CN114723900A

CN114723900A - Contour drawing method of ground element, electronic device and computer program product

Info

Publication number: CN114723900A
Application number: CN202210163501.6A
Authority: CN
Inventors: 胡小坡
Original assignee: Autonavi Software Co Ltd
Current assignee: Autonavi Software Co Ltd
Priority date: 2022-02-22
Filing date: 2022-02-22
Publication date: 2022-07-08

Abstract

The embodiment of the disclosure discloses a contour drawing method of a ground element, electronic equipment and a computer program product, wherein the method comprises the following steps: acquiring a delineation range in the point cloud image; determining point cloud data enclosed in the delineation range in the point cloud image; constructing a road plane based on the point cloud data in the delineating range; constructing a gray image of the point cloud data in the delineating range projected on the road plane based on the reflection intensity of the point cloud data; determining an image block outline of foreground content in the gray image; and drawing the outer contour of the ground element in the point cloud image based on the image block contour. According to the technical scheme, by means of the mode of combining manpower and a machine, when the high-precision map is manufactured, the outline of the ground elements is drawn on the point cloud image in a semi-automatic drawing mode, the high precision can be guaranteed, meanwhile, the labor cost is saved, the manual operation complexity is reduced, and the manufacturing efficiency of the high-precision map is improved.

Description

Contour drawing method of ground element, electronic device and computer program product

Technical Field

The present disclosure relates to the field of location-based services, and in particular, to a method for drawing a contour of a ground element, an electronic device, and a computer program product.

Background

With the development of Location Based Services (LBS), more and more application software integrates service capabilities related to electronic maps. In addition, some artificial intelligence devices also rely on electronic maps, for example, autopilot devices rely on high-precision maps to implement driving processes. Compared with an electronic navigation map used by a driver in a manual driving mode, the high-precision map describes roads through more accurate and rich information so that the automatic driving equipment can understand the road conditions, and therefore the driving process is achieved by executing actions based on the road condition planning actions.

In the manufacturing process of the high-precision map, the outline of the nonlinear ground element needs to be drawn for meeting the automatic driving positioning requirement. Because the requirement on data accuracy is high in automatic driving, a full-automatic mode based on deep learning cannot meet word requirements, and the requirement on high accuracy cannot be met in some scenes, and particularly for processing of an external frame, manual correction and redrawing are frequently required.

However, manual drawing operation is difficult in a three-dimensional scene, and ground abrasion affects manual operation efficiency, so that a simple, efficient and stable drawing scheme is required to solve the technical problem that the outline of a nonlinear ground element is complicated in manual drawing.

Disclosure of Invention

The embodiment of the disclosure provides a contour drawing method of a ground element, electronic equipment and a computer program product.

In a first aspect, an embodiment of the present disclosure provides a method for drawing an outline of a ground element, where the method includes:

acquiring a delineation range in the point cloud image;

determining point cloud data enclosed in the delineation range in the point cloud image;

constructing a road plane based on the point cloud data in the delineating range;

constructing a gray image of the point cloud data in the delineating range after projection on the road plane based on the reflection intensity of the point cloud data;

determining an image block outline of foreground content in the gray image; wherein the foreground content is a component of the ground element;

and drawing the outer contour of the ground element in the point cloud image based on the image block contour.

Further, constructing a gray level image of the point cloud data in the delineating range projected on the road plane based on the reflection intensity of the point cloud data, including:

projecting the point cloud data within the delineating range to the road plane;

and generating the gray image based on the reflection intensity of the projected point cloud data.

Further, drawing the outer contour of the ground element in the point cloud image based on the image block contour, including:

when the image block outline comprises a plurality of outlines, determining vector data of the outer outline of the ground element based on the image block outline with the area larger than or equal to a preset area threshold;

and rendering on the point cloud image based on the vector data to obtain the outer contour of the ground element.

Further, the delineating range comprises a point cloud frame; determining point cloud data enclosed within the delineating range in the point cloud image, including:

carrying out point cloud collision detection on an octree space structure corresponding to the point cloud data on the point cloud image and the point cloud frame to obtain rough point cloud data which has collision with the point cloud frame;

down-sampling the rough point cloud data;

performing accurate point cloud collision detection based on the space coordinates of the rough point cloud data after down-sampling and the point cloud frame;

and eliminating the rough point cloud data outside the point cloud frame based on the detection result, and determining the point cloud data in the delineating range based on the reserved rough point cloud data.

Further, determining an image block contour of foreground content in the grayscale image includes:

and determining the image block outline of the foreground content in the gray image based on the reflection intensity difference of the point cloud data corresponding to the road surface and the point cloud data corresponding to the ground element in the gray image.

Further, the method further comprises:

displaying the point cloud image;

receiving a drawn line range and an extending direction on the point cloud image;

and determining the delineation range surrounding the ground elements of the outline to be drawn based on the line drawing range and the external expansion direction, wherein the delineation range comprises a frame in a preset shape obtained after the line drawing range extends for a certain distance in the external expansion direction.

In a second aspect, an embodiment of the present disclosure provides a method for providing a location-based service, where the method includes: mapping the outline of the ground element on the map by using the method of the first aspect, and mapping the outline of the ground element to provide a location-based service for the served object, wherein the location-based service comprises: one or more of navigation, map rendering, route planning.

