Experiments and analysis on observation vector generation and channel number selection in motion detection algorithm based on Independent Component Analysis

被引：0
作者：
Zhang, Chao [1 ]
Wu, Xiao-Pei [1 ]
Lü, Zhao [1 ]
机构：
[1] Key laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei
来源：
Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology | 2015年 / 37卷 / 01期
关键词：
Channel number selection; Computer Vision (CV); Independent Component Analysis (ICA); Motion detection; Observation vector generation;
D O I：
10.11999/JEIT140197
中图分类号：
学科分类号：
摘要：
Most of the existing Independent Component Analysis (ICA) based motion detection algorithms use a single observation vector generation method and two-channel data for motion detection, which make the traditional algorithms unable to obtain a more complete and accurate state of the moving objects. In this paper, four different observation vector generation methods are proposed and larger channel numbers are introduced into traditional ICA. The motion characteristics of the moving objects are covered more widely and more information for foreground extraction is obtained from the multi-channel data. These improvements make ICA be able to deal with indistinguishable and slowly moving objects. The quantitative evaluation from different experiments show s that the multi-channel data and the combination of four observation vector generation methods enable ICA to achieve a better performance with a reasonable cost of tiny increase on false alarms. ©, 2014, Science Press. All right reserved.
引用
收藏
页码：137 / 142
页数：5
相关论文
共 20 条
  • [1] Huang D.Y., Chen C.H., Hu W.C., Et al., Reliable moving vehicle detection based on the filtering of swinging tree leaves and raindrops, Journal of Visual Communication and Image Representation, 23, 4, pp. 648-664, (2012)
  • [2] Song H., Liu X., Zhang X., Et al., Real-time monitoring for crowd counting using video surveillance and GIS, Proceedings of the 2nd International Conference on Remote Sensing, Environment and Transportation Engineering, pp. 1-4, (2012)
  • [3] Sidla O., Rosner M., Ulm M., Et al., Traffic monitoring with distributed smart cameras, Proceedings of the IS & T/SPIE Electronic Imaging, (2012)
  • [4] Park S., Aggarwal J.K., A hierarchical Bayesian network for event recognition of human actions and interactions, Multime dia Systems, 10, 2, pp. 164-179, (2004)
  • [5] Shotton J., Sharp T., Kipman A., Et al., Real-time human pose recognition in parts from single depth images, Communications of the ACM, 56, 1, pp. 116-124, (2013)
  • [6] Schwarz L.A., Mateus D., Navab N., Recognizing multiple human activities and tracking full-body pose in unconstrained environments, Pattern Recognition, 45, 1, pp. 11-23, (2012)
  • [7] Haritaoglu I., Harwood D., Davis L.S., W4: real-time surveillance of people and their activities, IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, 8, pp. 809-830, (2000)
  • [8] Held C., Krumm J., Markel P., Et al., Intelligent video surveillance, Computer, 45, 3, pp. 83-84, (2012)
  • [9] Komagal E., Vinodhini A., Srinivasan A., Et al., Real time background subtraction techniques for detection of moving objects in video surveillance system, Proceedings of the IEEE International Conference on Computing, Communication and Applications, pp. 1-5, (2012)
  • [10] Hu W., Tan T., Wang L., Et al., A survey on visual surveillance of object motion and behaviors, IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 34, 3, pp. 334-352, (2004)
12