Temporal Attention Control System for Multiple Objects Tracking

摘要：

An important ability for mobile robots is to process multiple tasks in complex environments. Since the sensor resources on a robot are limited, it is necessary to distribute the sensors attention to different tasks along the time scale. This paper proposes a temporal attention control method which aims at detecting multiple objects and estimating their poses with a single actuated camera. The proposed method is based on three criteria which are partially inspired by human behavior: (i) minimization of the overall object poses perception uncertainty and minimization of the variance of the perception uncertainty of different objects; (ii) minimization of the camera movements for completing the tasks; (iii) maximization of the number of objects in the cameras field of view.The proposed approach use Kalman filters to estimate object poses and to determine the perception uncertainty. The method was evaluated with both simulation and experiment on actual robot. The results show that the proposed approach is able to switch the camera’s attention according to the objects poses and movements efficiently with a low frequency of the camera movements.

关键词： Attention control Kalman filter multiple objects tracking

作者: Xuelian Zang Draˇzen Brˇsˇc′ Wei Wang Kolja Kühnlenz

作者单位: Maximilians Universit¨at München, 80802 Germany Advanced Telecommunications Research Institute International (ATR), Kyoto, Japan Institute of Automatic Control Engineering,Technische Universit¨at München, 80333 Germany Institute of Automatic Control Engineering,Technische Universit¨at München, 80333 Germany Institute

会议类型: 国际会议

会议名称: The 31st Chinese Control Conference(第三十一届中国控制会议)

会议地点: 合肥

会议语种:英文

页码: 4836-4841

在线出版日期: 2012-07-01（万方平台首次上网日期，不代表论文的发表时间）