Data fusion method based on multiple laser radars

A radar data and multi-laser technology, applied in radio wave measurement systems, instruments, etc., can solve the problem that the accuracy of the effect is not as good as the original data fusion, and achieve the effect of ensuring effective use, ensuring data, and accurate identification

Pending Publication Date: 2020-07-14
沃行科技(南京)有限公司
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The processing algorithm of this post-target data fusion method is relatively simple an

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Data fusion method based on multiple laser radars

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The present invention will be further described below in conjunction with the accompanying drawings.

[0019] The present invention is based on the method for multi-laser radar data fusion, comprises the following steps:

[0020] Step 1: read the original data SC1 of the main laser radar and the original data SC2 of the side laser radar;

[0021] Step 2: Initialize the rotation matrix and translation matrix;

[0022] Step 3: According to the rotation matrix and translation matrix in step 2, transform the point cloud to obtain a new point cloud SC2_;

[0023] Step 4: Find adjacent point pairs to obtain the rearranged main radar point cloud SC1_;

[0024] Step 5: Go to the center to get _SC1_ and _SC2_ respectively;

[0025] Step 6: Decompose the corresponding point pair matrix and SVD to obtain a new rotation matrix and translation matrix;

[0026] Step 7: Repeat steps 3 to 6 until the position difference of the corresponding point pair is less than the set threshold...

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

No PUM Login to view more

Abstract

The invention discloses a data fusion method based on multiple laser radars. The method comprises the following steps of reading original data SC1 of a main laser radar and original data SC2 of a lateral laser radar, initializing a rotation matrix and a translation matrix, transforming a point cloud according to the rotation matrix and the translation matrix in the step 2 to obtain a new point cloud SC2_, searching adjacent point pairs to obtain a rearranged main radar point cloud SC1_, respectively decentralizing to obtain _SC1_ and _SC2_, performing SVD decomposition on the corresponding point pair matrix to obtain a new rotation matrix and a translation matrix, and repeatedly iterating the steps 3 to 6 until the position difference of the corresponding point pair is smaller than a set threshold. According to the data fusion method based on multiple laser radars, data of multiple laser radars can be effectively and fully utilized, what is avoided is that a target object in a common scanning area of the multiple radars is recognized as multiple objects, the surrounding environment of an intelligent driving vehicle is ensured to be accurately recognized, and effective utilization of data of a decision algorithm and a post-fusion algorithm is guaranteed.

Description

Technical field: [0001] The invention relates to a method based on multi-laser radar data fusion, which belongs to the technical field of electric vehicle intelligent driving. Background technique: [0002] Multi-sensor fusion in autonomous driving perception has become a trend in the field of unmanned driving. Multi-sensor Information Fusion (MSIF) is to use computer technology to combine information and data from multiple sensors or sources under certain criteria. It is an information processing process that is automatically analyzed and synthesized to complete the required decision-making and estimation. According to the realization principle, the fusion is divided into pre-original data fusion and target data post-fusion; fusion using the underlying data of the sensor is called pre-original data fusion; using the post-recognition results obtained by various sensors, that is, each sensor independently generates target data, Then the main processor fuses these characteris...

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
no application Login to view more
IPC IPC(8): G01S7/48
CPCG01S7/4802
Inventor 张林灿董钊志张婉蒙宋罡刘树全
Owner 沃行科技(南京)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap