The visual tracking system using a stereo vision robot

Abstract

Purpose – The purpose of this paper is to use vision stereo to simultaneously acquire image pairs under a normal environment. Then the methods of moving edges detection and moving target shifting are applied to reduce noise error in order to position a target efficiently. The target is then double confirmed via image merge and alignment. After positioning, the visual difference between the target and the image created by the stereo vision system is measured for alignment. Finally, the image depth of the target is calculated followed by real-time target tracking. Design/methodology/approach – This study mainly applies Sobel image principle. In addition, moving edges detection and moving target shifting are also used to work with system multi-threading for improving image identification efficiency. Findings – The results of the experiment suggest that real-time image tracking and positioning under a pre-set environment can be effectively improved. On the other hand, tracking and positioning are slightly affected under a normal environment. Errors of distance measurements occur because there is more noise existing. Research limitations/implications – This study mainly determines the movements and positioning of an object or a target via image. However, the stability of moving edges detection executed by the stereo vision system can be affected if the light sources in an environment are too strong or extreme. Practical implications – So far the method of tracking and positioning a moving object has been applied to surveillance systems or the application which requires measuring and positioning under a normal environment. The method proposed by this study can also be used to construct a 3D environment. Originality/value – The method proposed by this study can also be used to construct a 3D environment or tracking moving object to measure the distance.

Cite this paper

@article{yeh2014visual,
  title = {{The visual tracking system using a stereo vision robot}},
  author = {Yeh, Long-Jyi and Lee, Tsung Han and Hsu, Kuei-Shu},
  journal = {Engineering Computations},
  volume = {31},
  number = {8},
  pages = {1790--1799},
  year = {2014},
  doi = {10.1108/ec-12-2012-0308}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.

Related papers