In a third aspect, an embodiment of the present disclosure provides an apparatus for profiling a ground element, including:

a first acquisition module configured to acquire a delineation range in a point cloud image;

a first determination module configured to determine point cloud data enclosed within the delineation range in the point cloud image;

a first construction module configured to construct a road plane based on the point cloud data within the delineating range;

a second construction module configured to construct a gray-scale image of the point cloud data within the delineating range projected on the road plane based on the reflection intensity of the point cloud data;

a second determining module configured to determine an image block contour of foreground content in the grayscale image; wherein the foreground content is a component of the ground element;

a drawing module configured to draw an outer contour of the ground element in the point cloud image based on the image block contour.

The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above-described functions.

In one possible design, the apparatus includes a memory configured to store one or more computer instructions that enable the apparatus to perform the corresponding method, and a processor configured to execute the computer instructions stored in the memory. The apparatus may also include a communication interface for the apparatus to communicate with other devices or a communication network.

In a fourth aspect, the disclosed embodiments provide an electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any of the above aspects.

In a fifth aspect, the disclosed embodiments provide a computer-readable storage medium for storing computer instructions for any one of the above apparatuses, which when executed by a processor, are configured to implement the method of any one of the above aspects.

In a sixth aspect, the disclosed embodiments provide a computer program product comprising computer instructions for implementing the method of any one of the above aspects when executed by a processor.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

in the method and the device for drawing the outline of the ground element, the rough range of the ground element to be drawn is drawn by manual assistance, all point cloud data contained in the rough range are automatically determined based on the rough range and the point cloud image, all the point cloud data contained in the rough range are converted into a gray image through the reflection intensity of the point cloud data, the image block outline with foreground content is determined based on the gray image, and the outline of the ground element is rendered on the point cloud image based on the image block outline. According to the embodiment of the invention, through a mode of combining manpower with a machine, when the high-precision map is manufactured, the outline of the ground element is drawn on the point cloud image through a semi-automatic drawing mode, so that the high precision is ensured, the labor cost is saved, the manual operation complexity is reduced, and the manufacturing efficiency of the high-precision map is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. In the drawings:

FIG. 1 illustrates a flow diagram for one implementation of a method for contouring a ground element in accordance with an embodiment of the present disclosure;

FIG. 2 is a schematic block diagram of an electronic device suitable for use in implementing a method of contouring ground elements in accordance with an embodiment of the present disclosure;

FIG. 3 is a schematic data flow diagram of a contour drawing method for a ground element in an execution scene of a data collection vehicle according to an embodiment of the disclosure;

FIG. 4 illustrates an interactive scenario diagram when a method for contouring a ground element is performed at a data production center according to an embodiment of the present disclosure;

5(a) -5 (c) are schematic diagrams illustrating the effect of manually drawing the line drawing range, the delineating range and the outer contour on the road traffic sign in one embodiment of the present disclosure;

FIG. 6 illustrates a scene diagram of a human interaction drawing an outer contour of a ground element according to an embodiment of the present disclosure;

fig. 7 is a block diagram illustrating a configuration of a contour drawing device for a ground element according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.

In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, actions, components, parts, or combinations thereof, and do not preclude the possibility that one or more other features, numbers, steps, actions, components, parts, or combinations thereof are present or added.

It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

The details of the embodiments of the present disclosure are described in detail below with reference to specific embodiments.

FIG. 1 illustrates a flow diagram for one implementation of a method for contouring a ground element according to one embodiment of the present disclosure.

As shown in fig. 1, the contour drawing method of the ground element includes the following steps S101 to S105:

in step S101, the operator draws a line. In this step, an operator may draw a rough contour line of the ground element along the ground element on the point cloud image (the drawn line portion does not require precision), and the point cloud data in the rough contour line corresponds to the point cloud data of the area where the ground element is located. It should be noted that the operator who draws a line in the embodiment of the present disclosure is not limited to an operator, and may be a machine-implemented operator.

In this embodiment, the ground element may be a nonlinear ground element on a road, that is, the ground element according to the embodiment of the present disclosure may be a planar element, and the planar element may include a planar traffic sign on the road surface except for a lane line, for example, a direction arrow sign (see fig. 5(a) -5 (c)), a road sign, a diversion strip, a zebra crossing, and the like.

The point cloud image may be an image formed from point cloud data, and the point cloud data may be a three-dimensional point data set of the actual road surface acquired by a three-dimensional laser scanning instrument.

In a traditional ground element drawing method, shape points of ground elements need to be drawn purely manually, but the traditional ground element drawing method is difficult to operate in a three-dimensional scene and low in manufacturing efficiency.

For this reason, the operator of the embodiment of the present disclosure previously defines an approximate range of the ground elements to be outlined on the point cloud image, which is referred to as a defining range herein, and the defining range provided by the operator may refer to a white frame shown in fig. 5 (b). The ground surface element to be outlined is a nonlinear ground surface element. After the operator provides the delineation range that contains the ground key element of waiting to draw on the point cloud image, can be based on the accurate outline that generates the ground key element of the reflection intensity of point cloud data, delineation range and the point cloud data on this point cloud image, this kind of mode has improved the outline drawing efficiency of ground key element, has reduced the manual operation degree of difficulty when guaranteeing the drawing precision, has saved the cost of labor.

