Target object tracking of humanoid robot based on stereo vision. | [Mehran University Research Journal of Engineering and Technology • 2009]

Author(s):

1. Altaf Hussain Rajpar: Department of Mechanical Engineering, Quaid-e-Awam University of Engineering, Science & Technology, Shaheed Benazir Bhuttoabad, Nawabshah, Pakistan

2. Abdul Fattah Chandio: Department of Electronic Engineering, Quaid-e-Awam University of Engineering, Science & Technology, Shaheed Benazir Bhuttoabad Nawabshah, Pakistan

3. Muhammad Akram Shaikh: Department of Computer Systems & Software Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan

Abstract:

Location and tracking of target object is a crucial issue in the field of autonomous and intelligent robots. Most vision based tracking systems use single visual feature and are failed in an unstructured, complex environment. In this paper visual features are analyzed for stereo vision based head of humanoid robot. Identical visual features such as stereo geometry, color, disparity and shape parameters are integrated together to realize effective tracking of target object. Active search stereo vision head is designed. Two computers are embedded in to the system as to realize fast and robust tracking of target object. Computers are linked with memo link communication card to ensure the tracking of the moving target object in a robust way. High robustness and real time tracking performance of the system is proved through the experimental work.

Page(s): 393-404

DOI: DOI not available

Published: Journal: Mehran University Research Journal of Engineering and Technology, Volume: 28, Issue: 3, Year: 2009

Keywords:

Keywords are not available for this article.

References:

References are not available for this document.

Citations

Citations are not available for this document.

Citations

Downloads

Views