Traffic element drawing method and device, equipment and storage medium

Abstract

The invention discloses a traffic element drawing method and device, equipment and a storage medium, and relates to the field of electronic maps, and the method comprises the steps: obtaining an element contour of a target traffic element from point cloud data; based on a reference point in an element template corresponding to the target traffic element, selecting a plurality of calibration points from the element contour; and drawing a target traffic element in the point cloud data according to the spatial position distribution among the plurality of calibration points and the template point set of the element template. According to the method, only the calibration points need to be selected from the element contours of the target traffic elements in the point cloud data, and then the target traffic elements can be semi-automatically drawn into the point cloud data according to the spatial position distribution of the calibration points and the template point set of the element template corresponding to the target traffic elements. Due to the fact that stroking drawing does not need to be conducted manually, the method not only enables the patterns drawn in the point cloud data to be more regular and accurate, but also improves the pattern drawing efficiency to a certain degree.

Description

Technical Field

[0001] The present application relates to the field of electronic maps, and in particular to a method, device, equipment and storage medium for drawing traffic elements. Background Art

[0002] In today's era of rapid technological development, the importance of high-precision maps has become increasingly prominent. As a high-precision geographic information data, high-precision maps provide key support for fields such as autonomous driving and intelligent transportation. In the production process of high-precision maps, traditional manual production methods have always occupied an important position. However, this method has many limitations. Among them, the problem is particularly prominent in the drawing of traffic elements based on point cloud data.

[0003] As a kind of high-precision three-dimensional spatial data, point cloud data can provide rich information for the drawing of traffic elements. At present, it is usually done manually according to the outline of the elements in the point cloud, and the method of manual drawing is greatly affected by the quality of the collected point cloud data. If the point cloud data is unclear, incomplete or noisy, the difficulty of manual drawing will be greatly increased. At the same time, the difference in manual operation level will also lead to uneven drawing quality, and some may have problems such as inaccurate shape and irregular size, which seriously affects the accuracy and reliability of high-precision maps. Faced with the huge amount of point cloud data and complex road scenes, manual operation requires a lot of time and effort. This not only increases production costs, but also makes it difficult to meet the needs of modern society for rapid updates and efficient production of high-precision maps. Therefore, the industry is in urgent need of a method that can improve the efficiency and accuracy of traffic element drawing. Summary of the invention

[0004] The main purpose of this application is to provide a traffic element drawing method, device, equipment and storage medium, aiming to solve the technical problems of low drawing efficiency and drawing accuracy of existing traffic element drawing methods.

[0005] To achieve the above object, the present application provides a method for drawing traffic elements, the method comprising the following steps:

[0006] Obtaining feature outlines of target traffic features from point cloud data;

[0007] Selecting a plurality of calibration points from the element contour based on reference points in the element template corresponding to the target traffic element;

[0008] The target traffic element in the point cloud data is drawn according to the spatial position distribution among the plurality of calibration points and the template point set of the element template.

[0009] In one embodiment, the step of drawing the target traffic element in the point cloud data according to the spatial position distribution between the plurality of calibration points and the template point set of the element template includes:

[0010] Determining a mapping analysis factor between the element template and the element contour according to the spatial position distribution among the plurality of calibration points;

[0011] Determining a target point set corresponding to the element template in the point cloud data according to the mapping analysis factor and the template point set of the element template;

[0012] The target traffic element in the point cloud data is drawn based on the target point set.

[0013] In one embodiment, the target traffic element includes a plane figure.

[0014] In one embodiment, the target traffic element includes an arrow mark, and the mapping analysis factor includes the coordinates of the calibration point, the arrow direction of the arrow mark, and the normal vector of the plane where the arrow mark is located;

[0015] And / or, the multiple calibration points include a first calibration point, a second calibration point and a third calibration point, wherein the first calibration point is the starting point of the arrow direction, the second calibration point is any point on the vector corresponding to the arrow direction in the arrow mark, and the third calibration point is any point in the plane where the arrow mark is located, and the third calibration point does not overlap with the first calibration point and the second calibration point.