In this embodiment, the delineation range may be a range of all point cloud data corresponding to the ground element including the contour to be drawn on the point cloud image, for example, the delineation range may be a point cloud frame capable of framing the ground element on the point cloud image, and the point cloud frame may be a rectangle, for example.

In some embodiments, the point cloud image may be presented to the operator via a browser or other application interface, and the operator may delineate a region around the ground element to be outlined based on editing functionality provided by the browser or other application interface. All point cloud data of ground elements may be included within the delineation range. In other embodiments, the machine may also be used as an operator to circle a field on the point cloud image.

In step S102, a point cloud frame is generated based on the drawn line of the operator, and point cloud data within the point cloud frame is calculated. That is, in this step, the point cloud data enclosed within the circumscribed range in the point cloud image may be determined based on the circumscribed range given by the line drawing by the operator.

The following describes a way to manually draw a line on a point cloud image and determine point cloud data enclosed within a circumscribed range in the point cloud image based on the manual draw:

2.1 manually draw a line along the ground element, which determines both the orientation of the ground element and the approximate extent of the point cloud frame.

And 2.2, generating a point cloud frame surrounding the point cloud data based on the drawn line expansion.

2.3, carrying out point cloud collision detection by using an octree (octree) space structure of the point cloud frame and the point cloud data, and roughly determining the point cloud data in the point cloud frame.

And 2.4, sending the point cloud frame and the roughly determined point cloud data as parameters to a WebAssembly browser so as to generate an accurate contour of the ground element.

It should be noted that the above is only one possible implementation manner, and the embodiment of the present disclosure is not limited to the above implementation manner, and other implementation manners may also be adopted, for example, a simple set machine model may be trained to draw a line on a point cloud image to generate a point cloud frame enclosing point cloud data where a ground element is located. In addition, the point cloud frame and the roughly determined point cloud data are not limited to be input to the WebAssembly browser to generate the precise contour, and may also be input to other similar software, or the precise contour generation process is realized through programming.

In step 103, a road plane is calculated based on the point cloud data within the circumscribed range.

After all the point cloud data within the defined range are determined, the point cloud data are three-dimensional data, and the ground elements on the road surface are plane figures, namely two-dimensional figures. Therefore, in order to accurately determine the outer contour of the ground element, a road plane is obtained by fitting based on all point cloud data in the delineation range, and in some embodiments, a point cloud plane, which is a road plane, can be obtained by fitting by a least square method.

In some embodiments, the road plane may be fitted from the point cloud data selected by the point cloud frame; an implementation of fitting a road plane using a WebAssembly browser is described below.

3.1 because the point cloud data is dense, the point cloud data can be down-sampled first to reduce the amount of calculation.

3.2 aiming at the point cloud data after the down sampling, performing accurate collision detection from the point cloud to the buffer frame according to the buffer frame, and only keeping the point cloud data in the buffer frame.

3.3 fitting a point cloud plane, namely a road plane, by using a least square method.

In step 104, the outer contour of the ground element is calculated.

The point cloud data can be projected to a road plane, a gray value is obtained based on the reflection intensity of each point in the point cloud data, and the point cloud data in the defined range can be affine transformed into a gray image based on the gray value and the projection point coordinates of the point cloud data on the road plane. That is to say, each pixel point in the grayscale image corresponds to a point projected onto the road plane in the point cloud data, and the pixel value corresponds to the reflection intensity of the point, the higher the reflection intensity is, the higher the pixel value is, and the lower the reflection intensity is, the lower the pixel value is.

Since the ground surface elements on the road surface are generally formed using a material having a lighter color than the asphalt on the road surface, the reflection intensity of the ground surface elements is higher than that of the road surface, and thus the gradation image obtained in this way has a larger gradation value in the area where the ground surface elements are located than that of the road surface area. Therefore, the image block contour of the foreground content in the grayscale image can be calculated by this difference of the grayscale values.

It will be appreciated that the foreground content in the grayscale image may be a component of the ground elements, while the background regions outside the foreground content correspond to the road surface regions.

Referring to fig. 5(b), the ground elements "right-turn arrow" on the road surface are white, the point cloud image in the white frame is an artificially defined range, and after being mapped into the gray scale image, the color of the road surface part is darker and the reflection intensity is lower, so that after being mapped into the gray scale image, the gray scale value is smaller, and the color of the white arrow part is lighter and the reflection intensity is higher, so that the gray scale value after being mapped into the gray scale image is larger. Therefore, the foreground content corresponding to the white arrow part and the background area corresponding to the road surface can be distinguished in the gray image based on the gray value. Considering that there is a color loss due to wear on the white arrow, for example, in a straight-line segment on the white arrow shown in fig. 5(b), some areas in the middle are darker because the color loss is no longer white, and therefore, after mapping to a gray-scale image, these color-loss areas are also identified as road surface areas, so that the finally identified foreground content is not an area in the shape of a complete white arrow, but a plurality of white image blocks with road surfaces at intervals. In the embodiment of the present disclosure, after further processing the contours of the plurality of image blocks corresponding to the identified foreground content, the complete contour of the ground element is obtained.

