CN109583313B - Lane line extraction method, device and storage medium - Google Patents
Lane line extraction method, device and storage medium Download PDFInfo
- Publication number
- CN109583313B CN109583313B CN201811290738.0A CN201811290738A CN109583313B CN 109583313 B CN109583313 B CN 109583313B CN 201811290738 A CN201811290738 A CN 201811290738A CN 109583313 B CN109583313 B CN 109583313B
- Authority
- CN
- China
- Prior art keywords
- point
- points
- key
- lane line
- base map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Instructional Devices (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method and a device for extracting a lane line and a storage medium, wherein a reflection value base map is obtained according to laser point cloud data, the lane line is projected on the reflection value base map to obtain a reflection value base map containing the lane line, and the lane line on the reflection value base map is corrected to obtain a corrected reflection value base map. In the process, a lane line is extracted based on a shot image of an aerial shooting device and the like, a mark point is obtained based on the lane line on a reflection value base map, the lane line obtained according to the shot image is projected on the reflection value base map, and then the lane line projected on a reflection value low map is corrected according to the mark point, so that the purpose of obtaining an accurate lane line is achieved.
Description
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to a lane line extraction method, a lane line extraction device and a storage medium.
Background
The high-precision map plays an important role in scenes such as position finding, automatic navigation and even automatic driving. In the automatic driving process, the automatic driving vehicle drives according to a navigation path planned on a high-precision map in advance, and the navigation path is at least accurate to a lane level. Therefore, when a high-precision map is created, it is necessary to draw a lane line on the high-precision map.
Under the condition of passing, the lane line is extracted based on the laser point cloud data, and the extracted lane line is marked on the high-precision map. The laser point cloud data is obtained by adopting a laser scanning mode; when a laser beam irradiates the surface of an object, the reflected laser beam carries information such as direction, distance and the like. When the laser beam is scanned along a certain trajectory, the reflected laser spot information is recorded while scanning, and since the scanning is extremely fine, a large number of laser spots can be obtained, and thus, laser point cloud data of an object can be formed. Laser point cloud data is a collection of a large number of point clouds characteristic of a target surface. In the lane line extraction process based on laser point cloud data, point cloud obtained according to a laser measurement principle comprises three-dimensional coordinates (XYZ) and laser reflection information; a point cloud obtained according to photogrammetry principles, comprising three-dimensional coordinates (XYZ); and combining laser measurement and photogrammetry principles to obtain a point cloud comprising three-dimensional coordinates (XYZ) and laser reflection information. And representing the laser point cloud data according to the reflection information in the point cloud, and acquiring a reflection value base map corresponding to the laser point cloud data. Since the lane line has a substance such as paint, the reflection intensity of a point on the lane line is different from that of a point on the ground other than the lane position, and therefore the lane line can be extracted based on the reflection value base map.
In the process of extracting the lane line through the reflection value base map, the resolution ratio of the reflection value base map obtained according to the laser point cloud data is high, and the extracted lane line is easy to break.
Disclosure of Invention
The embodiment of the invention provides a lane line extraction method, a lane line extraction device and a storage medium, wherein the lane line is projected onto a reflection value base map based on the lane line obtained by an aerial image, and the lane line projected onto a reflection value low map is corrected according to mark points based on mark points obtained by the lane line on the reflection value base map, so that accurate lane lines are obtained.
In a first aspect, an embodiment of the present invention provides a lane line extraction method, where the method includes:
determining a reflection value base map according to laser point cloud data obtained by scanning a road surface, and projecting a lane line on the reflection value base map, wherein the lane line is extracted according to a shot image, and the shot image is an image obtained by shooting the road surface by a shooting device;
dividing the reflection value base map to obtain a mark point set, wherein the mark point set comprises at least one mark point, and the at least one mark point is a point on an initial lane line obtained through the laser point cloud data;
and correcting the lane lines projected on the reflection value base map according to the marked point set.
In a possible implementation manner, before the correcting the lane line projected on the reflection value base map according to the marker point set, the method further includes:
determining at least one key point on the lane line;
and determining whether the mark point set of the key point exists or not according to the position of any key point in the at least one key point.
In one possible implementation, the correcting the lane line projected on the reflection value base map according to the marker point set includes:
determining M key points from the at least one key point, wherein the M key points are sequentially continuous key points, mark points of any one key point in the key points exist in the mark point set, and M is greater than or equal to a first threshold and is an integer;
and translating the line segments among the M key points in the lane line to the line segments formed by the M mark points corresponding to the M key points.
In one possible implementation, the correcting the lane line projected on the reflection value base map according to the marker point set includes:
determining N key points from the at least one key point, wherein the N key points are sequentially continuous key points, a mark point of any one key point in the N key points does not exist in the mark point set, and N is an integer and is greater than or equal to a second threshold;
determining a supplementary point corresponding to each key point in the N key points on the reflection value base map to obtain N supplementary points;
and replacing line segments among the N key points in the lane line by using a line formed by the N supplementary points.
