A target tracking and location robot system based on omnistereo vision. Issue 6 (16th October 2017)

• Record Type: Journal Article
• Authors: Cai, Chengtao; Fan, Bing; Weng, Xiangyu; Zhu, Qidan; Su, Li
• Is Part Of: Industrial robot. Volume 44:Issue 6(2017)
• Page Start: 741
• Page End: 753
• Publication Date: 2017-10-16
• Subjects: Sensors -- Robot vision -- Omnistereo vision robot system -- Stereo rectification -- Target tracking and location; Robots, Industrial -- Periodicals; Machinery in the workplace -- Periodicals; 629.892
• DOI: 10.1108/IR-03-2017-0042
• Languages: English
• ISSNs: 0143-991X

Abstract

Abstract : Purpose: Because of their large field of view, omnistereo vision systems have been widely used as primary vision sensors in autonomous mobile robot tasks. The purpose of this article is to achieve real-time and accurate tracking by the omnidirectional vision robot system. Design/methodology/approach: The authors provide in this study the key techniques required to obtain an accurate omnistereo target tracking and location robot system, including stereo rectification and target tracking in complex environment. A simple rectification model is proposed, and a local image processing method is used to reduce the computation time in the localization process. A target tracking method is improved to make it suitable for omnidirectional vision system. Using the proposed methods and some existing methods, an omnistereo target tracking and location system is established. Findings: The experiments are conducted with all the necessary stages involved in obtaining a high-performance omnistereo vision system. The proposed correction algorithm can process the image in real time. The experimental results of the improved tracking algorithm are better than the original algorithm. The statistical analysis of the experimental results demonstrates the effectiveness of the system. Originality/value: A simple rectification model is proposed, and a local image processing method is used to reduce the computation time in the localization process. A target tracking method is improved to make it suitable for omnidirectional vision system. Using the proposed methods and some existing methods, an omnistereo target tracking and location system is established.