medium

Abstract

The invention relates to a region boundary determination method and device, computer equipment and a storage medium. The method comprises the following steps: sorting all points in a channel corresponding to a target area to obtain a target point sequence; selecting a plurality of first evaluation point sets in the target point sequence, determining a plurality of first angle parameters corresponding to the plurality of first evaluation point sets, and determining a first boundary point set according to the plurality of first angle parameters; selecting a plurality of second evaluation point sets in the target point sequence, determining a plurality of second angle parameters according to the coordinate parameters corresponding to the plurality of second evaluation point sets, and determining a second boundary point set according to the plurality of second angle parameters; boundary points can be adjusted in real time by evaluating angle parameters, so that the boundary determination method can adapt to dynamic environment changes, and the robustness of boundary determination is improved; according to the first boundary point set and the second boundary point set, the target boundary point set of the target area is determined, the influence of noise or errors on a single point set can be reduced, and then the accuracy and stability of area boundary determination are improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, apparatus, computer device and storage medium for determining area boundaries. Background Art

[0002] In autonomous driving and intelligent transportation systems, it is crucial to accurately identify the boundaries of the drivable area, especially in unstructured scenarios. Unstructured scenarios refer to environments that lack clear structures, shapes, and rules. They are common in natural environments and city streets and are characterized by harsh environmental conditions, frequent dynamic changes, and diverse obstacles. These factors make the identification and boundary detection of drivable areas face huge technical challenges. Identifying the boundaries of the drivable area not only ensures the safe driving of the vehicle, but also improves driving efficiency and passenger comfort. In complex environments, vehicles may encounter pedestrians, animals, other vehicles, and unpredictable obstacles. Therefore, timely and accurate identification of the boundaries of the drivable area is crucial for obstacle avoidance, path planning, and dynamic decision-making.

[0003] In traditional area boundary determination technology, a camera is used to capture environmental images, and boundaries are identified through algorithms such as edge detection and image segmentation.

[0004] However, in traditional technologies, there are various lighting conditions (such as strong light, shadows, and reflections) in the actual driving environment of vehicles. These lighting conditions will affect the contrast of the image, resulting in unclear or blurred edges, which in turn affects the accuracy of boundary determination. At the same time, algorithms such as edge detection and image segmentation perform poorly when processing certain types of images (such as curves, complex shapes, etc.), which may lead to inaccurate boundary determination. Summary of the invention

[0005] Based on this, it is necessary to provide a method, apparatus, computer device, storage medium and computer program product for determining a region boundary that can improve the accuracy of determining a region boundary in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for determining a region boundary, comprising:

[0007] Sort all points in the channel corresponding to the target area to obtain a target point sequence;

[0008] Selecting a plurality of first evaluation point sets from the target point sequence, determining a plurality of first angle parameters corresponding to the plurality of first evaluation point sets, and determining a first boundary point set according to the plurality of first angle parameters;

[0009] Selecting a plurality of second evaluation point sets from the target point sequence, determining a plurality of second angle parameters according to coordinate parameters corresponding to the plurality of second evaluation point sets, and determining a second boundary point set according to the plurality of second angle parameters;

[0010] A target boundary point set of the target area is determined according to the first boundary point set and the second boundary point set.

[0011] In one embodiment, selecting a plurality of first evaluation point sets from the target point sequence and determining a plurality of first angle parameters corresponding to the plurality of first evaluation point sets comprises:

[0012] Taking each point in the target point sequence as a first reference point, selecting multiple evaluation points corresponding to each first reference point according to the target interval number, and obtaining a first evaluation point set corresponding to each first reference point; wherein each first evaluation point set includes the first reference point corresponding to it;

[0013] An angle parameter between a first reference point corresponding to the first evaluation point set and each evaluation point in each first evaluation point set is determined to obtain a first angle parameter corresponding to the first evaluation point set.

[0014] In one embodiment, determining a first boundary point set according to a plurality of first angle parameters comprises:

[0015] When it is determined that the first angle parameter corresponding to each first evaluation point set is less than the angle threshold, determining whether the height difference between the first reference point corresponding to the first evaluation point set and each evaluation point is greater than the height threshold;

[0016] When the height difference between the first reference point corresponding to the first evaluation point set and each evaluation point is greater than a height threshold, the first reference point corresponding to the first evaluation point set is used as a first boundary point.

[0017] In one embodiment, multiple second evaluation point sets are selected from the target point sequence, and multiple second angle parameters are determined according to coordinate parameters corresponding to the multiple second evaluation point sets, including:

[0018] For each point in the target point sequence, use the point as a second reference point;

[0019] Taking the second reference point as the center, selecting a plurality of evaluation points before and after the second reference point to obtain a second evaluation point set corresponding to the second reference point; wherein the second evaluation point set corresponding to the second reference point includes the second reference point;

[0020] A second evaluation point set corresponding to each point in the target point sequence is determined to obtain a plurality of second evaluation point sets.

[0021] In one embodiment, determining a plurality of second angle parameters according to coordinate parameters corresponding to a plurality of second evaluation point sets includes:

[0022] Obtain the horizontal coordinate data corresponding to each evaluation point in each second evaluation point set;

[0023] Calculating a first average coordinate value and a second average coordinate value according to horizontal coordinate data corresponding to each evaluation point in the second evaluation point set;

[0024] A second angle parameter corresponding to the second evaluation point set is determined according to the second reference point, the first average coordinate value, and the second average coordinate value.