In a possible implementation manner, the determining, on the reflection value base map, a supplementary point corresponding to each of the N key points to obtain N supplementary points includes:
determining a supplementary point corresponding to each key point in the N key points on the reflection value base map according to a lane line moving formula to obtain N supplementary points; the lane line moving formula is as follows:
xkm′＝xkm；
wherein y represents a y coordinate, and for any one first key point (x) on the k-th line segment in the line segments formed by the N key pointskm，ykm) The first key point (x)km，ykm) The first supplementary point of (a) is (x)km′，ykm′)，yirA y coordinate representing a rightmost mark point, wherein the rightmost mark point is a rightmost mark point in all mark points on the left side of the first supplementary point, the rightmost mark point is positioned on the ith line in the line segments sequentially obtained by the N supplementary points, and the y coordinate is used for representing the rightmost mark pointjlThe y coordinate of a leftmost mark point is represented, the leftmost mark point is the leftmost point of all mark points on the right of the first supplementary point, the leftmost mark point is positioned on the jth line segment of the line segments sequentially obtained by the N supplementary points, and y is representedir,kDenotes yirY coordinate of a point normally projected on the k-th line in the line segment formed by the N key points, yjl,kDenotes yjlAnd the y coordinate of a point normally projected on the k-th line in the line segment formed by the N key points. i. j and k are positive integers, and the values of i and j are different.
In a possible implementation manner, before the correcting the lane line projected on the reflection value base map according to the marker point set, the method further includes:
rotating the reflection value base map so that the lane line is in a horizontal direction.
In a possible implementation manner, the determining whether a marker point of a key point exists in the marker point set according to a position of any key point in the at least one key point includes:
if the key point has at least two mark points, sequencing the at least two mark points according to the confidence degree to obtain a mark point queue, and taking the first mark point in the mark point queue as the mark point of the key point.
In a second aspect, an embodiment of the present invention provides a lane line extraction device, including:
the projection module is used for determining a reflection value base map according to laser point cloud data obtained by scanning a road surface and projecting a lane line on the reflection value base map, wherein the lane line is extracted according to a shot image, and the shot image is an image obtained by shooting the road surface by a shooting device;
the processing module is used for carrying out segmentation processing on the reflection value base map to obtain a marking point set, wherein the marking point set comprises at least one marking point, and the at least one marking point is a point on an initial lane line obtained through the laser point cloud data;
and the correction module is used for correcting the lane line projected on the reflection value base map according to the marking point set.
In a possible implementation manner, the apparatus further includes:
a determination module for determining at least one keypoint on a lane line projected on the reflection value base map before the projection module corrects the lane line according to the set of marker points; and determining whether the mark point set of the key point exists or not according to the position of any key point in the at least one key point.
In a feasible implementation manner, the correction module is specifically configured to determine M key points from the at least one key point, where the M key points are consecutive key points, and a mark point of any one key point in the key points exists in the mark point set, where M is greater than or equal to a first threshold and is an integer; and translating the line segments among the M key points in the lane line to the line segments formed by the M mark points corresponding to the M key points.
In a feasible implementation manner, the correction module is specifically configured to determine N key points from the at least one key point, where the N key points are consecutive key points, and no mark point of any key point in the N key points exists in the mark point set, and N is greater than or equal to a second threshold and is an integer; determining a supplementary point corresponding to each key point in the N key points on the reflection value base map to obtain N supplementary points; and replacing line segments among the N key points in the lane line by using a line formed by the N supplementary points.
In a feasible implementation manner, the correction module is configured to determine, on the reflection value base map, a supplementary point corresponding to each key point of the N key points, and when the N supplementary points are obtained, specifically, determine, according to a lane line movement formula, a supplementary point corresponding to each key point of the N key points on the reflection value base map, so as to obtain N supplementary points; the lane line moving formula is as follows:
xkm′＝xkm；
wherein y represents a y coordinate, and for any one first key point (x) on the k-th line segment in the line segments formed by the N key pointskm，ykm) The first key point (x)km，ykm) The first supplementary point of (a) is (x)km′，ykm′)，yirThe y coordinate of the rightmost mark point is represented, the rightmost mark point is the rightmost mark point in all the mark points on the left side of the first supplementary point, and the rightmost mark point is positioned on a line sequentially obtained by the N supplementary pointsOn the ith line in a segment, yjlThe y coordinate of a leftmost mark point is represented, the leftmost mark point is the leftmost point of all mark points on the right of the first supplementary point, the leftmost mark point is positioned on the jth line segment of the line segments sequentially obtained by the N supplementary points, and y is representedir,kDenotes yirY coordinate of a point normally projected on the k-th line in the line segment formed by the N key points, yjl,kDenotes yjlAnd the y coordinate of a point normally projected on the k-th line in the line segment formed by the N key points. i. j and k are positive integers, and the values of i and j are different.
In a possible implementation manner, the apparatus further includes:
a rotation module for rotating the reflection value base map so that the lane line is in a horizontal direction before the correction module corrects the lane line projected on the reflection value base map according to the marker point set.
In a feasible implementation manner, the determining module is specifically configured to, if at least two marker points exist in the key point, sort the at least two marker points according to the confidence level to obtain a marker point queue, and use a first marker point in the marker point queue as a marker point of the key point.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the method according to the first aspect or the various possible implementations of the first aspect.
In a fourth aspect, embodiments of the present invention provide a storage medium having stored therein instructions, which, when executed on a computer, cause the computer to perform the method according to the first aspect or the various possible implementations of the first aspect.
In a fifth aspect, embodiments of the present invention provide a computer program product, which when run on a computer, causes the computer to perform the method according to the first aspect or the various possible implementations of the first aspect.
According to the method, the device and the storage medium for extracting the lane lines, provided by the embodiment of the invention, the base map of the reflection values is obtained according to the laser point cloud data, the lane lines are projected on the base map of the reflection values to obtain the base map of the reflection values containing the lane lines, and the lane lines on the base map of the reflection values are corrected to obtain the base map of the reflection values after correction processing. In the process, a lane line is extracted based on a shot image of an aerial shooting device and the like, a mark point is obtained based on the lane line on a reflection value base map, the lane line obtained according to the shot image is projected on the reflection value base map, and then the lane line projected on a reflection value low map is corrected according to the mark point, so that the purpose of obtaining an accurate lane line is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is an application environment diagram of a lane line extraction method according to an embodiment of the present invention;
fig. 2 is a flowchart of a lane line extraction method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a lane line calibration method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a lane line extraction device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of another lane line extraction device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is an application environment diagram of a lane line extraction method according to an embodiment of the present invention. Referring to fig. 1, a network connection is established between an electronic device and a server, a network connection is established between a shooting device, such as an aerial shooting device and an industrial camera, and the server is used for storing pictures and the like shot by the shooting device, and a network connection is established between a laser scanner and the server, and the server is used for storing laser point cloud data obtained by scanning a road by the laser scanner. The electronic device can acquire the shot image, the laser point cloud data and the like through the server.
Referring to fig. 1, the lane line extraction method according to the embodiment of the present invention is applied to a lane line extraction device on an electronic device. The lane line extraction personnel can load and display the lane line on the electronic equipment by operating the electronic equipment. In the method for extracting the lane line in the embodiment of the invention, the base map of the reflection value is obtained according to the laser point cloud data, the lane line is projected on the base map of the reflection value to obtain the base map of the reflection value containing the lane line, and the lane line on the base map of the reflection value is corrected to obtain the base map of the reflection value after correction processing. The corrected reflection value base map can be applied to a high-precision map and the like. The electronic device may be a computer, a notebook, or the like, and the embodiment of the present invention is not limited thereto. Next, a lane line extraction method according to an embodiment of the present invention will be described in detail. For example, see fig. 2.
Fig. 2 is a flowchart of a lane line extraction method according to an embodiment of the present invention. The execution main body of the embodiment is a lane line extraction device, which may be implemented by software, hardware, or a combination of software and hardware, and may be part or all of an electronic device. The embodiment is described by taking the application of the lane line extraction method to the electronic device in fig. 1 as an example, and the embodiment includes:
101. determining a reflection value base map according to laser point cloud data obtained by scanning a road surface, and projecting a lane line on the reflection value base map, wherein the lane line is extracted according to a shot image, and the shot image is an image obtained by shooting the road surface by a shooting device.
In the embodiment of the invention, the shot image and the laser point cloud data are needed in the process of extracting the lane line, the lane line is obtained according to the shot image, and the reflection value base map is obtained according to the laser point cloud data so as to obtain the marked point set. The captured image and the laser point cloud data will be described in detail below.
First, an image is captured.
For roads needing to be marked on a high-precision map, the roads are shot in advance to obtain shot images. For example, the road is photographed at high altitude by an aerial photographing apparatus to obtain a photographed image including the road; for another example, a road is photographed by an onboard camera disposed on a vehicle, and a photographed image including the road is obtained. After the captured image is obtained, the lane line is extracted from the captured image. The captured image contains some non-lane information in addition to the lanes in the road. In the process of extracting the lane line, the extracted lane line is inaccurate due to interference of the non-lane information, and the inaccurate lane line represents the approximate position of the lane line. When the shot image is collected by the aerial shooting device, the shot image contains more global information, so that the continuity of the lane line can be ensured. That is, although the lane lines extracted based on the captured image obtained by the aerial device are not precisely positioned, the continuous lane lines, that is, the lane lines that are not precisely positioned, are not interrupted.
It should be noted that, when the captured image is captured by the aerial device, for example, the aerial device is higher than the ground, so that the actual lane line cannot be captured by the aerial device, the lane line may be extracted according to the traffic flow on the road. For example, the traffic flow on a lane is distributed in a substantially queue, and a lane line can be obtained according to the queue. Generally, the higher the aerial device, the wider the angle of the shot, the more global information is obtained, but the lower the resolution, the worse the accuracy. In practical implementation, the height of the aerial device can be adjusted, so that a compromise is made between the global information content and the accuracy.
Secondly, laser point cloud data.
In the embodiment of the invention, for the road needing to be marked on the high-precision map, the laser point cloud data of the road is obtained by utilizing a laser scanner and the like in advance. The laser point cloud data is three-dimensional laser point cloud data and can be obtained according to a laser measurement principle, and the laser point cloud data comprises three-dimensional coordinates and laser reflection intensity. And after the laser point cloud data is obtained, projecting the laser point cloud data onto a two-dimensional image to obtain a reflection value base map. In the projection process, non-ground points and the like are filtered from the 3D laser point cloud data, and a reflection value base map is obtained.
After the reflection value base map is obtained, the reflection intensity of the point on the ground other than the lane line is different from the reflection intensity of the point on the lane line, so that the lane line can be extracted based on the reflection value base map, and the position of the lane line is accurate. However, since the resolution of the reflection value base map is high, the lane line extracted based on the reflection value base map may be discontinuous, and an interruption occurs.
According to the above, it can be seen that: the lane line extracted based on the captured image is inaccurate in position, but the lane line is continuous; the position of the lane line extracted based on the reflection value base map is accurate, but the lane line is interrupted. After the lane lines extracted from the captured image are projected on the reflection value base map, the reflection value base map will include lane lines with inaccurate but continuous positions and lane lines with accurate but interrupted positions. Therefore, the inaccurate but continuous lane lines can be corrected according to the accurate but interrupted lane lines, so that the inaccurate but continuous lane lines projected on the reflection value base map are corrected to accurate and continuous lane lines.