In some embodiments, the complete outer contour of the face element may be determined by determining a bounding box of the plurality of image block contours and determining the bounding box as the complete outer contour of the face element

In some embodiments, after determining an image block contour corresponding to a foreground content in a grayscale image, an outer contour of a ground element may be rendered in point cloud data based on vector data of the image block contour, where a white rectangular frame shown in fig. 5(c) is an outer contour of a white arrow on a road, and four vertex coordinates on the white rectangular frame are vector data corresponding to the outer contour.

In some embodiments, the image block outline and the outer outline of the ground element may be a bounding box, and the vector data of the image block outline may include vertex coordinates of the bounding box, and the like. Therefore, vector data such as the vertex coordinates of the outer contour of the ground element can be finally determined based on the vertex coordinates of the bounding box of each image block contour.

Therefore, in an optional implementation manner of the present embodiment, in step S104, the step of calculating the outer contour of the ground element further includes the following steps:

constructing a gray image of the point cloud data in the delineating range projected on the road plane based on the reflection intensity of the point cloud data;

determining an image block outline of foreground content in the gray level image;

One implementation of calculating the outer contour of the ground element is described below. It is understood that the calculation of the outer contour of the ground element in the embodiment of the present disclosure is not limited to the following implementation manner, and any manner may be used as long as the method constructs a road plane based on the point cloud data in the defined range, constructs a gray image after the point cloud data in the defined range is projected onto the plane based on the reflection intensity of the point cloud data, determines an image block contour of the gray image including foreground content, and calculates the outer contour of the ground element based on the image block contour.

4.1 projecting all point clouds in the buffer frame onto a road plane;

4.2 carrying out affine on the point cloud in the road plane, and transforming the point cloud to a two-dimensional image; meanwhile, the point cloud reflectivity is mapped to a range of 0-255 as the color value of the corresponding pixel of the point on the two-dimensional image to form a two-dimensional image;

4.3, because the reflection intensity of the individual point cloud is influenced to become noise, Gaussian filtering can be carried out on the two-dimensional image to remove noise points;

4.4, calculating the content contour in the two-dimensional image, wherein the contour of the ground element can be accurately calculated because the reflectivity of the ground element in the ground element area is different from the reflectivity of the ground point cloud under normal conditions; in addition, considering the actual wear of the ground elements on the road surface, the area size of the content contour may be determined, the contours larger than a certain area are superimposed, the complete contour of the ground elements is obtained through calculation, the complete contour obtained through calculation is vector data on the two-dimensional image, that is, the boundary point coordinates of the complete contour, for example, when the complete contour is represented by a rectangular frame, the vector data may be four vertices of the rectangular frame, for example, a white line frame shown in fig. 5(c) is a complete contour of a "right-turning arrow" of the ground elements, and the four vertices are vector data obtained by superimposing the contours of a plurality of image blocks corresponding to the foreground content.

In step 105, the outer contour of the ground element is rendered.

One manner of rendering the outline of the ground element is described below.

5.1 rendering vector data based on the calculated outer contour of the ground element. In consideration of the fact that the calculated vector data is data on a two-dimensional image, inverse affine transformation of the vector data onto a point cloud image is performed, and rendering is performed on the point cloud image based on the transformed vector data.

5.2 human or other external objects need only verify that the outline meets the requirements.

Fig. 2 is a schematic structural diagram of an electronic device suitable for implementing a method of contouring a ground element in accordance with an embodiment of the present disclosure.

As shown in fig. 2, the electronic device 200 comprises a processing unit 201, which may be implemented as a CPU, GPU, FPGA, NPU, or the like processing unit. The processing unit 201 may perform various processes in the embodiment of any one of the above-described methods of the present disclosure according to a program stored in a Read Only Memory (ROM)202 or a program loaded from a storage section 208 into a Random Access Memory (RAM) 203. In the RAM 203, various programs and data necessary for the operation of the electronic apparatus 200 are also stored. The processing unit 201, the ROM 202, and the RAM 203 are connected to each other via a bus 204. An input/output (I/O) interface 205 is also connected to bus 204.

The following components are connected to the I/O interface 205: an input portion 206 including a keyboard, a mouse, and the like; an output section 207 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 208 including a hard disk and the like; and a communication section 209 including a network interface card such as a LAN card, a modem, or the like. The communication section 209 performs communication processing via a network such as the internet. A drive 210 is also connected to the I/O interface 205 as needed. A removable medium 211 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 210 as necessary, so that the computer program read out therefrom is mounted into the storage section 208 as necessary.

The electronic device may be a client device or a cloud device as a device for implementing any of the methods described above in the embodiments of the present disclosure.

Fig. 3 is a schematic data flow diagram illustrating a data flow of a contour drawing method for a ground element in an execution scenario of a data collection vehicle according to an embodiment of the disclosure. As shown in fig. 3, the data collection vehicle may be equipped with a client device and a lidar. The client device may be implemented as the electronic device shown in fig. 2. The lidar may collect point cloud data of a road and provide the point cloud data to the client device.

The client device displays the point cloud image corresponding to the point cloud data on a client interface for a human operator to draw lines. The human operator delineates the range of the ground element to be drawn on the point cloud image by drawing a line, and the client executes the method in the embodiment after acquiring the delineated range, so that the accurate contour of the ground element on the point cloud image is automatically determined, and drawing data of the ground element, such as point cloud data in the accurate contour and other related data, can be determined based on the accurate contour. The mapping data may be sent to a map server, which may store the mapping data as part of the map data, and when mapping a map using the map data, may use the mapping data to map the ground element at a corresponding location on the map.

FIG. 4 illustrates an interactive scenario when the method for profiling a ground element is performed in a data production center according to an embodiment of the present disclosure. As shown in fig. 4, the cloud device may be a device disposed in a data production center, and the cloud device may be implemented by the electronic device shown in fig. 2. The data acquisition device, such as a data acquisition vehicle mounted with a laser radar, acquires point cloud data of a road and provides the point cloud data to the cloud device.

And the cloud equipment sends the point cloud image corresponding to the point cloud data to client equipment used by a human operator. And displaying the point cloud image on the client device.

The manual operator delineates the range of the ground element to be drawn on the point cloud image by drawing a line, and the client executes the method in the embodiment after acquiring the delineated range, so that the accurate contour of the ground element on the point cloud image is automatically determined, and drawing data of the ground element, such as point cloud data in the accurate contour and other related data, can be determined based on the accurate contour. The mapping data may be sent to a map server, which may store the mapping data as part of the map data, and when mapping a map using the map data, may use the mapping data to map the ground element at a corresponding location on the map.

In the method, during the process of drawing the outer contour of the ground element, an external object such as a machine such as a manual or running machine model is used for drawing an approximate range of the ground element to be drawn, all point cloud data contained in the approximate range are automatically determined based on the approximate range and the point cloud image, all point cloud data contained in the approximate range are converted into a gray scale image through the reflection intensity of the point cloud data, an image block contour with foreground content is determined based on the gray scale image, and the outer contour of the ground element is rendered on the point cloud image based on the image block contour. According to the embodiment of the invention, by means of combination of the external object and the machine, when the high-precision map is manufactured, the outline of the ground element is drawn on the point cloud image in a semi-automatic drawing mode, so that the high precision is ensured, the labor cost is saved, the manual operation complexity is reduced, and the manufacturing efficiency of the high-precision map is improved.

In an optional implementation manner of this embodiment, in step S104, the step of drawing the outer contour of the ground element in the point cloud image based on the image block contour further includes the following steps:

In this alternative implementation, the pattern of the ground elements may be subject to wear due to the actual road, e.g. the border is not clear, the middle piece shows the road due to wear, etc. Therefore, after converting the point cloud data in the defined range into a grayscale image, the image block contour determined from the grayscale image is not necessarily the complete contour of the ground element, and may be a plurality of image block contours after being segmented in the worn area. Thus, in this case, the complete outer contour of the ground element can be obtained by superimposing the plurality of image block contours.

In addition, considering that stains may exist around the ground elements or the image block contours detected in the grayscale image due to other reasons, the image block contours with the areas smaller than the preset threshold value can be removed according to the area size of the image block contours, and the image block contours with the areas larger than or equal to the preset threshold value are only used for superposition to obtain the complete outer contour of the ground elements.

In a grayscale image, an image block contour may be represented by vector data, for example, when the image block contour is a rectangle, the image block contour may be represented by coordinates of four points of the rectangle, and a plurality of image block contours are superimposed, and actually, coordinates of four points corresponding to the plurality of image block contours are superimposed, for example, vector data of a superimposed complete outer contour may be obtained by taking a maximum value, that is, values of coordinates of four points of the complete outer contour are taken, so that the complete outer contour is a maximum circumscribed frame of the plurality of image block contours.

In an optional implementation of this embodiment, the delineation range includes a point cloud frame; the step of determining point cloud data in the point cloud image, which is enclosed in the delineation range, further comprises the following steps:

down-sampling the rough point cloud data;

performing accurate point cloud collision detection on the basis of the space coordinates of the roughly point cloud data after the down-sampling and the point cloud frame;

In this alternative implementation, the point cloud data is typically stored in the form of an octree space structure, where each node stores a block of point cloud data, which may include a plurality of points in the point cloud data. In order to reduce the amount of calculation, in the embodiment of the present disclosure, a point cloud frame corresponding to an octree space structure and a bounding range is first used for point cloud collision detection, and a point cloud block having a collision with the point cloud frame is determined as coarse point cloud data.

It will be appreciated that the point cloud block includes a plurality of points in the point cloud data, and that the point cloud block, if it collides with the point cloud frame, indicates that the point cloud block is located near the bounding frame, and may be a block of point cloud data across the bounding frame. If the point cloud block crosses the frame, partial point cloud data in the point cloud block is not in the defined range. Therefore, the point cloud data within the delineation range cannot be determined directly based on the rough point cloud data, and the point cloud data outside the point cloud frame in the point cloud block across the frame needs to be removed.

Therefore, the embodiment of the disclosure also performs accurate point cloud collision detection once. In the accurate collision detection process of the point cloud, point cloud collision is carried out on a point cloud block which has collision with a point cloud frame based on the space coordinates of all points in the point cloud block and the point cloud frame, and a detection result is determined. The detection result may include accurate point cloud data having a collision with the point cloud frame, point cloud data located at a boundary of the point cloud frame and point cloud data located inside the point cloud frame may be determined based on the accurate point cloud data, and point cloud data located at a boundary of the point cloud frame and point cloud data located inside the point cloud frame may be determined as point cloud data within a bounding range.

In an optional implementation manner of this embodiment, the step of determining an image block contour of foreground content in the grayscale image further includes the following steps:

In this alternative implementation, as described above, the pixel value of each pixel point in the grayscale image is determined based on the reflection intensity of the corresponding point cloud data. According to a common theory, the color of the ground elements in the actual road is lighter than that of the road surface, and the reflection intensity of the ground elements is greater than that of the road surface. Therefore, the reflection intensities of the ground elements and the point cloud data on the road surface in the point cloud data are different, and after the gray level image is generated through affine transformation, the difference of the reflection intensities is reflected on the gray level value, the part with the large reflection intensity forms the foreground content in the gray level image, and the part with the small reflection intensity forms the background in the gray level image. Therefore, the image block outline where the foreground content is located can be determined from the gray-scale image based on the gray-scale image and the pixel value difference corresponding to the reflection intensity difference.

In an optional implementation manner of this embodiment, the method further includes the following steps:

displaying the point cloud image;

and determining the delineation range surrounding the ground element to be drawn based on the line drawing range and the external expansion direction, wherein the delineation range comprises a frame in a preset shape obtained after the external expansion direction is expanded for a certain distance in the line drawing range.

In this optional implementation, the point cloud image of the road may be displayed on a display interface, and a drawing person draws a line on the ground element of the contour to be drawn by using an editing function provided on the display interface. The line may be oriented along the length of the ground element and the length of the line may be greater than or equal to the total length of the ground element. A line drawing range on the floor element can be obtained based on the line drawing operation by the drawing person, the line drawing range including a start point, an end point, a line length, and the like of the line drawing. Further, the painter may also specify a flaring direction of the drawn line after the drawn line is complete, for example the flaring direction may be perpendicular to the direction of the drawn line. After the drawn line and the outward expansion direction of the drawing person are detected, the drawn line can be expanded to the outward expansion direction within the range of the drawn line for a certain distance to obtain a frame with a preset shape. In some embodiments, the distance of the extension may be controlled by a drawing person, or may be set based on a preset default distance of the extension, which may be specifically set based on an actual application, and is not described herein again. Of course, it is understood that the point cloud image may be provided to other external objects such as a machine model, and the line drawing range and the extending direction may be provided by the external objects based on the corresponding manner.

In some embodiments, the drawing staff may specify an extending direction, and the actual extending occurs in the extending direction and a direction opposite to the extending direction, so as to finally obtain a frame that completely encloses the ground elements.

In some embodiments, after obtaining an initial range based on the drawn line range and the extending direction of the drawing person, the drawing person may further modify the initial range by using an editing function provided by the display interface, so that the initial range may surround all the ground elements and have the smallest area.

Fig. 5(a) -5 (c) are schematic diagrams illustrating the effect of manually drawing the line drawing range, the delineating range and the outer contour on the road traffic sign in an embodiment of the disclosure. As shown in fig. 5(a), in the 3D point cloud image, on the road driving right turn marking line, a vertical line is manually drawn by using a mouse, and the outward expansion direction is designated as a direction perpendicular to the vertical line by means of mouse dragging, so as to obtain the delineation range shown in fig. 5 (b). As can be seen from fig. 5(b), the manually drawn delineation range surrounds the road driving right turn sign, but the delineation range has poor precision, and the border is far away from the outer border of the road driving right turn sign line and is significantly larger than the outer border of the road driving right turn sign line. After the processing of the embodiment of the present disclosure, the outer contour as shown in fig. 5(c) can be obtained, and as can be seen from fig. 5(c), the accuracy of the outer contour is high and is completely matched with the external frame of the left-turn marking line of the road vehicle.

FIG. 6 shows a scene diagram of a human interaction drawing of an outer contour of a ground element according to an embodiment of the present disclosure. As shown in fig. 6, the point cloud image is displayed in the browser, the user draws a line and designates an extension direction on the point cloud image through the interactive input interface, the browser can automatically generate a delineation range based on the drawn line and the extension direction, if the automatically generated delineation range is correct, the automatically generated delineation range can be submitted to the background for processing, and the operator can also manually adjust the delineation range. And after receiving the delineation range and the point cloud data, the background performs three-dimensional geometric operation to determine the point cloud data in the delineation range, performs plane fitting on the point cloud data, projects the point cloud data onto a plane obtained by fitting, and further obtains a two-dimensional image by utilizing the projected data. And processing the two-dimensional image to obtain the outer contour of the ground element, and automatically drawing the outer contour on the point cloud image so as to display the outer contour on the interface of the browser.

According to an embodiment of the present disclosure, a method for providing a location-based service, which draws an outline of a ground element on a map by using the method for drawing an outline of a ground element and draws a map having the outline of the ground element, provides a location-based service to an object to be serviced, the method comprising: one or more of navigation, map rendering, route planning.

In this embodiment, the location-based service providing method may be executed on a terminal, where the terminal is a mobile phone, an ipad, a computer, a smart watch, an autonomous vehicle, or the like. When a map, for example, a high-definition map is created, the outline of the ground element can be drawn by the above-described contour drawing method for the ground element. It should be noted that the high-precision map may be a map having precise vehicle position information and rich road element data information, the high-precision map has detailed surface feature expression therein, and road network data expressed in the high-precision map includes accurate lane shapes, and further includes detailed data of a slope, a curvature, a heading, an elevation, a roll, and the like of each lane. Therefore, for the ground elements in the high-precision map, the contour drawing method of the ground elements can be adopted for drawing.

According to the embodiment of the disclosure, the outline of the ground element can be drawn for any road in the process of making the high-precision map, and the high-precision map can be provided for the served object, so as to provide more accurate position service for the served object, such as navigation service, path planning service and/or map rendering service.

The served object may be a cell phone, ipad, computer, smart watch, autonomous vehicle, robot, etc. Before navigating, planning a path or rendering a road on a map for a served object, a ground element on a high-precision map can be manufactured based on the method, and then, when navigating, planning a path or rendering a map, a service is provided based on the high-precision map, and specific details can be referred to the description of the method for determining the attribute of the target road element, which is not described herein again.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.

Fig. 7 is a block diagram illustrating a configuration of a contour drawing device for a ground element according to an embodiment of the present disclosure. The apparatus may be implemented as part or all of an electronic device through software, hardware, or a combination of both. As shown in fig. 7, the contour drawing device for a ground element includes:

a first obtaining module 701 configured to obtain a delineation range in a point cloud image;

a first determining module 702 configured to determine point cloud data enclosed within the delineation range in the point cloud image;

a first construction module 703 configured to construct a road plane based on the point cloud data within the delineating range;

a second constructing module 704 configured to construct a grayscale image of the point cloud data within the delineating range projected on the road plane based on the reflection intensity of the point cloud data;

a second determining module 705 configured to determine an image block contour of foreground content in the grayscale image; wherein the foreground content is a component of the ground element;

a drawing module 706 configured to draw an outer contour of the ground element in the point cloud image based on the image block contour.

In this embodiment, the ground element may be a nonlinear ground element on a road, that is, the ground element according to the embodiment of the present disclosure may be a planar element, and the planar element may include a planar traffic sign on the road surface except for a lane line, for example, a directional arrow sign, a road sign, a diversion strip, a zebra crossing, and the like.

Therefore, the embodiment of the disclosure adopts a man-machine combination mode, and the approximate range of the ground elements to be drawn with the outline on the point cloud image is manually and previously defined, which is called as the defined range. The ground surface element to be outlined is a nonlinear ground surface element. After the definition range of the ground elements to be drawn is artificially provided on the point cloud image, the machine can accurately generate the outline of the ground elements based on the point cloud data on the point cloud image, the definition range and the reflection intensity of the point cloud data, the outline drawing efficiency of the ground elements is improved by the method, the drawing precision is ensured, the manual operation difficulty is reduced, and the labor cost is saved.

In this embodiment, the delineation range may be a range of all point cloud data corresponding to the ground element including the contour to be drawn on the point cloud image, for example, the delineation range may be a frame capable of framing the ground element on the point cloud image, such as a rectangular frame.

The point cloud image may be presented to a drafter via a browser or other application interface, and the drafter may define a range around the ground element to be outlined based on an editing function provided by the browser or other application interface. All point cloud data of ground elements may be included within the delineation range.

Based on the bounding range, all point cloud data contained within the bounding range may be determined. In some embodiments, the point cloud data enclosed within the circumscribed range may be obtained by point cloud collision detection, and then the point cloud data within the circumscribed range may be converted into a grayscale image, and the grayscale value in the grayscale image may be determined based on the reflection intensity of the point cloud data. The stronger the reflection intensity, the higher the corresponding grey value, while the lower the reflection intensity, the lower the corresponding grey value may be.

After all the point cloud data located in the delineation range are determined, the point cloud data are three-dimensional data, and the ground elements on the road surface are plane graphs, so that in order to accurately determine the outer contours of the ground elements, a road plane is obtained by fitting based on all the point cloud data in the delineation range.

It will be appreciated that the foreground content in the grayscale image corresponds to ground elements, while the background region outside the foreground content corresponds to a road surface region.

After an image block contour corresponding to the foreground content is determined in the grayscale image, an outer contour of the ground element may be rendered in the point cloud data based on vector data of the image block contour. In some embodiments, the image block outline and the ground element outline may be a bounding box, and the vector data of the image outline may include vertex coordinates of the bounding box, or the like.

In an optional implementation manner of this embodiment, the second building module includes:

a projection sub-module configured to project the point cloud data within the delineating range to the road plane;

a generation sub-module configured to generate the grayscale image based on the reflection intensity of the projected point cloud data.

In this alternative implementation,

the point cloud data can be projected to a road plane, a gray value is obtained based on the reflection intensity of each point in the point cloud data, and the point cloud data in the defined range can be affine transformed into a gray image based on the gray value and the projection point coordinates of the point cloud data on the road plane. That is to say, each pixel point in the gray image corresponds to a point projected onto the road plane in the point cloud data, and the pixel value corresponds to the reflection intensity of the point, the higher the reflection intensity is, the higher the pixel value is, and the lower the reflection intensity is, the lower the pixel value is.

In an optional implementation manner of this embodiment, the drawing module includes:

a first determining sub-module configured to determine, when the image block contour includes a plurality of image blocks, vector data of an outer contour of the ground element based on the image block contour having an area greater than or equal to a preset area threshold;

a rendering submodule configured to render an outer contour of the ground element on the point cloud image based on the vector data.

