Multi-lidar fusion recognition method for intelligent vehicles based on target features

A technology of intelligent vehicles and target features, which is applied in the field of intelligent vehicle environment perception, can solve the problems of insufficient target category recognition ability, and achieve the effects of enhancing safety, improving accuracy and reliability, and expanding perception capabilities

Active Publication Date: 2019-03-08
CHONGQING UNIV OF POSTS & TELECOMM
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The present invention aims at the problem that the traditional smart vehicle multi-lidar data fusion method: the grid map fusion method has insufficient ability to identify target categories

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
  • Multi-lidar fusion recognition method for intelligent vehicles based on target features
  • Multi-lidar fusion recognition method for intelligent vehicles based on target features
  • Multi-lidar fusion recognition method for intelligent vehicles based on target features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention proposes a multi-laser radar fusion recognition system and method for intelligent vehicles based on target features. The system and method use target features to fuse multiple laser radars, improve the system's ability to perceive targets after fusion, and enhance intelligent vehicles in unmanned vehicles. Safety in driving and assisted driving.

[0035] The specific implementation manners of the present invention will be described below in conjunction with the accompanying drawings and specific examples.

[0036] Such as figure 1 Shown is the overall framework of the multi-lidar data fusion system for intelligent vehicles based on target characteristics. The system consists of single-line laser radar, four-line laser radar, satellite positioning system and computer. The system includes five processes of geometric feature extraction, target fusion, target tracking, target correction and target rasterization.

[0037] Such as figure 2 Shown 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

No PUM Login to view more

Abstract

The invention claims protection of a multi-laser radar fusion recognition method for intelligent vehicles based on target characteristics, which relates to the field of environment perception of intelligent vehicles. The steps involved are as follows: 1. Preprocess the collected data, extract the geometric features of the target, and determine the target category; 2. Calculate the geometric similarity of the target, and perform target matching according to the similarity; 3. Use the method based on distance weighted fusion to identify the target Geometric features are fused; 4. Use the multi-feature-based target tracking method to track the target to obtain the relative motion characteristics of the target; 5. Use the vehicle motion characteristics collected by the satellite positioning system to obtain the absolute motion characteristics of the target; 6. According to the absolute motion of the target The feature and target feature model corrects the target category; 7. Rasterizes the target feature and performs grid representation. The invention utilizes target features to fuse multiple laser radars, improves the system's ability to identify targets, and enhances the safety of vehicles during driving.

Description

technical field [0001] The invention belongs to the technical field of intelligent vehicle environment perception, relates to multi-sensor fusion technology, and mainly relates to a multi-laser radar fusion recognition method for intelligent vehicles based on target characteristics. Background technique [0002] An intelligent vehicle is a vehicle that has the functions of environment perception, planning decision-making, operation control, etc., and can realize unmanned driving. It can rely on its own various sensors to collect road and obstacle information around the vehicle in real time to realize unmanned driving and automatic obstacle avoidance, thereby reducing traffic accidents and improving traffic safety. [0003] Among them, environmental perception technology is the difficulty and key point in intelligent vehicles. [0004] In traditional environmental perception, a single sensor has certain limitations and cannot provide sufficient environmental information for ...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G01S7/48
CPCG01S7/4802G06T2207/30252G06T2207/30261G06T2207/10044G06V40/10G06V20/56G06V20/58G06V20/584G06V10/20G06V10/267G06V10/40G06V10/751G06V2201/08G06F18/23G06F18/253
Inventor 李银国田甄岑明邓永生冯辉宗赵文旋
Owner CHONGQING UNIV OF POSTS & TELECOMM
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