In addition, since the photographed image obtained by the aerial photographing device has a corresponding relationship with the world coordinate system, and the reflection value base map also has a corresponding relationship with the world coordinate system, the corresponding relationship between the photographed image and the world coordinate system can be established, so that the lane line extracted from the photographed image is projected on the reflection value base map.
102. And carrying out segmentation processing on the reflection value base map to obtain a marking point set, wherein the marking point set comprises at least one marking point, and the at least one marking point is a point on an initial lane line obtained through the laser point cloud data.
In this step, semantic segmentation processing is performed on the reflection value base map to obtain a marker point set of the lane line on the reflection value base map, where the marker point set includes a plurality of marker points. The reflection value base map is a reflection value base map obtained based on laser point cloud data. The semantic segmentation is to classify each pixel in the reflection value base map, that is, to obtain a pixel of what object each pixel in the reflection value base map belongs to. In the actual implementation process, a convolutional neural network mode can be adopted to classify the pixels.
103. And correcting the lane lines projected on the reflection value base map according to the marked point set.
In this step, the lane lines projected on the reflection value base map are corrected according to the marker points in the marker point set, so that the lane lines projected on the reflection value base map and having inaccurate and continuous positions are corrected into the lane lines having accurate and continuous positions.
According to the lane line extraction method provided by the embodiment of the invention, the reflection value base map is obtained according to the laser point cloud data, the lane line is projected on the reflection value base map to obtain the reflection value base map containing the lane line, and the lane line on the reflection value base map is corrected to obtain the corrected reflection value base map. In the process, a lane line is extracted based on a shot image of an aerial shooting device and the like, a mark point is obtained based on the lane line on a reflection value base map, the lane line obtained according to the shot image is projected on the reflection value base map, and then the lane line projected on a reflection value low map is corrected according to the mark point, so that the purpose of obtaining an accurate lane line is achieved.
Next, the relationship between the marker points in the marker point set and the lane lines projected on the reflection value base map will be described in detail.
In a possible implementation manner, before the correcting the lane line projected on the reflection value base map according to the marker point set, the method further includes: determining at least one key point on the lane line; and determining whether the mark point set of the key point exists or not according to the position of any key point in the at least one key point.
For example, after a lane line obtained according to a shot image is projected on a reflection value base map, the lane line and a mark point set exist on the reflection value base map at the same time, and a mark point in the mark point set can be understood as being obtained by supplying the lane line in the reflection value base map projected on a two-dimensional image according to laser point cloud data. Because the shot image and the reflection value base map are images of the same road and both the two images have a corresponding relation with the world coordinate system, a certain corresponding relation exists between the two images, and further a certain corresponding relation exists between the lane line projected on the reflection value base map and the mark point set.
In this embodiment, at least one key point may be discretized according to a lane line obtained by capturing an image, and for each key point in the at least one key point, whether a marker point corresponding to the key point exists in the marker point set may be determined according to a position of the key point on the reflection value base map. For example, on the reflection value base map, the key point is used as the center of a circle, a preset range is determined according to a preset radius, then whether a mark point exists in the preset range is determined, if yes, the actual position of the key point of the lane line obtained according to the shot image is considered as the position of the mark point, the key point of the imprecise lane line is replaced by the mark point, and when all the key points on the imprecise lane line find the mark point, all the mark points are sequentially connected, so that the corrected lane line can be obtained.
In the process of determining the marking point for the key point, the confidence of the marking point needs to be considered. That is, for a specific key point, even if there is a mark point in the preset range, if the confidence of the mark point does not satisfy the threshold, it is determined that there is no mark point corresponding to the key point in the mark point set. In addition, if a plurality of key points exist in the preset range, for example, at least two mark points exist, the at least two mark points are sequenced according to the confidence degree, a mark point queue is obtained, and the first mark point in the mark point queue is used as the mark point of the key point.
Next, a detailed description will be given of how to correct the lane lines projected on the reflection value base map based on the marker point sets in the above-described embodiment.
In a possible implementation manner, when the electronic device corrects the lane line projected on the reflection value base map according to the marker point set, M key points may be determined from the at least one key point, where the M key points are consecutive key points, and a marker point of any one key point in the key points exists in the marker point set, where M is greater than or equal to a first threshold and is an integer; and translating the line segments among the M key points in the lane line to the line segments formed by the M mark points corresponding to the M key points.
For example, a plurality of key points are determined on the lane line projected on the reflection value base map, and the key points divide the lane line into a plurality of line segments. For continuous M key points, if the mark point of any one key point in the M key points exists in the mark point set, sequentially connecting the M mark points corresponding to the M key points on the reflection value base map according to the sequence of the M key points, and translating the line segment between the M key points in the lane line to the line segment formed by the M mark points corresponding to the M key points. Where M is greater than or equal to a first threshold and is an integer, and the first threshold is, for example, 10. That is, when there are corresponding mark points in the mark point set for 10 consecutive key points projected on the lane line on the reflection value base map, the corresponding parts of 10 key points on the inaccurate but interrupted lane line can be replaced by the corresponding parts of 10 mark points on the accurate but interrupted lane line.
In another possible implementation manner, when the electronic device corrects the lane line projected on the reflection value base map according to the marker point set, N key points may be determined from the at least one key point, where the N key points are consecutive key points, and no marker point of any key point of the N key points exists in the marker point set, where N is greater than or equal to a second threshold and is an integer; according to a preset rule, determining a supplementary point corresponding to each key point in the N key points on the reflection value base map to obtain N supplementary points; and replacing line segments among the N key points in the lane line by using a line formed by the N supplementary points.