[0016] In one embodiment, when the mapping analysis factor includes the coordinates of the calibration point, the arrow direction of the arrow mark, and the normal vector of the plane where the arrow mark is located, the step of determining the target point set corresponding to the feature template in the point cloud data according to the mapping analysis factor and the template point set of the feature template includes:

[0017] Calculate the quaternion corresponding to the rotation of the feature template to the point cloud data based on the mapping analysis factor;

[0018] The template point set of the element template is converted into a quaternion according to the quaternion to obtain a target point set corresponding to the element template in the point cloud data.

[0019] In one embodiment, the step of drawing the target traffic element in the point cloud data based on the target point set includes:

[0020] Rendering the element template based on the target point set to obtain a rendering pattern;

[0021] The rendering pattern is fitted onto the element contour to draw the target traffic element in the point cloud data.

[0022] In one embodiment, the traffic element drawing method further includes obtaining an element template corresponding to the target traffic element in the following manner:

[0023] Determine the reference point, positioning edge, vector vector and plane normal contained in the element template corresponding to the target traffic element according to the sample standard data corresponding to the target traffic element;

[0024] An element template corresponding to the target traffic element is produced according to the reference point, the positioning edge, the vector and the plane normal.

[0025] In addition, to achieve the above-mentioned purpose, the present application also proposes a traffic element drawing device, the traffic element drawing device comprising:

[0026] A contour acquisition module, used to obtain the element contour of the target traffic element from the point cloud data;

[0027] A point calibration module, used for selecting a plurality of calibration points from the element contour based on reference points in the element template corresponding to the target traffic element;

[0028] The traffic element drawing module is used to draw the target traffic element in the point cloud data according to the spatial position distribution between the multiple calibration points and the template point set of the element template.

[0029] In addition, to achieve the above-mentioned purpose, the present application also proposes a traffic element drawing device, which includes: a memory, a processor, and a traffic element drawing program stored in the memory and executable on the processor, wherein the traffic element drawing program is configured to implement the steps of the traffic element drawing method described above.

[0030] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and stores a traffic element drawing program on the storage medium. When the traffic element drawing program is executed by a processor, the steps of the traffic element drawing method described above are implemented.

[0031] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer program product, which includes a traffic element drawing program, and when the traffic element drawing program is executed by a processor, the steps of the traffic element drawing method described above are implemented.

[0032] The present application obtains the element outline of the target traffic element from the point cloud data; selects multiple calibration points from the element outline based on the reference points in the element template corresponding to the target traffic element; and draws the target traffic element in the point cloud data according to the spatial position distribution between the multiple calibration points and the template point set of the element template. Compared with the traditional traffic element drawing method, the above method of the present application only needs to select calibration points from the element outline of the target traffic element in the point cloud data, and then automatically draw the target traffic element into the point cloud data according to the spatial position distribution of the calibration points and the template point set of the element template corresponding to the target traffic element. Since there is no need to rely on manual tracing, the above method of the present application not only makes the pattern drawn in the point cloud data more regular and accurate, but also improves the efficiency of pattern drawing. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of the first embodiment of the traffic element drawing method of the present application;

[0034] Figure 2 A schematic diagram of an element template for the traffic element drawing method of this application;

[0035] Figure 3 A schematic diagram of the calibration points for the traffic element drawing method of this application;

[0036] Figure 4 This is a flow chart of a second embodiment of the traffic element drawing method of the present application;

[0037] Figure 5 A schematic diagram of mapping analysis factors indicated by arrows in the traffic element drawing method of this application;

[0038] Figure 6 A schematic diagram of the flow chart of the third embodiment of the traffic element drawing method of the present application;

[0039] Figure 7 This is a structural block diagram of the first embodiment of the traffic element drawing device of the present application.

[0040] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0041] 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.

[0042] An embodiment of the present application provides a method for drawing traffic elements, in which a corresponding element template can be prepared for a target traffic element (such as any one or more of an arrow sign, a straight sign, a turn sign or a no-entry sign on a road), and then in the process of drawing or constructing the traffic element, the element contour of the target traffic element can be extracted from the point cloud data containing the target traffic element, and a plurality of calibration points can be selected from the element contour in combination with the reference points in the corresponding element template, and the target traffic element can be drawn based on the spatial position distribution between the plurality of calibration points selected from the element contour and the template point set of the corresponding element template; in the process of drawing the traffic element, there is no need to rely on manual stroking of the edge of its contour, so that the pattern drawn in the point cloud data is more regular and accurate, thereby improving the efficiency of pattern drawing.