[0025] In one embodiment, determining the second boundary point set according to the plurality of second angle parameters comprises:

[0026] When it is determined that the second angle parameter corresponding to each second evaluation point set is less than the angle threshold, determining whether the height difference between the second reference point corresponding to the second evaluation point set and each evaluation point is greater than the height threshold;

[0027] When the height difference between the second reference point corresponding to the second evaluation point set and each evaluation point is greater than the height threshold, the second reference point corresponding to the second evaluation point set is used as the second boundary point.

[0028] In one embodiment, all points in the channel corresponding to the target area are sorted to obtain a target point sequence, including:

[0029] Obtain the coordinate data of all points in the channel corresponding to the target area, and determine the coordinate data of the reference point in the channel corresponding to the target area;

[0030] Determine the angle data corresponding to each point in the channel corresponding to the target area according to the coordinate data of the reference point and the coordinate data of each point in the channel corresponding to the target area;

[0031] According to the angle data corresponding to each point in the channel corresponding to the target area, all points in the channel corresponding to the target area are sorted to obtain a target point sequence.

[0032] In a second aspect, the present application also provides a region boundary determination device, comprising:

[0033] A sorting module is used to sort all points in the channel corresponding to the target area to obtain a target point sequence;

[0034] A first determination module is used to select a plurality of first evaluation point sets from the target point sequence, determine a plurality of first angle parameters corresponding to the plurality of first evaluation point sets, and determine a first boundary point set according to the plurality of first angle parameters;

[0035] A second determination module is used to select a plurality of second evaluation point sets from the target point sequence, determine a plurality of second angle parameters according to coordinate parameters corresponding to the plurality of second evaluation point sets, and determine a second boundary point set according to the plurality of second angle parameters;

[0036] The target determination module is used to determine a target boundary point set of the target area according to the first boundary point set and the second boundary point set.

[0037] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0038] Sort all points in the channel corresponding to the target area to obtain a target point sequence;

[0039] Selecting a plurality of first evaluation point sets from the target point sequence, determining a plurality of first angle parameters corresponding to the plurality of first evaluation point sets, and determining a first boundary point set according to the plurality of first angle parameters;

[0040] Selecting a plurality of second evaluation point sets from the target point sequence, determining a plurality of second angle parameters according to coordinate parameters corresponding to the plurality of second evaluation point sets, and determining a second boundary point set according to the plurality of second angle parameters;

[0041] A target boundary point set of the target area is determined according to the first boundary point set and the second boundary point set.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0043] Sort all points in the channel corresponding to the target area to obtain a target point sequence;

[0044] Selecting a plurality of first evaluation point sets from the target point sequence, determining a plurality of first angle parameters corresponding to the plurality of first evaluation point sets, and determining a first boundary point set according to the plurality of first angle parameters;

[0045] Selecting a plurality of second evaluation point sets from the target point sequence, determining a plurality of second angle parameters according to coordinate parameters corresponding to the plurality of second evaluation point sets, and determining a second boundary point set according to the plurality of second angle parameters;

[0046] A target boundary point set of the target area is determined according to the first boundary point set and the second boundary point set.

[0047] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0048] Sort all points in the channel corresponding to the target area to obtain a target point sequence;

[0049] Selecting a plurality of first evaluation point sets from the target point sequence, determining a plurality of first angle parameters corresponding to the plurality of first evaluation point sets, and determining a first boundary point set according to the plurality of first angle parameters;

[0050] Selecting a plurality of second evaluation point sets from the target point sequence, determining a plurality of second angle parameters according to coordinate parameters corresponding to the plurality of second evaluation point sets, and determining a second boundary point set according to the plurality of second angle parameters;

[0051] A target boundary point set of the target area is determined according to the first boundary point set and the second boundary point set.

[0052] The above-mentioned method, device, computer equipment, storage medium and computer program product for determining the area boundary sort all points in the channel corresponding to the target area to obtain a target point sequence, which can ensure the systematization of the boundary determination process and enhance the accuracy of boundary determination; select multiple first evaluation point sets in the target point sequence, determine multiple first angle parameters corresponding to the multiple first evaluation point sets, and determine the first boundary point set based on the multiple first angle parameters; select multiple second evaluation point sets in the target point sequence, determine multiple second angle parameters based on the coordinate parameters corresponding to the multiple second evaluation point sets, and determine the second boundary point set based on the multiple second angle parameters; by evaluating the angle parameters, the boundary points can be adjusted in real time, so that the boundary determination method can adapt to dynamic environmental changes and improve the robustness of boundary determination; determine the target boundary point set of the target area based on the first boundary point set and the second boundary point set, which can reduce the risk of a single set being affected by noise or errors, thereby improving the accuracy and stability of area boundary determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] FIG1 is a diagram showing an application environment of a method for determining a region boundary in one embodiment;

[0055] FIG2 is a schematic diagram of a flow chart of a method for determining a region boundary in one embodiment;

[0056] FIG3 is a schematic flow chart of a step of determining a plurality of second angle parameters in one embodiment;

[0057] FIG4 is a structural block diagram of a device for determining a region boundary in one embodiment;