For example, a plurality of key points are determined on the lane line projected on the reflection value base map, and the key points divide the lane line into a plurality of line segments. For N consecutive key points, if there is no mark point of any key point in the M key points in the set of mark points, it is necessary to determine a point for the key point on the reflection value base map, and the point is referred to as a supplementary point. For example, when a reflection value base map is obtained from laser point cloud data, and a precise but interrupted lane line is obtained from the reflection value base map, the marking points obtained from the lane line are concentrated, and all the marking points are continuous part points, but for the interrupted part, no marking point exists. Therefore, if the N continuous key points correspond to the break portion, the marker points of the N key points do not exist in the set of marker points, and at this time, N supplementary points need to be determined from the reflection value base map, and the line segment between the N key points on the inaccurate continuous lane line needs to be replaced by the line segment connected by the N supplementary points. Where N is an integer greater than or equal to a second threshold, for example, 10. That is to say, when projected on a lane line on a reflection value base map, 10 continuous key points do not have corresponding mark points in a mark point set, supplementary points need to be determined for the 10 key points respectively, and then the determined supplementary points are used to replace the parts corresponding to the 10 key points on the inaccurate but continuous lane line.
In the following, how to determine the supplementary point corresponding to each key point in the N key points on the reflection value base map according to the preset rule in the above embodiment is described in detail, so as to obtain the N supplementary points.
In a feasible implementation manner, the electronic device determines, according to a preset rule, a supplementary point corresponding to each key point of the N key points on the reflection value base map, and when the N supplementary points are obtained, the supplementary point corresponding to each key point of the N key points on the reflection value base map may be determined according to a lane line movement formula, so as to obtain the N supplementary points; the lane line moving formula is as follows:
xkm′＝xkm；
wherein y represents a y coordinate, and for any one first key point (x) on the k-th line segment in the line segments formed by the N key pointskm，ykm) The first key point (x)km，ykm) The first supplementary point of (a) is (x)km′，ykm′)，yirA y coordinate representing a rightmost mark point, wherein the rightmost mark point is a rightmost mark point in all mark points on the left side of the first supplementary point, the rightmost mark point is positioned on the ith line in the line segments sequentially obtained by the N supplementary points, and the y coordinate is used for representing the rightmost mark pointjlThe y coordinate of a leftmost mark point is represented, the leftmost mark point is the leftmost point of all mark points on the right of the first supplementary point, the leftmost mark point is positioned on the jth line segment of the line segments sequentially obtained by the N supplementary points, and y is representedir,kDenotes yirY coordinate of a point normally projected on the k-th line in the line segment formed by the N key points, yjl,kDenotes yjlAnd the y coordinate of a point normally projected on the k-th line in the line segment formed by the N key points. i. j and k are positive integers, and the values of i and j are different.
Next, the lane line extraction method will be described in detail with reference to a specific example. For example, see fig. 3.
Fig. 3 is a schematic diagram of the lane line correction according to the lane line extraction method of the embodiment of the present invention. Referring to fig. 3, a solid line indicates a lane line projected on a reflection value base map, black filled points on the solid line indicate key points, a dotted line indicates a precise but interrupted lane line extracted on the reflection value base map obtained from laser point cloud data, black filled triangles indicate mark points in a set of mark points, and blank portions on the dotted line indicate interruption of the lane line. The chain line indicates a lane line obtained by correcting the lane line corresponding to the break portion projected on the reflection value base map.
Referring to fig. 3, it is assumed that there are 30 key points projected on a lane line on a reflection value base map, where each key point of 1 st to 10 th key points and each key point of 21 st to 30 th key points in the 30 key points have a mark point corresponding thereto in a mark point set, and each key point of 11 th to 20 th key points (only one key point of the 10 th key points is shown in the map, as shown by an unfilled circle in the map), and no mark point corresponding thereto exists in the mark point set.
In the correction process, for each key point in the 1 st to 10 th key points and each key point in the 21 st to 30 th key points, the mark points corresponding to the key points are directly used for replacing the key points, and the effect of translating the line segment between the 1 st to 10 th key points of the lane line to the line segment formed by the mark points corresponding to the 10 key points and translating the line segment between the 21 st to 30 th key points to the line segment formed by the mark points corresponding to the 10 key points is achieved. For the 11 th to 20 th key points, a supplementary point (shown as an unfilled triangle in the figure) needs to be determined for each key point in the 10 key points, and then the line formed by the 11 th to 20 th key points is replaced by the line formed by the 10 supplementary points. In this way, all the key points on the lane line are corrected, and the corrected lane line is a line formed by a dotted line and a dashed line in the figure.
In the following, how to determine the supplementary point corresponding to any one of the 10 key points with respect to the 11 th to 20 th key points in the above embodiment is described in detail.