[0043] The traffic element drawing method provided in the present application can be deployed and executed on a computer device, which can be a vehicle-mounted device (such as a vehicle-mounted controller, a vehicle-mounted processor or other vehicle-mounted units, etc.), or a terminal outside the vehicle, an independent server, a cloud, a server cluster, a distributed system, an Internet of Things device or an Internet of Vehicles device, etc. This embodiment does not limit this, and those skilled in the art can set up a computer device to implement the traffic element drawing method according to actual needs.

[0044] Please refer to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the traffic element drawing method of the present application.

[0045] In this embodiment, the traffic element drawing method includes the following steps:

[0046] Step S1: Obtain the element outline of the target traffic element from the point cloud data.

[0047] It is understandable that the above-mentioned point cloud data can be acquired by one or more devices including the collection unit on the vehicle, the roadside unit in the traffic scene (such as the point cloud collection device set up at the intersection, etc.), the drone, and other point cloud devices. For example, it can be obtained by the collection unit on the vehicle or the roadside unit through laser scanning of the target scene, or by aerial photography by a drone, etc.; the point cloud data in the embodiment of the present application can be a collection of a set of vectors in a three-dimensional coordinate system, these vectors are recorded in the form of points, and each point contains three-dimensional coordinate information.

[0048] It should be understood that the above-mentioned target traffic elements may include three-dimensional objects and / or two-dimensional plane graphics. The three-dimensional objects may include but are not limited to any one or any combination of traffic lights, highway gates, speed limit signs and restricted traffic signs set up on the roadside, etc.; the aforementioned plane graphics may include but are not limited to any one or any combination of road signs in high-precision maps such as arrow signs, diamond signs, motor vehicle lane signs, speed limit signs, diversion signs, etc., and may also be signs of any other arbitrary shapes, which are not limited in this embodiment.

[0049] Step S2: Based on the reference points in the element template corresponding to the target traffic element, multiple calibration points are selected from the element contour.

[0050] It should be noted that the above-mentioned element template is a standard specification element of the target traffic element, and the standard specification element can be produced with reference to the drawing standards of traffic control and / or electronic maps; that is, the element template and the target traffic element have the same element type, and the element template meets the standard specification requirements of the traffic element of this element type, that is, the element template is a standard specification element of this element type, and the shape and size of the ideal target traffic element and the element template are the same; specifically, the embodiment of the present application can refer to the standard specification data corresponding to the target traffic element in the relevant standard documents, and construct the element template corresponding to the target traffic element in the 3D mapping software according to the specification ratio of 1:1, or draw the element template of the target traffic element by manual stroking; if the target traffic element to be drawn is arrow A, then the standard specification data corresponding to the arrow can be consulted, and the element template of arrow B as arrow A can be constructed in the 3D mapping software according to the specification ratio of 1:1.

[0051] In a feasible implementation, the traffic element drawing method may further include obtaining an element template corresponding to the target traffic element in the following manner: determining the reference point, positioning edge, vector and plane normal contained in the element template corresponding to the target traffic element based on the sample standard data corresponding to the target traffic element; and making the element template corresponding to the target traffic element based on the reference point, positioning edge, vector and plane normal.

[0052] It should be noted that the above-mentioned sample standard data refers to the standard data (such as line length, line width, angle, spacing, color, etc.) for producing the element template corresponding to the target traffic element in the production standard file.

[0053] In the embodiment of the present application, the reference point in the feature template is at least one point selected from the template point set of the feature template. The template point set of the feature template can be a set of at least two point combinations on the contour of the feature template. The calibration point can be a clear point with positioning characteristics in the feature contour (such as but not limited to any one or combination of inflection points, intersection points, vertices, etc.). In the embodiment of the present application, the number of points, reference points and calibration points in the aforementioned template point set is not limited, and those skilled in the art can set them according to actual needs.

