Interactive automatic extraction method of road boundary line based on laser point cloud
A laser point cloud and automatic extraction technology, which is applied in character and pattern recognition, image analysis, image enhancement, etc., can solve the problems of low fitting accuracy and high labor cost between the road boundary and the actual road boundary line, and achieve simplification and complex calculation Speed, convenient and quick modification, and efficient combination
Active Publication Date: 2020-12-29
WUHAN ZHONGHAITING DATA TECH CO LTD
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The method of purely manual manual collection has higher plane accuracy than point cloud, but the labor cost is higher
The current fully automatic extraction method, the accuracy of the extracted road boundary and the actual road boundary line is not high, suitable for rough segmentation of the road surface, not suitable for direct use of road boundary elements in high-precision maps
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0046] Such as Figures 1 to 5 As shown, a method for interactive automatic extraction of road boundary lines based on laser point cloud, which includes the following steps:
[0047] S1. On the laser point cloud operation platform, manually specify the starting point, and select manual guided boundary line collection or trajectory guided boundary line collection; when collecting trajectory guided boundary lines, the source data needs to be accompanied by trajectory data matching the point cloud as a guide point set ( image 3 ); when collecting manually guided borderlines, it is necessary to input a guide point along the extension direction of the borderline ( Figure 4 );
[0048] S2. Find the guide point closest to the starting point, obtain its heading, move forward along the heading from the starting point, and calculate the left guide line and right guide line respectively from the vertical heading to the left and right, and guide the left guide line and the right side ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention relates to a method for interactive automatic extraction of road boundary lines based on laser point cloud, which comprises the following steps: S1, on the laser point cloud operation platform, obtain a manually designated starting point, and select manual guide boundary line collection or track guide boundary line Acquisition; when collecting for the trajectory guidance boundary line, the source data needs to be accompanied by the trajectory data matched with the point cloud as a guide point set; when collecting for the manual guidance boundary line, it is necessary to input a guide point along the extension direction of the boundary line; S2, search Get the heading of the guidance point closest to the starting point, move forward along the heading from the starting point, and calculate the left and right guiding lines respectively from the vertical heading to the left and right, and connect the left and right guiding lines into A polygon, using the polygon to segment the point cloud; S3, grid the point cloud according to the result of step S2, and obtain point cloud boundary points based on PCL boundary calculation; S4, use the RANSAC method to fit the point cloud boundary points based on PCL.
Description
technical field [0001] The invention relates to the field of high-precision electronic maps, in particular to an interactive automatic extraction method for road boundary lines based on laser point clouds. Background technique [0002] In recent years, autonomous driving technology has developed rapidly. As one of the necessary sensors for autonomous vehicles, high-precision electronic maps provide high-precision lane-level road information for them. Road boundary line is one of the important contents of high-precision map road information. At present, the collection of high-precision map data mainly comes from laser point cloud. Laser point cloud is a collection of massive points that use high-precision laser scanning technology to obtain target spatial distribution and surface characteristics. [0003] There are not many existing researches on road boundary line extraction based on laser point cloud, including purely manual collection, converting point cloud into depth i...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06T7/12
CPCG06T7/12G06T2207/10028G06V20/588
Inventor 惠念
Owner WUHAN ZHONGHAITING DATA TECH CO LTD