BASED-ON PARTICLE FILTER FOR VEHICLE DETECTION AND TRACKING IN DIGITAL VIDEO
In this paper, the visual-tracking problem for the case of maneuvering target is addressed. The environment of maneuvering tracking for the visual information processing is complex often, there is much non-linear motion. The particle filter is applied for this problem. To predict the probably position of the visual-object at the next time by used this method. For initial filter, discrete wavelet transform is used to detect the object, and a suitable model to characterize a state space. By experimental, this method is proved much effectively, and the accuracy of tracking is improved greatly.
Tracking Estimation Particle filtering Visual information processing
DA-PENG BAI BING-BING LEE
Institute of Command Automation, PLA University of Science and Technology, Nanjing 210007, China CETC 49th Institute, Harbin 150001, China
国际会议
2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)
昆明
英文
2810-2814
2008-07-12（万方平台首次上网日期，不代表论文的发表时间）