[0054] For ease of understanding, the arrow mark is used as a specific example of the target traffic element and the element type of the element template. The element template is an arrow mark that meets the standard specification requirements. Please refer to Figure 2 , Figure 2 Given a specific example of a feature template marked with an arrow, you can, but are not limited to, select a set of points p0, p1, p2, p3, p4, p5, and p6 from the contour of the arrow mark (i.e., the feature template) as the template point set of the feature template, and then you can select p0 and p1 from the template point set as reference points in the feature template.

[0055] Furthermore, in step S2, at least one calibration point can be selected from the target traffic element based on the reference points p0 and p1 in the element template; see Figure 3 , Figure 3 This is a schematic diagram of the calibration points of the traffic element drawing method of this application, which gives a specific example of selecting calibration points. Figure 3 Select point a0 on the target traffic element shown and corresponding to the reference point p0 on the element template as the first calibration point, and select Figure 2 Any point a1 on the line corresponding to the vector p0p1 (i.e. the direction of the arrow) is the second calibration point. Figure 3 Any point a2 on the plane where the target traffic element is located is the third calibration point (a2 does not overlap with a0 and a1), then the first calibration point a0, the second calibration point a1 and the third calibration point a2 (3 calibration points) can be obtained. Figure 2 Here n1 represents the normal vector of the plane where the feature template is located, u1 represents the arrow direction of the feature template, v1 represents the vector pointing from p6 to p0, and n1 can be expressed as the cross product of u1 and v1.

[0056] Step S3: drawing the target traffic element in the point cloud data according to the spatial position distribution among the plurality of calibration points and the template point set of the element template.

[0057] It should be understood that, under the condition that the spatial position distribution between the above-mentioned multiple calibration points and the template point set of the feature template are known, the feature template can be geometrically transformed (for example, any one or any combination of rotation, translation, mirroring, etc.) according to the spatial position distribution and the template point set, so as to achieve the technical purpose of drawing the target traffic element in the point cloud data.

[0058] This embodiment obtains the element contour of the target traffic element from the point cloud data; selects multiple calibration points from the element contour based on the reference points in the element template corresponding to the target traffic element; and draws the target traffic element in the point cloud data according to the spatial position distribution between the multiple calibration points and the template point set of the element template. Compared with the traditional traffic element drawing method, the above method of this embodiment only needs to select calibration points from the element contour of the target traffic element in the point cloud data, and then automatically draw the target traffic element into the point cloud data according to the spatial position distribution of the calibration points and the template point set of the element template corresponding to the target traffic element. Since there is no need to rely on manual tracing, the above method of this application not only makes the pattern drawn in the point cloud data more regular and accurate, but also improves the efficiency of pattern drawing.

[0059] refer to Figure 4 , Figure 4 This is a flow chart of the second embodiment of the traffic element drawing method of the present application.

[0060] In a feasible implementation manner, step S3 may be implemented by the following steps S31, S32, and S33:

[0061] Step S31: determining a mapping analysis factor between the feature template and the feature contour according to the spatial position distribution among the plurality of calibration points.

[0062] Step S32: determining a target point set corresponding to the element template in the point cloud data according to the mapping analysis factor and the template point set of the element template.

[0063] It should be noted that the above-mentioned target point set may be a set of positioning points of the feature template in the point cloud data, and the aforementioned positioning points are points in the point cloud data corresponding to the positions of the points in the template point set of the feature template.

[0064] Step S33: drawing the target traffic element in the point cloud data based on the target point set.

[0065] It is understandable that after the target point set corresponding to the element template in the point cloud data is determined, the target traffic element can be drawn in the point cloud data by connecting each point in the target point set in sequence, or by rendering the target traffic element in the point cloud data based on the target point set. Of course, other methods of drawing traffic elements based on a point set can also be used, and this embodiment is not limited to this.

[0066] It should be noted that in step S31, the mapping analysis factors between the target traffic elements and the element contours of different element types (such as arrow signs, motor vehicle lane signs or diversion signs, etc.) may be different, and then in step S32, the target point set corresponding to the element template in the point cloud data may be determined according to the analysis method corresponding to the mapping analysis factor; technical personnel in this field may set the corresponding mapping analysis factor based on the specific element type of the target traffic element and the analysis method corresponding to the mapping analysis factor.