[0058] FIG. 5 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] The method for determining the regional boundary provided by the embodiment of the present application can be applied to the application environment shown in FIG. 1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 sends a request for determining the regional boundary to the server 104, and the server 104 receives the request for determining the regional boundary, sorts all the points in the corresponding channel of the target area, and obtains a target point sequence; selects multiple first evaluation point sets in the target point sequence, determines multiple first angle parameters corresponding to the multiple first evaluation point sets, and determines the first boundary point set according to the multiple first angle parameters; selects multiple second evaluation point sets in the target point sequence, determines multiple second angle parameters according to the coordinate parameters corresponding to the multiple second evaluation point sets, and determines the second boundary point set according to the multiple second angle parameters; determines the target boundary point set of the target area according to the first boundary point set and the second boundary point set. Among them, the terminal 102 can be, but is not limited to, various vehicles such as cars, motorcycles, and aircraft. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0061] In an exemplary embodiment, as shown in FIG2 , a method for determining a region boundary is provided, and the method is applied to the server in FIG1 as an example for description, and includes the following steps 202 to 208. Among them:

[0062] Step 202, sort all points in the channel corresponding to the target area to obtain a target point sequence.

[0063] The target area refers to the spatial area where the boundary of the area needs to be determined. The channel corresponding to the target area refers to an independent area in the target area, which may be different roads, lanes or any place that can be passed. The target area may include multiple independent channels.

[0064] For example, the laser radar device obtains the coordinate data of all points in the channel corresponding to the target area, and sorts all points in the channel corresponding to the target area according to the coordinate data of all points in the channel corresponding to the target area. For example, the angle parameter corresponding to each point is determined according to the coordinate data of all points, and then sorted according to the angle parameter, or sorted according to the horizontal coordinate data value of the point.

[0065] Step 204 : Select a plurality of first evaluation point sets from the target point sequence, determine a plurality of first angle parameters corresponding to the plurality of first evaluation point sets, and determine a first boundary point set according to the plurality of first angle parameters.

[0066] Optionally, each point in the target point sequence is used as a first reference point, and the first evaluation point set corresponding to each first reference point is determined according to a pre-set selection method. The first evaluation point set corresponding to each point in the target point sequence is determined to obtain multiple first evaluation point sets corresponding to the target point sequence. For each first evaluation point set, a trigonometric function is used to calculate the angle between the first reference point corresponding to the first evaluation point set and each evaluation point of the first evaluation point set to obtain the first angle parameter corresponding to the first evaluation point set. According to the first angle parameter corresponding to the first evaluation point set, it is determined whether the first reference point corresponding to the first evaluation point set is a region boundary point.

[0067] Step 206 , selecting a plurality of second evaluation point sets from the target point sequence, determining a plurality of second angle parameters according to coordinate parameters corresponding to the plurality of second evaluation point sets, and determining a second boundary point set according to the plurality of second angle parameters.

[0068] Optionally, each point in the target point sequence is used as a second reference point, and the second evaluation point set corresponding to each second reference point is determined according to a preset selection method. The second evaluation point set corresponding to each point in the target point sequence is determined to obtain multiple second evaluation point sets corresponding to the target point sequence. For each second evaluation point set, the coordinate parameters corresponding to the second evaluation point set are calculated, and the second angle parameters corresponding to the second evaluation point set are determined according to the coordinate parameters corresponding to the second evaluation point set. And according to the second angle parameters corresponding to the second evaluation point set, it is determined whether the second reference point corresponding to the second evaluation point set is a region boundary point.

[0069] Step 208: Determine a target boundary point set of the target area according to the first boundary point set and the second boundary point set.

[0070] Optionally, the overlapping part of the boundary points in the first boundary point set and the second boundary point set is obtained, and the overlapping part of the boundary points is used as the target boundary point set of the target area, that is, the first boundary point set and the second boundary point set are intersected to obtain the target boundary point set of the target area.

[0071] In the above-mentioned method for determining the region boundary, all points in the channel corresponding to the target region are sorted to obtain a target point sequence, which can ensure the systematization of the boundary determination process and enhance the accuracy of boundary determination; multiple first evaluation point sets are selected from the target point sequence, multiple first angle parameters corresponding to the multiple first evaluation point sets are determined, and the first boundary point set is determined based on the multiple first angle parameters; multiple second evaluation point sets are selected from the target point sequence, multiple second angle parameters are determined based on the coordinate parameters corresponding to the multiple second evaluation point sets, and the second boundary point set is determined based on the multiple second angle parameters; by evaluating the angle parameters, the boundary points can be adjusted in real time, so that the boundary determination method can adapt to dynamic environmental changes and improve the robustness of boundary determination; according to the first boundary point set and the second boundary point set, the target boundary point set of the target region is determined, which can reduce the risk of a single set being affected by noise or errors, thereby improving the accuracy and stability of region boundary determination.

[0072] In an exemplary embodiment, all points in the channel corresponding to the target area are sorted to obtain a target point sequence, including: acquiring coordinate data of all points in the channel corresponding to the target area, and determining coordinate data of a reference point in the channel corresponding to the target area; determining angle data corresponding to each point in the channel corresponding to the target area according to the coordinate data of the reference point and the coordinate data of each point in the channel corresponding to the target area; and sorting all points in the channel corresponding to the target area according to the angle data corresponding to each point in the channel corresponding to the target area to obtain a target point sequence.

