Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Three-dimensional target detection method fusing monocular camera and laser radar

A laser radar, three-dimensional target technology, applied in neural learning methods, computer parts, character and pattern recognition, etc., can solve the problem of reduced recognition effect, achieve good prediction, improve accuracy, and improve the effect of robustness

Pending Publication Date: 2022-03-01
WUHAN UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the laser point cloud is sparse, and when the target is far away, the recognition effect will drop significantly

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
  • Three-dimensional target detection method fusing monocular camera and laser radar
  • Three-dimensional target detection method fusing monocular camera and laser radar
  • Three-dimensional target detection method fusing monocular camera and laser radar

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention provides a three-dimensional target detection method that combines a monocular camera and a laser radar, including three stages of target detection, target tracking and trajectory prediction. In the target detection stage, the laser radar and the camera are first registered, and the laser radar and The spatial position relationship of the camera, and then preprocess the point cloud, use the YOLOv4 target detection algorithm to obtain a two-dimensional outsourcing rectangle on the image, and generate a three-dimensional cone sense corresponding to the two-dimensional outsourcing rectangle according to the projection relationship between the point cloud and the image In the region of interest, finally cluster the point cloud in the 3D cone-shaped region of interest and fit the 3D outsourcing rectangle to realize the detection of the target; in the target tracking stage, the detected target is matched between frames based on the DeepSORT algorithm, and ...

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 relates to a three-dimensional target detection method fusing a monocular camera and a laser radar. The method comprises three stages of target detection, target tracking and trajectory prediction. In the target detection stage, the advantages of the camera and the laser radar are fully combined, and the precision of three-dimensional dynamic target detection is improved; in the target tracking stage, a tracker management model based on a quaternary state machine is provided, and the robustness of a tracking algorithm is effectively improved; in a trajectory prediction stage, a trajectory prediction model based on lane line constraint is innovatively provided, modeling is performed on vehicle motion in a road coordinate system, and the vehicle motion can be better predicted.

Description

technical field [0001] The invention belongs to the technical field of intelligent driving, and in particular relates to a three-dimensional target detection method combining a monocular camera and a laser radar. Background technique [0002] Dynamic object perception system in complex environment is an important part of autonomous driving technology. The perception system needs to detect and track the three-dimensional dynamic target and predict the movement trend of the target according to the historical trajectory, so as to provide sufficient environmental information for the decision-making and planning system. At present, the sensors used in 3D target detection mainly include cameras and lidar. [0003] The camera expresses environmental information by recording light intensity signals, which has the characteristics of low cost and rich texture information. Monocular 3D target detection can be divided into: traditional algorithms based on prior models and algorithms b...

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 Applications(China)
IPC IPC(8): G06V10/80G06V10/762G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/23G06F18/25
Inventor 赵望宇黄远宪周剑张文
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com