A Method to Recognize ecognize 3D Shapes of Moving Targets based on Integration of Inclined 2D Range Scans
Recently Recently, laser laser-based people people-tracking systems ha have ve received increasing attention for their ability to localize human subjects precise precisely ly in crow crowded situations. However ed However, in a real environment, there exist many kinds of moving objects other than people people, and previous methods have focused only on human humans. To . design a more sophisticated system system, it is necessary , to distinguish humans from observed objects and recognize their individual condition—for example, the kind and amount of belongings they are carrying. However, in previous methods using 2D laser range finders (LRFs), it proved difficult to recognize the type of target since all sensors obs observe a common erve horizontal plane and only the 2D contours of their targets. In this study study, to recognize , the type of target target, we , observe the 3D shapes of objects moving in their environment by installing LRFs with an angle of inclination inclination. So far, in the area of 3D . modeling modeling, LRFs have been used to construct 3D models of static , objects by moving the sensor and registering multiple views. In contrast, our method observes moving obje objects by using cts a static LRF network in the environment. Experimental results are shown to confirm the effectiveness of the proposed method.
Tetsushi Ikeda Yoshihiro Chigodo Takahiro Miyashita Fumio Kishino Norihiro Hagita
ATR ATR-IRC Laboratories,Kyoto 619 619-0288,Japan Department of Multimedia Engineering Engineering,Graduate School of Information Scien Science and Te Department of Human System Interaction,Graduate School of Science and Technology,Kwansei Gakuin Univ
国际会议
2011 IEEE International Conference on Robotics and Automation(2011年IEEE世界机器人与自动化大会 ICRA 2011)
上海
英文
3575-3580
2011-05-09（万方平台首次上网日期，不代表论文的发表时间）