[0073] Exemplarily, before sorting all the points in the channel corresponding to the target area, a reference point is selected in the channel corresponding to the target area, and the coordinate data corresponding to the reference point is determined. The reference point may be the center point of the channel corresponding to the target area, or the origin of the coordinate system. After determining the reference point, for each point in the channel corresponding to the target area, the inverse tangent function is used to determine the angle data corresponding to the point according to the coordinate data corresponding to the point and the coordinate data corresponding to the reference point. Specifically, the projection of each point in the channel corresponding to the target area on the plane may be calculated, and trigonometric functions may be used to determine the angle between the vector from the reference point to the point and the X-axis of the coordinate system, thereby obtaining the angle data corresponding to the point.

[0074] According to the coordinate data corresponding to all points in the channel corresponding to the target area and the coordinate data corresponding to the reference point, the angle data corresponding to all points in the channel corresponding to the target area are determined. The angle data corresponding to all points in the channel corresponding to the target area are sorted from large to small or from small to large to obtain a target point sequence.

[0075] In this embodiment, sorting all points in the channel corresponding to the target area can ensure the systematization of the boundary determination process, reduce the complexity of subsequent calculations, and enhance the accuracy of boundary determination; in dynamic application scenarios (such as autonomous driving or robot navigation), sorting all points in the channel corresponding to the target area through angle data can more naturally reflect the relative positions between points, and thus can respond more quickly to changes in the environment in the target area, thereby improving the efficiency of regional boundary determination.

[0076] In an exemplary embodiment, multiple first evaluation point sets are selected in a target point sequence, and multiple first angular parameters corresponding to the multiple first evaluation point sets are determined, including: taking each point in the target point sequence as a first reference point, selecting multiple evaluation points corresponding to each first reference point with a target interval number, and obtaining first evaluation point sets corresponding to each first reference point; wherein each first evaluation point set includes a first reference point corresponding to it; and determining, in each first evaluation point set, the angle parameters between the first reference point corresponding to the first evaluation point set and each evaluation point, and obtaining the first angular parameters corresponding to the first evaluation point set.

[0077] Each point in the target point sequence is taken as a first reference point, and multiple evaluation points corresponding to each first reference point are selected with the target interval number to obtain the first evaluation point set corresponding to each first reference point. Exemplarily, for each point in the target point sequence, the point is taken as the first reference point, and multiple points are selected forward from the first reference point with the target interval number according to the order of the target point sequence (i.e., the sorting order of the angle data) to obtain multiple first evaluation points, and these multiple first evaluation points and the first reference point are recorded as the first evaluation point set corresponding to the first reference point (or the first evaluation point set corresponding to the point). Among them, the target interval number is set according to the time situation. For example, if the target interval number is n, the nth and 2nth points can be selected forward from the first reference point to obtain two first evaluation points, and then the two first evaluation points and the first reference point are recorded as the first evaluation point set corresponding to the first reference point. Determine the first evaluation point set corresponding to each first reference point (each point) in the target point sequence to obtain multiple second evaluation point sets.

[0078] Exemplarily, the first evaluation point includes a first auxiliary point, a second auxiliary point, and a first reference point corresponding to the first evaluation point set. For each first evaluation point set, the distance data between the points corresponding to the first evaluation point set is determined, and a trigonometric function is used based on the distance data to obtain a first angle parameter corresponding to the first evaluation point set. Optionally, determining the first angle parameter corresponding to the first evaluation point set may also include, for each first evaluation point set, determining a vector between the first reference point corresponding to the first evaluation point set and the first auxiliary point and the second auxiliary point to obtain two vectors, and obtaining the first angle parameter corresponding to the first evaluation point set based on the two vectors.

[0079] In this embodiment, each point in the target point sequence is taken as a first reference point, and multiple evaluation points corresponding to each first reference point are selected according to the target interval number to obtain a first evaluation point set corresponding to each first reference point, which can avoid the uncertainty caused by random selection; determining the first angle parameter corresponding to each first evaluation point set can clearly reflect the relative position relationship between the first reference point and each first evaluation point in a dynamic environment, thereby improving the reliability of boundary determination.

[0080] In the previous exemplary embodiment, the first boundary point set is determined according to multiple first angular parameters, including: when it is determined that the first angular parameter corresponding to each first evaluation point set is less than an angle threshold, judging whether the height difference between the first reference point corresponding to the first evaluation point set and each evaluation point is greater than the height threshold; when the height difference between the first reference point corresponding to the first evaluation point set and each evaluation point is greater than the height threshold, using the first reference point corresponding to the first evaluation point set as the first boundary point.

[0081] Optionally, for each first evaluation point set, determine the height difference between the first reference point and the first auxiliary point corresponding to the first evaluation point set. Specifically, determine the three-dimensional coordinate data of the first reference point and the first auxiliary point respectively, and determine the height difference between the first reference point and the first auxiliary point according to the three-dimensional coordinate data of the first reference point and the first auxiliary point (that is, determine the difference between the first reference point and the first auxiliary point in the Z-axis direction) to obtain the first height difference. Determine the height difference between the first auxiliary point and the second auxiliary point corresponding to the first evaluation point set to obtain the second height difference. At the same time, determine the height difference between the first reference point and the second auxiliary point corresponding to the first evaluation point set to obtain the third height difference.

