Slow Feature Analysis for Multi-Camera Activity Understanding
Multi-camera activity analysis is a key point in video surveillance of many wide-area scenes,such as airports,underground stations,shopping mall and road junctions.On the basis of previous work,this paper presents a new feature learning method based on Slow Feature Analysis (SFA) to understand activities observed across the network of cameras.The main contribution of this paper can be summarized as follows: (1) It is the first time that SFA-based learning method is introduced to multi-camera activity understanding; (2) It presents an evaluation to examine the effectiveness of SFAbased method to facilitate the learning of inter-camera activity pattern dependencies; and (3) It estimates the sensitivity of learning inter-camera time delayed dependency given different training size,which is a critical factor for accurate dependency learning and has not been largely studied by existing work before.Experiments are carried out on a dataset obtained in a trident roadway.The results demonstrate that the SFA-based method outperforms the sate of the art.
video surveillance slow feature analysis multicamera activity analysis
Lei Zhang Xiaoqiang Lu Yuan Yuan
Center for OPTical IMagery Analysis and Learning(OPTIMAL),State Key Laboratory of Transient Optics a Center for OPTical IMagery Analysis and Learning(OPTIMAL),State Key Laboratory of Transient Optics a
国际会议
西安
英文
241-244
2013-09-14（万方平台首次上网日期，不代表论文的发表时间）