Rapid calibration method for multi-laser radar point cloud deduplication of automatic driving system
A technology of automatic driving and calibration method, applied in the field of radar, it can solve the problems of position deviation, a large number of repeated point clouds, etc., and achieve the effect of increasing the density
Pending Publication Date: 2022-08-02
天津优控智行科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In the current calibration methods, most of the methods are realized based on coordinate system transformation. Through the coordinate system relationship between different sensors, the point cloud is processed according to the transformation relationship between coordinate systems. The disadvantage of this operation is that point The cloud data is simply superimposed, there is a certain position deviation and a large number of repeated point clouds
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
[0032] It should be noted that the embodiments of the present invention and the features of the embodiments may be combined with each other under the condition of no conflict.
[0033] The present invention will be described in detail below with reference to the embodiments.
[0034] In the current calibration methods, most of the methods are based on coordinate system transformation. Through the coordinate system relationship between different sensors, the point cloud is processed according to the transformation relationship between coordinate systems. The disadvantage of this operation is that the point cloud is The cloud data is simply superimposed, and there is a certain positional deviation and a large number of repeated point clouds.
[0035] This patent performs external parameter calibration between different lidars based on the point cloud feature matching method. The specific process is as follows:
[0036] Multi-lidar data analysis;
[0037] Roughly calculate the ...
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 provides an automatic driving system multi-laser radar point cloud deduplication rapid calibration method comprising the following steps: S1, aiming at data analysis of a parent radar and a child radar, generating point cloud data, the parent radar being a laser radar which finally releases fusion point cloud data, the child radar being a laser radar which finally releases fusion point cloud data, and the parent radar being a laser radar which finally releases fusion point cloud data; the sub-radars refer to laser radars which need to convert point cloud data; s2, roughly calculating the poses of the parent radar and the child radar; and S3, calculating a registration relation between the parent radar and the child radar. The rapid calibration method for multi-laser radar point cloud deduplication of the automatic driving system has the beneficial effects that through point cloud data analysis, point cloud data feature extraction registration and fine registration of the ICP algorithm, time-space synchronization is performed on different point cloud data, repeated point removal is performed through an adjacent threshold method, and the accuracy of the deduplication of the multi-laser radar point cloud is improved. The external reference fine calibration of a plurality of laser radars is realized, different laser radar data are expressed at the same visual angle, and the density of point cloud data and the visual field of the radars are greatly improved.
Description
technical field [0001] The invention belongs to the technical field of radar, and in particular relates to a rapid calibration method for deduplication of multiple laser radar point clouds of an automatic driving system. Background technique [0002] In the field of unmanned driving technology, environmental perception plays a very important role as an interaction module for unmanned vehicles in the surrounding environment. In the current technical field, the commonly used sensor types are generally lidar and monocular cameras. Because lidar is not affected by light, it can work around the clock, and its ranging method can provide accurate obstacle position information for unmanned vehicles, and provide a reliable basis for the subsequent decision-making and control of unmanned vehicles. [0003] At present, due to the high price of radars with high wiring harnesses and the low density of radar point clouds with low wiring harnesses, in order to reduce the equipment price of...
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 Applications(China)
IPC IPC(8): G01S7/497G06K9/62
CPCG01S7/497G06F18/23213G06F18/22
Inventor 常飞翔吴晨晓肖永国廖明
Owner 天津优控智行科技有限公司