A fine 3D feature extraction method for ruts based on continuous laser point cloud of road surface
A three-dimensional feature, laser point cloud technology, used in image analysis, image enhancement, instrumentation, etc., can solve the problem of unable to achieve refined rut extraction, and achieve the effect of overcoming slow processing speed, overcoming information loss, and fast calculation speed
Active Publication Date: 2022-04-22
SHANDONG UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Aiming at the problem that the existing methods cannot achieve the fine extraction of the whole rut, the present invention provides a fine three-dimensional feature extraction method for ruts based on the continuous laser point cloud of the road surface
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
[0098] The specific embodiment of the present invention will be further described below in conjunction with accompanying drawing and specific embodiment:
[0099] combine Figure 1 to Figure 13 , a method for extracting fine 3D features of ruts based on continuous laser point clouds of road surfaces, including the following steps:
[0100] Step 1: Sampling and extracting a certain amount of road surface point cloud data, using multiple linear regression to roughly fit the road surface plane, and using the road surface plane as a benchmark, normalize the elevation of the road surface point cloud data.
[0101] The z coordinate of the point cloud data is used as the dependent variable, and the x and y coordinates are two independent variables to establish a multiple linear regression model of the road surface:
[0102] z=b 0 +b 1 x+b 2 y+e;
[0103] Solve using the matrix method:
[0104]
[0105]
[0106] Then the general formula of rough pavement plane equation is:...
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 invention discloses a fine three-dimensional feature extraction method for ruts based on continuous laser point clouds on the road surface. First, the point cloud data is used to fit the road surface plane, and the road surface point cloud data is preprocessed to further generate road surface elevation feature images, slope feature images and slope The rut characteristics in each feature image are comprehensively analyzed, and the edge line of the side wall of the rut groove and the center line of the groove bottom are extracted. Then, based on the cross-sectional laser point cloud scanning line, continuous sampling at equal intervals accurately extracts the rut plane contour position points and the cross-sectional contour line; with the precise rut contour points extracted based on point cloud as constraints, the continuous rut contour line based on feature image extraction is corrected information. Finally, the fine three-dimensional characteristics of the ruts are expressed by the edge lines of the side walls of the ruts, the centerlines of the bottom of the grooves and the contour lines of the cross section. The invention can acquire continuous and accurate rut position information, and overcomes the problem of lack of information at non-sections when extracting ruts based on point clouds.
Description
technical field [0001] The invention relates to the technical field of road surface defect detection by a mobile measurement system, in particular to a fine three-dimensional feature extraction method for ruts based on continuous laser point clouds on the road surface. Background technique [0002] Due to the natural environment, especially the influence of high temperature, asphalt is easy to soften, and under the action of traffic load, the asphalt pavement is prone to plastic flow or further compaction, the wheel track belt gradually deforms and sinks, and the two sides bulge to form ruts. Rutting reduces the flatness of the road surface, affecting driving comfort and safety; at the same time, rutting weakens the overall strength of the road surface, which will further induce other road surface diseases. Therefore, the monitoring and prevention of pavement rutting disease is very important. [0003] At present, the measurement and extraction of road surface diseases at h...
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): G06T7/00G06T5/00G06T5/20G06T7/13G06T7/181G06T7/187G06V10/762G06K9/62
CPCG06T7/0004G06T5/20G06T7/13G06T7/187G06T7/181G06T2207/10028G06T2207/20032G06T2207/30132G06F18/23G06T5/70
Inventor 刘如飞柴永宁朱健王旻烨马新江杨雷
Owner SHANDONG UNIV OF SCI & TECH