[0067] For ease of understanding, the technical solutions of the above steps S31 to S33 are explained here using arrows as element types of target traffic elements:

[0068] In this example, the target traffic element is an arrow mark, and the mapping analysis factors in step S31 may include the coordinates of the calibration point, the arrow direction of the arrow mark, and the normal vector of the plane where the arrow mark is located.

[0069] The calibration points in this example can refer to the above Figure 3 The first calibration point a0, the second calibration point a1 and the third calibration point a2 are shown in FIG. Figure 2 The starting point of the arrow direction is the second calibration point a1, which is the vector vector corresponding to the arrow direction in the arrow mark (corresponding to p0 in the element template shown in FIG. Figure 2 The third calibration point a2 is any point in the plane where the arrow mark is located, and a0, a1 and a2 do not overlap. Please refer to Figure 5 , Figure 5 This is a schematic diagram of the mapping analysis factors of the arrow marks in the traffic element drawing method of the present application, wherein a0, a1, and a2 represent the first calibration point, the second calibration point, and the third calibration point, respectively, u2 represents the arrow direction of the above-mentioned arrow marks, v2 represents the vector from the third calibration point a2 to the first calibration point a0, and n2 (i.e., the normal vector of the plane where the above-mentioned arrow marks are located) is the cross product of u2 and v2.

[0070] Furthermore, in step S32, the target point set can be obtained based on the mapping analysis factors of step S31. Specifically, the template point set in the feature template can be specifically transformed according to the mapping analysis factors between the feature template and the feature contour, so that the relative distribution of the points in the converted point set is consistent with the relative distribution of the points in the template point set. The converted point set is the above-mentioned target point set.

[0071] In a feasible implementation manner, when drawing the target traffic element in step S33, it can be implemented through the following steps S331 and S332:

[0072] Step S331: Rendering the element template based on the target point set to obtain a rendering pattern.

[0073] It should be understood that the above rendering pattern represents the target traffic element that needs to be drawn in the point cloud data.

[0074] Step S332: Fitting the rendering pattern to the element outline to draw the target traffic element in the point cloud data.

[0075] In a specific implementation, color data can be added to the rendering pattern, that is, the pixel color information of the corresponding position of the target traffic element is assigned to the corresponding point in the point cloud, so that the point cloud data has color information while having geometric shape information, which helps to display the objects and scenes in the map more intuitively.

[0076] This embodiment determines the mapping analysis factor between the feature template and the feature contour according to the spatial position distribution between the multiple calibration points; determines the target point set corresponding to the feature template in the point cloud data according to the mapping analysis factor and the template point set of the feature template; renders the feature template based on the target point set to obtain a rendering pattern; and fits the rendering pattern to the feature contour to draw the target traffic element in the point cloud data. Compared with the traditional traffic element drawing method, the above method of this embodiment determines the target point set corresponding to the feature template in the point cloud data according to the mapping analysis factor between the feature template and the feature contour and the template point set of the feature template, and then renders the feature template based on the target point set to obtain a rendering pattern that can draw the target traffic element in the point cloud data at one time. Compared with manual stroke drawing, the above method of this embodiment greatly improves the drawing efficiency of the target traffic element.

[0077] refer to Figure 6 , Figure 6 This is a flow chart of the third embodiment of the traffic element drawing method of the present application.

[0078] In a feasible implementation manner, when the target traffic element is an arrow mark, step S32 can be implemented by the following steps S321 and S322:

[0079] Step S321: Calculate the quaternion corresponding to the element template rotated to the point cloud data based on the mapping analysis factor.

[0080] It should be noted that the above quaternion is a mathematical concept of complex number extension, which is used to represent rotation in three-dimensional space. A quaternion is usually written in the form of q=w+xi+yj+zk, where w, x, y, z are real numbers, i, j, k are imaginary units, and i 2 =j 2 =k 2 =ijk=-1. In practical applications, quaternions are often expressed in the form of (x, y, z, w). Among them, the three components x, y, and z together constitute the direction vector of the rotation axis. If the direction of the rotation axis is represented by a unit vector v=(x, y, z) (and it is required that ), then x, y, and z determine the axis around which the object in three-dimensional space rotates. For example, if v = (1,0,0), it means rotation around the x-axis; if v = (0,1,0), it means rotation around the y-axis; if v = (0,0,1), it means rotation around the z-axis. The w component can be regarded as the "scalar" part of the rotation. When w = 1 and x = y = z = 0, the quaternion indicates no rotation (unit quaternion). From a geometric point of view, w is related to the angle of rotation. For a unit quaternion q = (x, y, z, w), the rotation angle θ satisfies w = cos(θ / 2), which determines the amplitude of the rotation to a certain extent.

