Title :
Design of a real-time tracking robot based on simplified binocular positioning model
Author :
Kang, Yu ; Liu, Bo-Wen ; Huang, Kun ; Sheng, Meng ; Liu, Ye
Author_Institution :
School of Information and Electronics, Beijing Institute of Technology, 100081, China
Abstract :
A real-time-tracking robot based on binocular positioning is proposed in this essay. This system synthetically evaluates both color and morphological property of the target, realizing fast positioning with a simplified binocular positioning model. With the use of Kalman filter to predict the movement of the target, the system promptly adjusts the direction of the PTZ which carries the cameras, making it possible for the real time tracking of the target. Besides, the essay introduces an edge detection algorithm based on brightness equalization to eliminate possible false boundary lines caused by shadows or illumination. Finally, experiment results demonstrate the realtime performance and accuracy of the system.
Keywords :
Kalman filter; binocular vision; brightness-equalization; wheel-type robot;
Conference_Titel :
Automatic Control and Artificial Intelligence (ACAI 2012), International Conference on
Conference_Location :
Xiamen
Electronic_ISBN :
978-1-84919-537-9
DOI :
10.1049/cp.2012.1101