[0082] The height threshold may include multiple ones, such as a first height threshold and a second height threshold, and the first height threshold and the second height threshold may be set according to actual conditions, wherein the second height threshold may be set to 0.05. For each first evaluation point set, determine whether the first angle parameter corresponding to the first evaluation point set is less than the angle threshold. Among them, the angle threshold is set according to actual conditions and is not limited here. When it is determined that the first angle parameter corresponding to the first evaluation point set is less than the angle threshold, determine whether the first height difference or the second height difference is greater than the first height threshold. When it is determined that the first height difference or the second height difference is greater than the first height threshold, determine whether the third height difference is greater than the second height threshold. When the third height difference is greater than the second height threshold, the first reference point corresponding to the first evaluation point set is used as a first boundary point. Determine whether the first reference point corresponding to each first evaluation point set is a first boundary point, and obtain multiple first boundary points corresponding to multiple first evaluation point sets, which are recorded as first boundary point sets.

[0083] In this embodiment, by using the height difference and angle parameters, it is determined whether the first reference point corresponding to each first evaluation point set is the first boundary point, which can improve the accuracy of boundary determination. In addition, the boundary point determination is performed on each point in the target point sequence, which can improve the comprehensiveness of the region boundary determination.

[0084] In an exemplary embodiment, multiple second evaluation point sets are selected in the target point sequence, and multiple second angle parameters are determined according to the coordinate parameters corresponding to the multiple second evaluation point sets, including: for each point in the target point sequence, the point is used as a second reference point; with the second reference point as the center, multiple evaluation points before and after the second reference point are selected to obtain a second evaluation point set corresponding to the second reference point; wherein the second evaluation point set corresponding to the second reference point includes the second reference point; and the second evaluation point set corresponding to each point in the target point sequence is determined to obtain multiple second evaluation point sets.

[0085] For each point in the target point sequence, the point is taken as a second reference point; multiple evaluation points before and after the second reference point are selected with the second reference point as the center to obtain the second evaluation point set corresponding to the second reference point. Exemplarily, for each point in the target point sequence, the point is taken as the second reference point, and n points are selected forward and backward with the second reference point as the center according to the order of the target point sequence (i.e., the sorting order of the angle data), to obtain 2n second evaluation points, wherein the second evaluation points include n front evaluation points and n rear evaluation points. Specifically, the second reference point is searched forward in sequence with the second reference point as the center, and the n points closest to the second reference point are selected as n front evaluation points, and the second reference point is searched backward in sequence with the second reference point as the center, and the n points closest to the second reference point are selected as n rear evaluation points. The n front evaluation points, n rear evaluation points and the second reference point are taken as the second evaluation point set corresponding to the second reference point. The second evaluation point set corresponding to each second reference point (each point) in the target point sequence is determined to obtain multiple second evaluation point sets.

[0086] In this embodiment, determining the second evaluation point set corresponding to each point in the target point sequence can ensure the comprehensiveness and accuracy of the data, and help avoid the inaccuracy of boundary determination due to missing data. At the same time, selecting n points forward and backward with each second reference point as the center can ensure that these points are evenly distributed in space, so as to fully capture the features in the corresponding channel of the target area, thereby improving the accuracy of boundary determination.

[0087] In the previous exemplary embodiment, as shown in FIG3 , determining a plurality of second angle parameters according to the coordinate parameters corresponding to a plurality of second evaluation point sets includes steps 302 to 306. Among them:

[0088] Step 302: Obtain horizontal coordinate data corresponding to each evaluation point in each second evaluation point set.

[0089] Step 304 , calculating a first average coordinate value and a second average coordinate value according to the horizontal coordinate data corresponding to each evaluation point in the second evaluation point set.

[0090] Step 306: Determine a second angle parameter corresponding to the second evaluation point set according to the second reference point, the first average coordinate value, and the second average coordinate value.

[0091] For each second evaluation point set, the coordinate data of the n front evaluation points, n rear evaluation points and the second reference point corresponding to the second evaluation point set are obtained. The coordinate data of the n front evaluation points, n rear evaluation points and the second reference point corresponding to the second evaluation point set are summarized to obtain the front evaluation point coordinate set and the rear evaluation point coordinate set.

[0092] In the field of autonomous driving technology, the driving direction of a vehicle is mainly affected by factors in the horizontal plane, rather than changes in height, and the height information may be affected by sensor noise or other errors. Ignoring this height information can reduce the interference of noise on the boundary determination result. Therefore, in this embodiment, the height information in the vertical direction is ignored, and the average coordinate value of all evaluation points in each second evaluation point set on the horizontal plane is calculated.

[0093] Exemplarily, the height data in the vertical direction is ignored, and the horizontal coordinate data of the n front evaluation points corresponding to the second evaluation point set are averaged to obtain the average coordinate value of the n front evaluation points on the horizontal plane, which is recorded as the first average coordinate value. Similarly, the average coordinate value of the n rear evaluation points is determined by this method, which is recorded as the second average coordinate value. According to the first average coordinate value, the second average coordinate value and the second reference point, a trigonometric function is used to obtain the second angle parameter corresponding to the second evaluation point set.

