Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Binocular vision based dynamic object movement track identifying method

A technology of object movement and binocular vision, which is applied in the field of video tracking, can solve the problems of difficult detection and tracking, inaccurate motion trajectory recognition, etc., and achieve good detection and tracking effects and high detection and tracking success rates

Inactive Publication Date: 2018-04-13
WUHAN UNIV OF SCI & TECH
View PDF7 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these methods improve the accuracy of detection, it is difficult to detect and track objects with fast moving speed, small size or unobvious two-dimensional shape features, and the identification of motion trajectory is not accurate.

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
  • Binocular vision based dynamic object movement track identifying method
  • Binocular vision based dynamic object movement track identifying method
  • Binocular vision based dynamic object movement track identifying method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described in detail below in conjunction with specific embodiments.

[0034] A method for recognizing the motion track of a dynamic object based on binocular vision. The binocular vision system on which the method is based includes two cameras installed horizontally in parallel and a computer connected to the cameras. The dynamic object in this embodiment is a shuttlecock. The method includes the following steps :

[0035] A) Two cameras simultaneously collect the image data of the shuttlecock and send it to the computer;

[0036] B) Use the background difference method to process the image data collected in step A), the current frame and the previous frame of the badminton image data collected by the camera are respectively F k and B, the difference between the current frame and the previous frame is obtained to obtain the frame difference D k :

[0037] D. k =F k -B

[0038] Binarize the difference image, set the binarizatio...

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 field of video tracking and discloses a binocular vision based dynamic object movement track identifying method. According to the invention, a binocular vision system includes two cameras mounted horizontally and in parallel and a computer connected to the cameras. The method includes steps of collecting image data of a dynamic object and transmitting the image data to the computer; using a background differencing method for processing the image data so as to acquire outline in each frame of the image data; acquiring two-dimensional coordinates of the dynamic objectthrough identification performed according to characteristics of the dynamic object; acquiring three-dimensional coordinates of the dynamic object through binocular vision matching calculation and a trigonometric survey principle; compiling movement track capturing software for acquiring the movement track of the object. Two-dimensional characteristic identification is performed on objects havinghigh movement speed, small boundary dimensions and unconspicuous two-dimensional shape characteristics by adopting an outline filtering algorithm and three-dimensional coordinate calculation is performed by utilizing results of binocular vision matching, so that movement track of the dynamic object is obtained and the detection and tracking efficiency is high.

Description

technical field [0001] The invention relates to the field of video tracking, in particular to a binocular vision-based dynamic object motion trajectory recognition method. Background technique [0002] Video tracking technology, after nearly 50 years of in-depth research and development, has a wide range of applications and development prospects in robotics, military guidance, visual navigation, security monitoring, intelligent transportation, medical diagnosis, and meteorological analysis. Civilian aspects have important research value and application prospects. Among them, sports robots are a hot topic in robot research. This type of robot generally has the characteristics of high intelligence, high mobility, and high responsiveness. Its research can promote the development of robot motion capabilities and has broad application prospects and markets. value. Moving object detection is a hotspot in the field of computer vision, and it has a wide range of applications in th...

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): G06T7/292G06T7/246G06T5/20
CPCG06T5/20G06T2207/10016G06T2207/20036G06T2207/30241G06T7/246G06T7/292
Inventor 孙伟孔建益
Owner WUHAN UNIV OF SCI & TECH
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
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