[0081] In the specific implementation, it is assumed that the point coordinates are described as (x, y, z), where x is the X-axis coordinate value, y is the Y-axis coordinate value, and z is the Z-axis coordinate value; the vector is described as (x, y, z), where x is the direction vector of the X-axis, y is the direction vector of the Y-axis, and z is the direction vector of the Z-axis. From point a = (a x ,a y ,a z ) to point b = (b x ,b y ,b z ) Quaternion is described as (x, y, z, w) and is used to represent rotation. The rotation angle θ can be expressed as quaternion The modulus of a quaternion is Quaternion conjugation , the inverse of the quaternion

[0082]

[0083] For a vector Normalization is to transform it into a unit vector. The normalization formula is in is the normalized vector, is a vector The model, Normalized vector For two vectors and The vector cross product formula is The vector dot product formula is For two unit vectors and Let the angle be θ; vector and The dot product of

[0084]

[0085] According to the above formula, the unit vector can be calculated Rotate to unit vector According to the vector dot product formula, we can get θ = arccos(a x b x +a y b y +a z b z ), obtained by vector cross product Plane Normal Model

[0086] Will Normalized Then the quaternion q=

[0087]

[0088] In another embodiment, the quaternion can also be calculated based on the following scheme. remember Calculate cosine Take the quaternion q = (n x ,n y ,n z ,cosθ+1), and then normalize q to get This is the desired quaternion.

[0089] vector The vector is obtained by rotating the unit quaternion q have: vector Using quaternion expression (a x ,a y ,a z ,0). Quaternion q=(q x ,q y ,q z ,q w ), its inverse q -1 =(-q x ,-q y ,-q z ,q w ).

[0090] You can calculate first

[0091] Recalculate

[0092] Finally got

[0093] Furthermore, the drawing process of the target traffic element in this embodiment can be regarded as the process of rotating the element template of the target traffic element into the point cloud data. In a feasible implementation, combined with the above discussion on quaternions, the element template of the target traffic element can be rotated into the point cloud data through quaternions. Specifically, the rotation axis direction and rotation angle corresponding to a certain vector (such as a vector vector, a normal vector, etc.) in the element template rotated to a specific position in the point cloud data can be calculated according to the above mapping analysis factors, thereby obtaining the above quaternion based on the rotation axis direction and the rotation angle.

[0094] Step S322: performing quaternion conversion on the template point set of the element template according to the quaternion to obtain a target point set corresponding to the element template in the point cloud data.

[0095] In the specific implementation, if the template point set of the feature template includes the above Figure 2 When the set of points p0 to p6 in the image is composed of n1, we can first calculate n1 (corresponding to Figure 2 The normal vector of the plane where the element template is marked by an arrow) is converted to n2 (corresponding to Figure 5 The quaternion q1 is applied to the above template point set, and the new point set is recorded as t0~t6. Then the vector from t0 to t1 is recorded as u3, and the conversion of u3 to u2 (corresponding to Figure 5The quaternion q2 of the target traffic element is the direction of the arrow when the target traffic element is an arrow mark, and the quaternion conversion of q2 is performed on the point sets t0 to t6 respectively, and the final point set obtained is the target point set corresponding to the above element template in the point cloud data. In addition, in other embodiments, in addition to using quaternions to realize vector rotation, vector rotation can also be realized by using rotation matrices, Euler angles, etc. instead of quaternions, which will not be repeated here.

