A corner feature extraction method based on 3D laser point cloud and its application
A three-dimensional laser, corner feature technology, applied in the application field of intelligent cleaning robots, can solve problems such as poor stability, and achieve the effect of improving stability and accuracy
Active Publication Date: 2022-06-28
SHANGHAI GAOXIAN AUTOMATION TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to solve the above-mentioned deficiencies and provide a corner point feature extraction method based on three-dimensional laser point cloud, which improves the stability and accuracy, and solves the problem of poor stability of the previous laser corner point feature extraction methods in complex environments.
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
[0027] Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, only used to explain the embodiments of the present application, and should not be construed as limitations on the embodiments of the present application.
[0028] Laser point cloud intensity: When the laser point cloud is irradiated to different material surfaces, there will be different intensity values. For example, the intensity of the laser point cloud on the lane line is much larger than that of the laser point on the road.
[0029] ICP (Iterative Closest Point): A point cloud-to-point cloud optimization algorithm that optimizes the direct coordinate transformation of point clouds at different times....
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 the technical field of unmanned robots, in particular to a corner point feature extraction method based on a three-dimensional laser point cloud and its application in an intelligent cleaning robot. The method includes the following steps: 1) Obtaining a three-dimensional laser point cloud Data; 2) along a single laser line in the three-dimensional laser point cloud, for each laser point, select two laser points before and after the calculation of the angle Θ and spatial continuity C at the point; 3) filter out the angle Θ less than the angle threshold or spatial If the continuity C is less than the continuity threshold, the remaining points are used as candidate corner points; 4) Finally, based on the sliding window, all angle peak points are extracted in the candidate corner points, which are the final corner points; the extraction method of the present invention Based on the angle change and continuity of a single laser line in the 3D laser point cloud, a stable laser point cloud corner point extraction is realized, which solves the problem of poor stability of the previous laser corner point feature extraction methods in complex environments, and improves the performance of the laser point cloud. stability and precision.
Description
[Technical field] [0001] The invention relates to the technical field of unmanned robots, in particular to a corner feature extraction method based on a three-dimensional laser point cloud and its application in an intelligent cleaning robot. [Background technique] [0002] With the development of robotics and laser sensors, the mapping and positioning technology based on laser sensors has been more and more widely used. Especially in the fields of security, cleaning, express delivery, etc., unmanned robots with autonomous mapping and positioning have brought great convenience to people's lives. However, in some complex scenes, the mapping and localization technology based on laser point cloud may not be able to extract feature points normally. [0003] At present, the ICP (Iterative Closest Point) algorithm based on laser 3D point cloud matching uses all laser points or points with higher flatness to perform point-to-point, point-to-line or point-to-surface matching. Amon...
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): G06V10/44G06V10/74G06K9/62
CPCG06V10/44G06F18/22
Inventor 杜鹏飞宋乐程昊天
Owner SHANGHAI GAOXIAN AUTOMATION TECH