[0094] In this embodiment, by ignoring the height data in the vertical direction and focusing on the angle calculation in the horizontal plane, the complexity can be reduced. In practical applications, the environment is complex and changeable. Ignoring unnecessary height data can reduce the impact of noise on the angle calculation, thereby improving the robustness and stability of boundary determination. Calculating the horizontal coordinate data corresponding to each evaluation point in the second evaluation point set to obtain the first average coordinate value and the second average coordinate value can reduce the impact of the outlier value of a single point on the boundary determination and improve the reliability of the boundary determination.

[0095] In an exemplary embodiment, a second boundary point set is determined based on multiple second angular parameters, including: when it is determined that the second angular parameter corresponding to each second evaluation point set is less than an angle threshold, judging whether the height difference between the second reference point corresponding to the second evaluation point set and each evaluation point is greater than the height threshold; when the height difference between the second reference point corresponding to the second evaluation point set and each evaluation point is greater than the height threshold, using the second reference point corresponding to the second evaluation point set as the second boundary point.

[0096] Optionally, for each second evaluation point set, multiple height differences between the second reference point corresponding to the second evaluation point set and the n front evaluation points are determined, and the largest height difference among the multiple height differences is recorded as the front evaluation height difference, and multiple height differences between the second reference point corresponding to the second evaluation point set and the n rear evaluation points are determined, and the largest height difference among the multiple height differences is recorded as the rear evaluation height difference. At the same time, the height difference between the second reference point corresponding to the second evaluation point set and all the second evaluation points is determined to obtain a second evaluation height difference set. The maximum value in the second evaluation height difference set is determined, and the maximum value is used as the fourth height difference.

[0097] The height threshold may also include a third height threshold, which may be set according to actual conditions. For each second evaluation point set, determine whether the second angle parameter corresponding to the second evaluation point set is less than the angle threshold. Wherein, the angle threshold is set according to actual conditions and is not limited here. When it is determined that the second angle parameter corresponding to the second evaluation point set is less than the angle threshold, determine whether the pre-evaluation height difference or the post-evaluation height difference is greater than the third height threshold. When it is determined that the pre-evaluation height difference or the post-evaluation height difference is greater than the third height threshold, determine whether the fourth height difference is greater than the second height threshold, and when the fourth height difference is greater than the second height threshold, the second reference point corresponding to the second evaluation point set is used as a second boundary point. Determine whether the second reference point corresponding to each second evaluation point set is a second boundary point, and obtain multiple second boundary points corresponding to multiple second evaluation point sets, which are recorded as second boundary point sets.

[0098] In this embodiment, a boundary point judgment is performed on each point in the target point sequence, which can improve the comprehensiveness of the regional boundary determination. Through the height difference and angle parameters, it is determined whether the second reference point of each second evaluation point set is a second boundary point. Complex terrain or changes can be captured, making the regional boundary judgment more comprehensive, reducing the misjudgment of boundary points, and thus improving the reliability and effectiveness of regional boundary determination.

[0099] In another embodiment, a method for determining a region boundary is provided, the method comprising:

[0100] Obtain the coordinate data of all points in the channel corresponding to the target area, and determine the coordinate data of the reference point in the channel corresponding to the target area; determine the angle data corresponding to each point in the channel corresponding to the target area according to the coordinate data of the reference point and the coordinate data of each point in the channel corresponding to the target area; sort all points in the channel corresponding to the target area according to the angle data corresponding to each point in the channel corresponding to the target area to obtain a target point sequence.

[0101] Each point in the target point sequence is taken as a first reference point, and multiple evaluation points corresponding to each first reference point are selected according to the target interval number to obtain a first evaluation point set corresponding to each first reference point; wherein each first evaluation point set includes the first reference point corresponding to it; in each first evaluation point set, the angle parameter between the first reference point corresponding to the first evaluation point set and each evaluation point is determined to obtain the first angle parameter corresponding to the first evaluation point set.

[0102] When it is determined that the first angle parameter corresponding to each first evaluation point set is less than the angle threshold, it is determined whether the height difference between the first reference point corresponding to the first evaluation point set and each evaluation point is greater than the height threshold; when the height difference between the first reference point corresponding to the first evaluation point set and each evaluation point is greater than the height threshold, the first reference point corresponding to the first evaluation point set is used as the first boundary point. And according to the multiple first evaluation point sets of the target point sequence, the first boundary point set is determined.

[0103] For each point in the target point sequence, take the point as a second reference point; select multiple evaluation points before and after the second reference point with the second reference point as the center to obtain a second evaluation point set corresponding to the second reference point; wherein the second evaluation point set corresponding to the second reference point includes the second reference point; determine the second evaluation point set corresponding to each point in the target point sequence to obtain multiple second evaluation point sets.

[0104] Obtain the horizontal coordinate data corresponding to each evaluation point in the second evaluation point set; calculate the first average coordinate value and the second average coordinate value based on the horizontal coordinate data corresponding to each evaluation point in the second evaluation point set; determine the second angle parameter corresponding to the second evaluation point set based on the second reference point, the first average coordinate value and the second average coordinate value.

[0105] When it is determined that the second angle parameter corresponding to each second evaluation point set is less than the angle threshold, it is determined whether the height difference between the second reference point corresponding to the second evaluation point set and each evaluation point is greater than the height threshold; when the height difference between the second reference point corresponding to the second evaluation point set and each evaluation point is greater than the height threshold, the second reference point corresponding to the second evaluation point set is used as the second boundary point. And according to the multiple second evaluation point sets of the target point sequence, the second boundary point set is determined.

[0106] A target boundary point set of the target area is determined according to the first boundary point set and the second boundary point set.

[0107] In this embodiment, in dynamic application scenarios (such as autonomous driving or robot navigation), all points in the channel corresponding to the target area are sorted by angle data, which can more naturally reflect the relative position between points, and thus can respond to changes in the environment in the target area more quickly, and improve the efficiency of regional boundary determination. At the same time, all points in the channel corresponding to the target area are sorted, which can ensure the systematization of the boundary determination process, reduce the complexity of subsequent calculations, and enhance the accuracy of boundary determination. Each point in the target point sequence is used as the first reference point and the second reference point, and multiple evaluation points corresponding to each first reference point are selected according to the target interval number to obtain the first evaluation point set corresponding to each first reference point, which can avoid the uncertainty caused by random selection; determining the first angle parameter corresponding to each first evaluation point set can clearly reflect the relative position relationship between the first reference point and each first evaluation point in a dynamic environment, thereby improving the reliability of boundary determination. Selecting n points forward and backward with each second reference point as the center as evaluation points can ensure that these points are evenly distributed in space, thereby fully capturing the features in the channel corresponding to the target area, thereby improving the accuracy of boundary determination. By ignoring the vertical height data and focusing on the angle calculation in the horizontal plane, the complexity can be reduced. In practical applications, the environment is complex and changeable. Ignoring unnecessary height data can reduce the impact of noise on the angle calculation, thereby improving the robustness and stability of boundary determination. Through the height difference and angle parameters, it is determined whether the first reference point corresponding to each first evaluation point set is the first boundary point, and whether the second reference point corresponding to each second evaluation point set is the second boundary point. Complex terrain or changes can be captured, making the regional boundary judgment more comprehensive, thereby improving the accuracy of boundary determination.

[0108] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0109] Based on the same inventive concept, the embodiment of the present application also provides a region boundary determination device for implementing the region boundary determination method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more region boundary determination device embodiments provided below can refer to the limitations of the region boundary determination method above, and will not be repeated here.

[0110] In an exemplary embodiment, as shown in FIG4 , a region boundary determination device is provided, comprising: a sorting module 402 , a first determination module 404 , a second determination module 406 and a target determination module 408 , wherein:

[0111] A sorting module 402 is used to sort all points in the channel corresponding to the target area to obtain a target point sequence;

[0112] A first determination module 404 is used to select a plurality of first evaluation point sets from the target point sequence, determine a plurality of first angle parameters corresponding to the plurality of first evaluation point sets, and determine a first boundary point set according to the plurality of first angle parameters;

[0113] A second determination module 406 is used to select a plurality of second evaluation point sets from the target point sequence, determine a plurality of second angle parameters according to coordinate parameters corresponding to the plurality of second evaluation point sets, and determine a second boundary point set according to the plurality of second angle parameters;

[0114] The target determination module 408 is used to determine a target boundary point set of the target area according to the first boundary point set and the second boundary point set.

[0115] In an exemplary embodiment, the first determination module 404 is also used to take each point in the target point sequence as a first reference point, select multiple evaluation points corresponding to each first reference point according to the target interval number, and obtain a first evaluation point set corresponding to each first reference point; wherein each first evaluation point set includes the first reference point corresponding to it; determine the angle parameters between the first reference point corresponding to the first evaluation point set and each evaluation point in each first evaluation point set, and obtain the first angle parameters corresponding to the first evaluation point set.

[0116] In an exemplary embodiment, the first determination module 404 is also used to determine whether the height difference between the first reference point corresponding to the first evaluation point set and each evaluation point is greater than the height threshold when the first angle parameter corresponding to each first evaluation point set is less than an angle threshold; when the height difference between the first reference point corresponding to the first evaluation point set and each evaluation point is greater than the height threshold, the first reference point corresponding to the first evaluation point set is used as the first boundary point.

[0117] In an exemplary embodiment, the second determination module 406 is also used to take each point in the target point sequence as a second reference point; select multiple evaluation points before and after the second reference point with the second reference point as the center to obtain a second evaluation point set corresponding to the second reference point; wherein the second evaluation point set corresponding to the second reference point includes the second reference point; determine the second evaluation point set corresponding to each point in the target point sequence to obtain multiple second evaluation point sets.

[0118] In an exemplary embodiment, the second determination module 406 is also used to obtain horizontal coordinate data corresponding to each evaluation point in each second evaluation point set; calculate the first average coordinate value and the second average coordinate value based on the horizontal coordinate data corresponding to each evaluation point in the second evaluation point set; and determine the second angular parameter corresponding to the second evaluation point set based on the second reference point, the first average coordinate value and the second average coordinate value.

[0119] In an exemplary embodiment, the second determination module 406 is also used to determine whether the height difference between the second reference point corresponding to the second evaluation point set and each evaluation point is greater than the height threshold when it is determined that the second angle parameter corresponding to each second evaluation point set is less than the angle threshold; when the height difference between the second reference point corresponding to the second evaluation point set and each evaluation point is greater than the height threshold, the second reference point corresponding to the second evaluation point set is used as the second boundary point.

