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

Novel binocular vision multi-target tracking method and system

A multi-target tracking and binocular vision technology, which is applied in the field of new binocular vision multi-target tracking methods and systems to achieve the effects of improving tracking accuracy and speed, and improving the level of automation and intelligence.

Inactive Publication Date: 2020-09-01
JIANGSU XINTONGDA ELECTRONICS SCI & TECHCO
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Due to the need to realize real-time and accurate tracking of various objects under different environmental conditions, there is currently no sensor system that can fully provide all the information required for target tracking.

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
  • Novel binocular vision multi-target tracking method and system
  • Novel binocular vision multi-target tracking method and system
  • Novel binocular vision multi-target tracking method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] figure 1 It is a flow chart of the novel binocular vision multi-target tracking method involved in the present invention.

[0071] Such as figure 1 As shown, this embodiment 1 provides a new binocular vision multi-target tracking method, including: acquiring images through binocular vision; acquiring moving targets according to images; constructing vehicle motion space and vehicle motion models; and through improved joint probability The data association (joint probabilistic data association, JPDA) tracks the moving target according to the vehicle motion space and the vehicle motion model, realizes the multi-target tracking of the intelligent vehicle, greatly improves the automation and intelligence level of the driving system, and improves the tracking accuracy and speed , and there will be no obvious offset when tracking vehicles, and no missing tracking of pedestrians.

[0072] figure 2 It is a specific flow chart of the novel binocular vision multi-target tracki...

Embodiment 2

[0120] image 3 It is a functional block diagram of the novel binocular vision multi-target tracking system involved in the present invention.

[0121] Such as image 3 As shown, on the basis of Embodiment 1, this Embodiment 2 also provides a novel binocular vision multi-target tracking system, including: an acquisition module, which acquires images through binocular vision; a moving target acquisition module, which acquires moving targets according to the images ; a building block for constructing a vehicle motion space and a vehicle motion model; and a tracking module for tracking a moving target according to the vehicle motion space and the vehicle motion model through an improved joint probability data association.

[0122] In this embodiment, the acquisition module acquires images through binocular vision, the moving target acquisition module acquires moving targets according to the images, the construction module constructs the vehicle motion space and the vehicle motio...

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 belongs to the technical field of automatic driving multi-target tracking, and particularly relates to a novel binocular vision multi-target tracking method and system, and the method comprises the steps: obtaining an image through binocular vision; acquiring a moving target according to the image; constructing a vehicle motion space and a vehicle motion model; and tracking the moving target according to the vehicle motion space and the vehicle motion model through improved joint probability data association. According to the invention, multi-target tracking of the intelligent vehicle is realized, the automation and intelligence level of a driving system is greatly improved, the tracking precision and speed are improved, obvious deviation is not generated during vehicle tracking, and pedestrian tracking is not missed.

Description

technical field [0001] The invention belongs to the technical field of multi-target tracking for automatic driving, and in particular relates to a novel binocular vision multi-target tracking method and system. Background technique [0002] Achieving reliable perception of the surrounding environment under various uncertain conditions is a fundamental task in almost any assisted or autonomous system application, especially with the continuous rise of autonomous driving research, academia and major technology companies are actively developing advanced driving auxiliary system. The core technologies of driver assistance systems include functions such as adaptive cruise, collision avoidance, lane change assistance, traffic sign recognition, and parking assistance. mistake. Among various technologies, moving object tracking is a key task of the driver assistance system. When the vehicle can detect dynamic objects in its environment and predict its future behavior, it can great...

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): G06T7/246G01C21/26
CPCG06T7/251G01C21/26G06T2207/30248
Inventor 胡广地李孝哲黎康杰顾丽军
Owner JIANGSU XINTONGDA ELECTRONICS SCI & TECHCO
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