In an optional implementation of this embodiment, the delineation range includes a point cloud frame; the first determining module includes:

a first detection sub-module configured to perform point cloud collision detection on an octree space structure corresponding to the point cloud data on the point cloud image and the point cloud frame to obtain rough point cloud data having a collision with the point cloud frame;

a downsampling sub-module configured to downsample the coarse point cloud data;

a second detection sub-module configured to perform accurate point cloud collision detection with the point cloud frame based on the down-sampled spatial coordinates of the coarse point cloud data;

and the second determining sub-module is configured to reject the rough point cloud data outside the point cloud frame based on the detection result and determine the point cloud data in the delineation range based on the retained rough point cloud data.

In an optional implementation manner of this embodiment, the second determining module includes:

and the third determining submodule is configured to determine an image block outline of the foreground content in the gray-scale image based on the reflection intensity difference of the point cloud data corresponding to the road surface and the point cloud data corresponding to the ground element in the gray-scale image.

In an optional implementation manner of this embodiment, the apparatus further includes:

a presentation module configured to present a point cloud image;

a receiving module configured to receive a range of drawn lines on the point cloud image and a direction of dilation;

and the third determining module is configured to determine the delineation range surrounding the ground element of the contour to be drawn based on the drawn line range and the outward extending direction, wherein the delineation range comprises a frame in a preset shape obtained after the drawn line range is extended for a certain distance towards the outward extending direction.

In the optional implementation manner, the point cloud image of the road can be displayed on the display interface, the drawing personnel can draw a line on the ground element to be drawn with the contour by using the editing function provided on the display interface, the direction of the line can be along the length direction of the ground element, and the length of the line can be greater than or equal to the total length of the ground element. A line drawing range on the ground element including a start point, an end point, a line length, and the like of the line drawing can be obtained based on the line drawing operation by the drawing person. Further, the painter may also specify a flaring direction of the drawn line after the drawn line is complete, for example the flaring direction may be perpendicular to the direction of the drawn line. After the drawn line and the outward expansion direction of the drawing person are detected, the drawn line can be expanded to the outward expansion direction within the range of the drawn line for a certain distance to obtain a frame with a preset shape. In some embodiments, the distance of the extension may be controlled by a drawing person, or may be set based on a preset default distance of the extension, specifically based on an actual application, and is not described herein again.

In some embodiments, the drawing staff may specify an outward expansion direction, and the actual outward expansion occurs in the outward expansion direction and the opposite direction of the outward expansion direction, so that a frame that completely encloses the ground elements is finally obtained.

According to an embodiment of the present disclosure, there is provided a location-based service providing apparatus for providing a location-based service to an object to be serviced by drawing an outline of a ground element on a high-precision map using an outline drawing apparatus for the ground element and drawing the high-precision map having the outline of the ground element, the location-based service providing apparatus including: one or more of navigation, map rendering, route planning.

In this embodiment, the location-based service providing apparatus may be implemented on a terminal, and the terminal may be a mobile phone, an ipad, a computer, a smart watch, an autonomous vehicle, or the like. When a high-precision map is manufactured, the outline drawing device of the ground elements can be used for drawing the outline of the ground elements in a manual combination mode.

According to the embodiment of the disclosure, the outline of the ground element can be drawn for any road so as to make a high-precision map, and the high-precision map can be provided for the served object so as to provide more accurate position services for the served object, such as navigation services, path planning services and/or map rendering services.

The served object may be a cell phone, ipad, computer, smart watch, autonomous vehicle, robot, etc. Before navigating, planning a path or rendering a road on a map for a served object, a ground element on a high-precision map can be manufactured based on the device, and then, when navigating, planning a path or rendering a map, a service is provided based on the high-precision map, and specific details can be referred to the description of the attribute determining device for the target road element, which is not described herein again.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation on the units or modules themselves. As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the above-described embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims

1. A method of contouring a ground element, comprising:

acquiring a delineation range in the point cloud image;

2. The method of claim 1, wherein constructing a grayscale image of the delineated range of point cloud data projected on the road plane based on the reflection intensity of the point cloud data comprises:

projecting the point cloud data within the delineating range to the road plane;

3. The method of claim 1 or 2, wherein drawing the outer contour of the ground element in the point cloud image based on the image block contour comprises:

4. The method of claim 1 or 2, wherein the delineation range comprises a point cloud box; determining point cloud data enclosed within the delineating range in the point cloud image, including:

down-sampling the rough point cloud data;

5. The method of claim 1 or 2, wherein determining an image block contour of foreground content in the grayscale image comprises:

6. The method according to claim 1 or 2, wherein the method further comprises:

displaying the point cloud image;

receiving a line drawing range and an outward expansion direction on the point cloud image;

7. A location-based service providing method, comprising: mapping the outline of the ground element on the map using the method of any one of claims 1-6 and mapping the outline of the ground element with the map providing location-based services to the serviced object, the location-based services comprising: one or more of navigation, map rendering, route planning.

8. An apparatus for contouring a ground element, comprising:

a first acquisition module configured to acquire a delineating range in a point cloud image;

a first construction module configured to construct a road plane based on point cloud data within the delineating range;

a second construction module configured to construct a gray image of the point cloud data within the delineation range projected on the road plane based on the reflection intensity of the point cloud data;

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any of claims 1-6.

10. A computer program product comprising computer instructions, wherein the computer instructions, when executed by a processor, implement the method of any one of claims 1-6.