[0120] In an exemplary embodiment, the target determination module 408 is also used to obtain the coordinate data of all points in the channel corresponding to the target area, and determine the coordinate data of the reference point in the channel corresponding to the target area; determine the angle data corresponding to each point in the channel corresponding to the target area according to the coordinate data of the reference point and the coordinate data of each point in the channel corresponding to the target area; sort all points in the channel corresponding to the target area according to the angle data corresponding to each point in the channel corresponding to the target area to obtain a target point sequence.

[0121] Each module in the above-mentioned area boundary determination device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0122] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG5. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the first evaluation point set and the second evaluation point set data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining a regional boundary is implemented.

[0123] Those skilled in the art will understand that the structure shown in FIG. 5 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0124] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0125] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0126] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0127] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0128] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0129] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0130] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining a region boundary, characterized in that: The method comprises: Sort all points in the channel corresponding to the target area to obtain a target point sequence; Selecting a plurality of first evaluation point sets from the target point sequence, determining a plurality of first angle parameters corresponding to the plurality of first evaluation point sets, and determining a first boundary point set according to the plurality of first angle parameters; Selecting a plurality of second evaluation point sets from the target point sequence, determining a plurality of second angle parameters according to coordinate parameters corresponding to the plurality of second evaluation point sets, and determining a second boundary point set according to the plurality of second angle parameters; A target boundary point set of a target area is determined according to the first boundary point set and the second boundary point set.

2. The method according to claim 1, characterized in that: The step of selecting a plurality of first evaluation point sets from the target point sequence and determining a plurality of first angle parameters corresponding to the plurality of first evaluation point sets comprises: Taking each point in the target point sequence as a first reference point, selecting a plurality of evaluation points corresponding to each first reference point according to the target interval number, and obtaining a first evaluation point set corresponding to each first reference point; wherein each first evaluation point set includes the first reference point corresponding thereto; An angle parameter between a first reference point corresponding to the first evaluation point set and each evaluation point in each first evaluation point set is determined to obtain a first angle parameter corresponding to the first evaluation point set.

3. The method according to claim 2, characterized in that The determining of a first boundary point set according to the plurality of first angle parameters comprises: When it is determined that the first angle parameter corresponding to each first evaluation point set is less than the angle threshold, determining whether the height difference between the first reference point corresponding to the first evaluation point set and each evaluation point is greater than the height threshold; When the height difference between the first reference point corresponding to the first evaluation point set and each evaluation point is greater than a height threshold, the first reference point corresponding to the first evaluation point set is used as a first boundary point.

4. The method according to claim 1, characterized in that: The selecting a plurality of second evaluation point sets from the target point sequence comprises: For each point in the target point sequence, use the point as a second reference point; Taking the second reference point as the center, selecting a plurality of evaluation points before and after the second reference point to obtain a second evaluation point set corresponding to the second reference point; wherein the second evaluation point set corresponding to the second reference point includes the second reference point; A second evaluation point set corresponding to each point in the target point sequence is determined to obtain a plurality of second evaluation point sets.

5. The method according to claim 4, characterized in that The determining of a plurality of second angle parameters according to the coordinate parameters corresponding to the plurality of second evaluation point sets comprises: Obtain the horizontal coordinate data corresponding to each evaluation point in each second evaluation point set; Calculating a first average coordinate value and a second average coordinate value according to horizontal coordinate data corresponding to each of the evaluation points in the second evaluation point set; A second angle parameter corresponding to the second evaluation point set is determined according to the second reference point, the first average coordinate value, and the second average coordinate value.

6. The method according to claim 5, characterized in that The determining of the second boundary point set according to the plurality of the second angle parameters comprises: When it is determined that the second angle parameter corresponding to each second evaluation point set is less than the angle threshold, determining whether the height difference between the second reference point corresponding to the second evaluation point set and each evaluation point is greater than the height threshold; When the height difference between the second reference point corresponding to the second evaluation point set and each evaluation point is greater than the height threshold, the second reference point corresponding to the second evaluation point set is used as the second boundary point.

7. The method according to claim 1, characterized in that The step of sorting all points in the channel corresponding to the target area to obtain a target point sequence includes: Obtain the coordinate data of all points in the channel corresponding to the target area, and determine the coordinate data of the reference point in the channel corresponding to the target area; Determine the angle data corresponding to each point in the channel corresponding to the target area according to the coordinate data of the reference point and the coordinate data of each point in the channel corresponding to the target area; According to the angle data corresponding to each point in the channel corresponding to the target area, all points in the channel corresponding to the target area are sorted to obtain a target point sequence.

8. A device for determining a region boundary, characterized in that: The device comprises: A sorting module is used to sort all points in the channel corresponding to the target area to obtain a target point sequence; a first determination module, configured to select a plurality of first evaluation point sets from the target point sequence, determine a plurality of first angle parameters corresponding to the plurality of first evaluation point sets, and determine a first boundary point set according to the plurality of first angle parameters; a second determination module, configured to select a plurality of second evaluation point sets from the target point sequence, determine a plurality of second angle parameters according to coordinate parameters corresponding to the plurality of second evaluation point sets, and determine a second boundary point set according to the plurality of second angle parameters; The target determination module is used to determine a target boundary point set of a target area according to the first boundary point set and the second boundary point set.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images