[0096] In particular, for target traffic elements other than arrow marks, for example, in another embodiment, it is necessary to draw a motor vehicle lane mark in the point cloud data, then the corresponding specific implementation process can be implemented based on at least the following steps: first, the motor vehicle lane mark contour corresponding to the motor vehicle lane mark can be obtained from the point cloud data, and a number of calibration points are selected from the motor vehicle lane mark contour according to the reference points in the motor vehicle lane mark template; then, a number of calibration points are specifically converted according to the conversion rules corresponding to the motor vehicle lane mark, so as to obtain the template point set of the motor vehicle lane mark template; finally, the motor vehicle lane mark is drawn in the point cloud data based on the template point set of the motor vehicle lane mark template. It is understandable that, due to the differences between different target traffic elements, when drawing different target traffic elements, the corresponding conversion rules may be the same or different, and the specific needs to be flexibly set based on the actual scenario, which will not be elaborated here.

[0097] In this embodiment, when the mapping analysis factor includes the coordinates of the calibration point, the arrow direction of the arrow mark, and the normal vector of the plane where the arrow mark is located, the quaternion corresponding to the rotation of the feature template to the point cloud data is calculated based on the mapping analysis factor; the template point set of the feature template is converted into a quaternion according to the quaternion to obtain the target point set corresponding to the feature template in the point cloud data. Compared with the traditional traffic element drawing method, the above method of this embodiment obtains the target point set corresponding to the feature template in the point cloud data based on the rotation of the feature template to the quaternion corresponding to the point cloud data, which greatly reduces the manual workload and reduces the quality requirements of the point cloud data for traffic element drawing.

[0098] In addition, an embodiment of the present application further provides a storage medium, on which a traffic element drawing program is stored. When the traffic element drawing program is executed by a processor, the steps of the traffic element drawing method described above are implemented.

[0099] Reference Figure 7 , Figure 7 This is a structural block diagram of the first embodiment of the traffic element drawing device of the present application.

[0100] like Figure 7 As shown, the traffic element drawing device proposed in the embodiment of the present application includes:

[0101] The contour acquisition module 701 is used to obtain the element contour of the target traffic element from the point cloud data;

[0102] A point calibration module 702, configured to select a plurality of calibration points from the element contour based on reference points in the element template corresponding to the target traffic element;

[0103] The traffic element drawing module 703 is used to draw the target traffic element in the point cloud data according to the spatial position distribution between the multiple calibration points and the template point set of the element template.

[0104] This embodiment obtains the element contour of the target traffic element from the point cloud data; selects multiple calibration points from the element contour based on the reference points in the element template corresponding to the target traffic element; and draws the target traffic element in the point cloud data according to the spatial position distribution between the multiple calibration points and the template point set of the element template. Compared with the traditional traffic element drawing method, the above method of this embodiment only needs to select calibration points from the element contour of the target traffic element in the point cloud data, and then automatically draw the target traffic element into the point cloud data according to the spatial position distribution of the calibration points and the template point set of the element template corresponding to the target traffic element. Since there is no need to rely on manual tracing, the above method of this application not only makes the pattern drawn in the point cloud data more regular and accurate, but also improves the efficiency of pattern drawing.

[0105] Based on the first embodiment of the traffic element drawing device of the present application, a second embodiment of the traffic element drawing device of the present application is proposed.

[0106] In this embodiment, the traffic element drawing module 703 is also used to determine the mapping analysis factor between the element template and the element contour according to the spatial position distribution between the multiple calibration points; determine the target point set corresponding to the element template in the point cloud data according to the mapping analysis factor and the template point set of the element template; and draw the target traffic element in the point cloud data based on the target point set.

[0107] Furthermore, the target traffic element includes a plane figure.

[0108] Furthermore, the target traffic element includes an arrow mark, and the mapping analysis factors include the coordinates of the calibration point, the arrow direction of the arrow mark, and the normal vector of the plane where the arrow mark is located; and / or, the multiple calibration points include a first calibration point, a second calibration point, and a third calibration point, wherein the first calibration point is the starting point of the arrow direction, the second calibration point is any point on the vector vector corresponding to the arrow direction in the arrow mark, and the third calibration point is any point in the plane where the arrow mark is located, and the third calibration point does not overlap with the first calibration point and the second calibration point.

[0109] Furthermore, the traffic element drawing module 703 is also used to calculate the quaternion corresponding to the rotation of the element template to the point cloud data based on the mapping analysis factor; perform quaternion conversion on the template point set of the element template according to the quaternion to obtain the target point set corresponding to the element template in the point cloud data.