Illustratively, for the 10 gatesAny one of the key points, assuming that the y coordinate of the key is ykmY 'is the y coordinate of the supplementary point'kmAnd then:
xkm′＝xkm；
referring to fig. 3, a precise but interrupted lane line obtained from the laser point cloud data and a non-precise but continuous lane line extracted from the aerial image and projected on the reflection value base map exist on the reflection value base map. The precise but interrupted lane line comprises three parts: the device comprises a left part, an interruption part and a right part, wherein the interruption part corresponds to a line segment consisting of 11 th to 20 th key points on a back radiation value base map. In the above formula, yirY coordinate value representing the rightmost marked point (i.e., the rightmost marked point on the left part), yjlA y-coordinate value representing the leftmost marked point (i.e., the leftmost marked point of the right portion). y isir,kDenotes yirY coordinate of a point normally projected on the k-th line in a line segment formed by N key points successivelyjl,kDenotes yjlAnd (3) projecting the y coordinate of a point on the k-th line in the line segment formed by sequentially and continuously forming the N key points along the normal direction. For a first part (such as a part consisting of 11 th to 20 th key points in the figure) on the inaccurate but continuous lane line, the first part comprises a plurality of line segments, the line segments comprise a k-th line segment, and for any point on the k-th line segment, the point is marked as (x)km，ykm)，ykmY coordinate, y, representing any one point on the k-th line segmentkm' represents ykmY-coordinate, x, of a supplementary point on a precise but interrupted lane linekmX coordinate, x, representing any point on the k-th line segmentkm' represents xkmIn the x coordinate of the supplementary point on the precise but interrupted lane line, i, j and k are positive integers, and the values of i and j are different.
After the supplementary point is determined, the supplementary point can be continuously used for calculating the supplementary points of other key points, that is, when the mark points are not stored in the N continuous key points to form an interruption part, a supplementary point is determined by adopting the method according to the interruption part, then the supplementary point is used as the rightmost mark point or the leftmost mark point, and the coordinate of the next supplementary point is continuously calculated by adopting the lane line moving formula. Thus, it can be seen that: for a key point, if the mark point set does not have a mark point corresponding to the key point, the supplementary point can be determined according to the coordinates of the key point on the left side and the key point on the right side of the key point.
Since the above formula is for a scene in which the lane line projected on the reflection value base map is a horizontal lane line. For a scene with a lane line vertical or a lane line and a horizontal line at an angle, before correcting the lane line projected on the reflection value base map according to the marked point set, the electronic device rotates the reflection value base map to make the lane line in a horizontal direction, so that for a key point without a marked point, the above lane line moving formula can be used to determine a supplementary point.
In addition, in the above embodiment, if, among the L consecutive key points, some key points have mark points corresponding thereto, some key points do not have mark points corresponding thereto, and the number of the some key points is smaller than a preset threshold, for example, less than 10, the some key points are deleted, so that the lane line formed by the mark points corresponding to the remaining key points, respectively, is used to replace the lane line formed by the key points, thereby implementing the correction of the lane line.
The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of the present invention.
Fig. 4 is a schematic structural diagram of a lane line extraction device according to an embodiment of the present invention, where the lane line extraction device may be implemented by software and/or hardware. As shown in fig. 4, the lane line extraction device 100 includes:
the projection module 11 is configured to determine a reflection value base map according to laser point cloud data obtained by scanning a road surface, and project a lane line on the reflection value base map, where the lane line is extracted according to a captured image, and the captured image is an image obtained by capturing the road surface by a capturing device;
a processing module 12, configured to perform segmentation processing on the reflection value base map to obtain a marker point set, where the marker point set includes at least one marker point, and the at least one marker point is a point on an initial lane line obtained through the laser point cloud data;
and the correcting module 13 is configured to correct the lane line projected on the reflection value base map according to the marker point set.
Fig. 5 is a schematic structural diagram of another lane line extraction device according to an embodiment of the present invention. As shown in fig. 5, the lane line extraction device 100 according to the present embodiment further includes, in addition to the above-described fig. 4:
a determining module 14, configured to determine at least one keypoint on a lane line projected on the reflection value base map before the projecting module 11 corrects the lane line according to the set of mark points; and determining whether the mark point set of the key point exists or not according to the position of any key point in the at least one key point.
In a feasible implementation manner, the correcting module 13 is specifically configured to determine M key points from the at least one key point, where the M key points are consecutive key points, and a mark point of any one key point in the key points exists in the mark point set, where M is greater than or equal to a first threshold and is an integer; and translating the line segments among the M key points in the lane line to the line segments formed by the M mark points corresponding to the M key points.
In a possible implementation manner, the correcting module 13 is specifically configured to determine N key points from the at least one key point, where the N key points are consecutive key points, and no mark point of any key point in the N key points exists in the mark point set, and N is greater than or equal to a second threshold and is an integer; determining a supplementary point corresponding to each key point in the N key points on the reflection value base map to obtain N supplementary points; and replacing line segments among the N key points in the lane line by using a line formed by the N supplementary points.
In a feasible implementation manner, the correction module 13 is configured to determine, on the reflection value base map, a supplementary point corresponding to each key point of the N key points, and when N supplementary points are obtained, specifically, determine, according to a lane line movement formula, a supplementary point corresponding to each key point of the N key points on the reflection value base map, so as to obtain N supplementary points; the lane line moving formula is as follows:
xkm′＝xkm；
wherein y represents a y coordinate, and for any one first key point (x) on the k-th line segment in the line segments formed by the N key pointskm，ykm) The first key point (x)km，ykm) The first supplementary point of (a) is (x)km′，ykm′)，yirA y coordinate representing a rightmost mark point, wherein the rightmost mark point is a rightmost mark point in all mark points on the left side of the first supplementary point, the rightmost mark point is positioned on the ith line in the line segments sequentially obtained by the N supplementary points, and the y coordinate is used for representing the rightmost mark pointjlThe y coordinate of a leftmost mark point is represented, the leftmost mark point is the leftmost point of all mark points on the right of the first supplementary point, the leftmost mark point is positioned on the jth line segment of the line segments sequentially obtained by the N supplementary points, and y is representedir,kDenotes yirY coordinate of a point normally projected on the k-th line in the line segment formed by the N key points, yjl,kDenotes yjlAnd the y coordinate of a point normally projected on the k-th line in the line segment formed by the N key points. i. j and k are positive integers, and the values of i and j are different.
Referring to fig. 5 again, the lane line extraction apparatus 100 further includes:
a rotation module 15, configured to rotate the reflection value base map so that the lane line is in a horizontal direction before the correction module 13 corrects the lane line projected on the reflection value base map according to the set of marker points.
In a feasible implementation manner, the determining module 14 is specifically configured to, if at least two marker points exist in the key point, sort the at least two marker points according to the confidence level to obtain a marker point queue, and use a first marker point in the marker point queue as a marker point of the key point.
The implementation principle and the implementation technology of the lane line extraction device provided by the embodiment of the invention can be referred to the method embodiment, and are not described herein again.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 6, the electronic apparatus 200 includes:
at least one processor 21 and memory 22;
the memory 22 stores computer-executable instructions;
the at least one processor 21 executes computer-executable instructions stored by the memory 22, causing the at least one processor 21 to perform the lane line extraction method as described above.
For a specific implementation process of the processor 21, reference may be made to the above method embodiments, which implement similar principles and technical effects, and this embodiment is not described herein again.
Optionally, the user equipment 20 further comprises a communication section 23. The processor 21, the memory 22, and the communication unit 23 may be connected by a bus 24.
The embodiment of the invention also provides a storage medium, wherein the storage medium stores computer execution instructions, and the computer execution instructions are used for realizing the lane line extraction method when being executed by the processor.
Embodiments of the present invention further provide a computer program product, which, when running on a computer, causes the computer to execute the above lane line extraction method.
In the above embodiments, it should be understood that the described apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the modules is only one logical division, and other divisions may be realized in practice, for example, a plurality of modules may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit. The unit formed by the modules can be realized in a hardware form, and can also be realized in a form of hardware and a software functional unit.
The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable an electronic device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the method according to various embodiments of the present invention.
It should be understood that the processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, etc.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present invention are not limited to only one bus or one type of bus.
The storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in a terminal or server.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A lane line extraction method is characterized by comprising the following steps:
determining a reflection value base map according to laser point cloud data obtained by scanning a road surface, and projecting a lane line on the reflection value base map, wherein the lane line is extracted according to a shot image, and the shot image is an image obtained by shooting the road surface by a shooting device;
dividing the reflection value base map to obtain a mark point set, wherein the mark point set comprises at least one mark point, and the at least one mark point is a point on an initial lane line obtained through the laser point cloud data;
rotating the reflection value base map so that the lane line is in a horizontal direction;
and correcting the lane lines projected on the reflection value base map according to the marked point set.
2. The method of claim 1, wherein before correcting the lane lines projected on the reflection value base map according to the set of marker points, further comprising:
determining at least one key point on the lane line;
and determining whether the mark point set of the key point exists or not according to the position of any key point in the at least one key point.
3. The method of claim 2, wherein said correcting the lane lines projected on the base map of reflection values from the set of marker points comprises:
determining M key points from the at least one key point, wherein the M key points are sequentially continuous key points, mark points of any one key point in the M key points exist in the mark point set, and M is greater than or equal to a first threshold and is an integer;
and translating the line segments among the M key points in the lane line to the line segments formed by the M mark points corresponding to the M key points.
4. The method of claim 2, wherein said correcting the lane lines projected on the base map of reflection values from the set of marker points comprises:
determining N key points from the at least one key point, wherein the N key points are sequentially continuous key points, a mark point of any one key point in the N key points does not exist in the mark point set, and N is an integer and is greater than or equal to a second threshold;
determining a supplementary point corresponding to each key point in the N key points on the reflection value base map to obtain N supplementary points;
and replacing line segments among the N key points in the lane line by using a line formed by the N supplementary points.
5. The method of claim 4, wherein said determining a supplemental point corresponding to each keypoint of said N keypoints on said reflection value base map, resulting in N supplemental points, comprises:
determining a supplementary point corresponding to each key point in the N key points on the reflection value base map according to a lane line moving formula to obtain N supplementary points; the lane line moving formula is as follows:
xkm′＝xkm；
wherein y represents a y coordinate, and for any one first key point (x) on the k-th line segment in the line segments formed by the N key pointskm，ykm) The first key point (x)km，ykm) The first supplementary point of (a) is (x)km′，ykm′)，yirA y coordinate representing a rightmost mark point, wherein the rightmost mark point is a rightmost mark point in all mark points on the left side of the first supplementary point, the rightmost mark point is positioned on the ith line in the line segments sequentially obtained by the N supplementary points, and the y coordinate is used for representing the rightmost mark pointjlThe y coordinate of a leftmost mark point is represented, the leftmost mark point is the leftmost point of all mark points on the right of the first supplementary point, the leftmost mark point is positioned on the jth line segment of the line segments sequentially obtained by the N supplementary points, and y is representedir,kDenotes yirY coordinate of a point normally projected on the k-th line in the line segment formed by the N key points, yjl,kDenotes yjlThe y coordinate of a point on the k-th line in the line segment formed by the N key points is projected along the normal direction; i. j and k are positive integers, and the values of i and j are different.
6. The method according to any one of claims 2 to 5, wherein the determining whether the marked point of any one key point exists in the set of marked points according to the position of the key point comprises:
if the key point has at least two mark points, sequencing the at least two mark points according to the confidence degree to obtain a mark point queue, and taking the first mark point in the mark point queue as the mark point of the key point.