[0110] Furthermore, the traffic element drawing module 703 is also used to render the element template based on the target point set to obtain a rendering pattern; and fit the rendering pattern to the element contour to draw the target traffic element in the point cloud data.

[0111] Furthermore, the traffic element drawing module 703 is also used to determine the reference point, positioning edge, vector and plane normal contained in the element template corresponding to the target traffic element according to the sample standard data corresponding to the target traffic element; and to make the element template corresponding to the target traffic element according to the reference point, the positioning edge, the vector and the plane normal.

[0112] Other embodiments or specific implementations of the traffic element drawing device of the present application can refer to the above-mentioned method embodiments, which will not be repeated here.

[0113] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0114] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0115] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0116] The above are only preferred embodiments of the present application, and are not intended to 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 applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for drawing traffic elements, characterized in that: The method comprises the following steps: Obtaining feature outlines of target traffic features from point cloud data; Selecting a plurality of calibration points from the element contour based on reference points in the element template corresponding to the target traffic element; The target traffic element in the point cloud data is drawn according to the spatial position distribution among the multiple calibration points and the template point set of the element template.

2. The method for drawing traffic elements according to claim 1, characterized in that: The step of drawing the target traffic element in the point cloud data according to the spatial position distribution between the multiple calibration points and the template point set of the element template includes: Determining a mapping analysis factor between the element template and the element contour according to the spatial position distribution among the plurality of calibration points; Determining a target point set corresponding to the element template in the point cloud data according to the mapping analysis factor and the template point set of the element template; The target traffic element in the point cloud data is drawn based on the target point set.

3. The method for drawing traffic elements according to claim 1 or 2, characterized in that: The target traffic element includes a plane figure.

4. The method for drawing traffic elements according to claim 2, characterized in that: The target traffic element includes an arrow mark, and the mapping analysis factor includes the coordinates of the calibration point, the arrow direction of the arrow mark, and the normal vector of the plane where the arrow mark is located; And / or, the multiple calibration points include a first calibration point, a second calibration point and a third calibration point, wherein the first calibration point is the starting point of the arrow direction, the second calibration point is any point on the vector corresponding to the arrow direction in the arrow mark, and the third calibration point is any point in the plane where the arrow mark is located, and the third calibration point does not overlap with the first calibration point and the second calibration point.

5. The method for drawing traffic elements according to claim 4, characterized in that: When the mapping analysis factor includes the coordinates of the calibration point, the arrow direction of the arrow mark, and the normal vector of the plane where the arrow mark is located, the step of determining the target point set corresponding to the feature template in the point cloud data according to the mapping analysis factor and the template point set of the feature template includes: Calculate the quaternion corresponding to the rotation of the feature template to the point cloud data based on the mapping analysis factor; The template point set of the element template is converted into a quaternion according to the quaternion to obtain a target point set corresponding to the element template in the point cloud data.

6. The method for drawing traffic elements according to claim 2, characterized in that: The step of drawing the target traffic element in the point cloud data based on the target point set includes: Rendering the element template based on the target point set to obtain a rendering pattern; The rendering pattern is fitted onto the element contour to draw the target traffic element in the point cloud data.

7. The method for drawing traffic elements according to claim 1, characterized in that: The method further includes obtaining an element template corresponding to the target traffic element by: Determine the reference point, positioning edge, vector vector and plane normal contained in the element template corresponding to the target traffic element according to the sample standard data corresponding to the target traffic element; An element template corresponding to the target traffic element is produced according to the reference point, the positioning edge, the vector and the plane normal.

8. A traffic element drawing device, characterized in that: The traffic element drawing device comprises: A contour acquisition module, used to obtain the element contour of the target traffic element from the point cloud data; A point calibration module, used for selecting a plurality of calibration points from the element contour based on reference points in the element template corresponding to the target traffic element; The traffic element drawing module is used to draw the target traffic element in the point cloud data according to the spatial position distribution between the multiple calibration points and the template point set of the element template.

9. A traffic element drawing device, characterized in that: The device comprises: a memory, a processor, and a traffic element drawing program stored in the memory and executable on the processor, wherein the traffic element drawing program is configured to implement the steps of the traffic element drawing method according to any one of claims 1 to 7.

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

Images