7. A lane line extraction device, comprising:
the projection module is used for determining a reflection value base map according to laser point cloud data obtained by scanning a road surface and projecting a lane line on the reflection value base map, wherein the lane line is extracted according to a shot image, and the shot image is an image obtained by shooting the road surface by a shooting device;
the processing module is used for carrying out segmentation processing on the reflection value base map to obtain a marking point set, wherein the marking point set comprises at least one marking point, and the at least one marking point is a point on an initial lane line obtained through the laser point cloud data;
the rotating module is used for rotating the reflection value base map so as to enable the lane line to be in the horizontal direction;
and the correction module is used for correcting the lane line projected on the reflection value base map according to the marking point set.
8. An electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of the preceding claims 1-6 when executing the program.
9. A storage medium having stored therein instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811290738.0A CN109583313B (en) | 2018-10-31 | 2018-10-31 | Lane line extraction method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811290738.0A CN109583313B (en) | 2018-10-31 | 2018-10-31 | Lane line extraction method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109583313A CN109583313A (en) | 2019-04-05 |
| CN109583313B true CN109583313B (en) | 2020-10-16 |
Family
ID=65921160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811290738.0A Active CN109583313B (en) | 2018-10-31 | 2018-10-31 | Lane line extraction method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109583313B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560558B (en) * | 2019-09-26 | 2023-04-18 | 阿里巴巴集团控股有限公司 | Lane line correction method and device and electronic equipment |
| CN110956100A (en) * | 2019-11-15 | 2020-04-03 | 北京三快在线科技有限公司 | High-precision map generation method and device, electronic equipment and storage medium |
| CN112825196B (en) * | 2019-11-20 | 2023-04-25 | 阿里巴巴集团控股有限公司 | Method and device for determining road sign, storage medium and editing platform |
| CN113256756B (en) * | 2020-02-07 | 2023-03-21 | 阿里巴巴集团控股有限公司 | Map data display method, device, equipment and storage medium |
| CN113223113B (en) * | 2021-04-30 | 2024-04-19 | 阿波罗智联(北京)科技有限公司 | Lane line processing method and device, electronic equipment and cloud control platform |
| CN115683130A (en) * | 2021-07-27 | 2023-02-03 | 北京三快在线科技有限公司 | Method and device for generating target area entrance and exit area of map based on lane line |
| CN113607185B (en) * | 2021-10-08 | 2022-01-04 | 禾多科技（北京）有限公司 | Lane line information display method, lane line information display device, electronic device, and computer-readable medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105528588A (en) * | 2015-12-31 | 2016-04-27 | 百度在线网络技术（北京）有限公司 | Lane line recognition method and device |
| CN105701449A (en) * | 2015-12-31 | 2016-06-22 | 百度在线网络技术（北京）有限公司 | Method and device for detecting lane lines on road surface |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9677898B2 (en) * | 2014-06-17 | 2017-06-13 | Think Ware Corporation | Electronic apparatus and control method thereof |
| CN106570446B (en) * | 2015-10-12 | 2019-02-01 | 腾讯科技（深圳）有限公司 | The method and apparatus of lane line drawing |
-
2018
- 2018-10-31 CN CN201811290738.0A patent/CN109583313B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105528588A (en) * | 2015-12-31 | 2016-04-27 | 百度在线网络技术（北京）有限公司 | Lane line recognition method and device |
| CN105701449A (en) * | 2015-12-31 | 2016-06-22 | 百度在线网络技术（北京）有限公司 | Method and device for detecting lane lines on road surface |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109583313A (en) | 2019-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583313B (en) | Lane line extraction method, device and storage medium | |
| CN110869974B (en) | Point cloud processing method, equipment and storage medium | |
| CN108805934B (en) | External parameter calibration method and device for vehicle-mounted camera | |
| CN112444242B (en) | Pose optimization method and device | |
| JP7138718B2 (en) | Feature detection device, feature detection method, and feature detection program | |
| CN110969592B (en) | Image fusion method, automatic driving control method, device and equipment | |
| CN109741241B (en) | Fisheye image processing method, device, equipment and storage medium | |
| CN112927306B (en) | Calibration method and device of shooting device and terminal equipment | |
| CN111976601B (en) | Automatic parking method, device, equipment and storage medium | |
| US11972507B2 (en) | Orthophoto map generation method based on panoramic map | |
| CN111080784A (en) | Ground three-dimensional reconstruction method and device based on ground image texture | |
| CN112673280A (en) | Road detection method for a motor vehicle equipped with a LIDAR sensor | |
| CN114969221A (en) | Method for updating map and related equipment | |
| CN112991441A (en) | Camera positioning method and device, electronic equipment and storage medium | |
| CN114463372A (en) | Vehicle identification method and device, terminal equipment and computer readable storage medium | |
| CN111982132A (en) | Data processing method, device and storage medium | |
| CN111605481A (en) | Congestion car following system and terminal based on look around | |
| CN110539748A (en) | congestion car following system and terminal based on look around | |
| CN109598199B (en) | Lane line generation method and device | |
| CN115205825B (en) | Traffic sign detection and identification method based on improved YOLOV5 driving video sequence image | |
| KR20200142315A (en) | Method and apparatus of updating road network | |
| CN114037977B (en) | Road vanishing point detection method, device, equipment and storage medium | |
| CN112150621B (en) | Bird's eye view image generation method, system and storage medium based on orthographic projection | |
| JP2012099010A (en) | Image processing apparatus and image processing program | |
| CN111256707A (en) | Congestion car following system and terminal based on look around |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |