Algorithm on Moving Targets Classification Based on Fuzzy Clustering

摘要：

In video surveillance system, in order to classify vehicles, every region of moving target can be labeled by single linking region growing algorithm, o the area and degree of shape complex can be gotten for every target, and can be used as input eigenvalues, then fuzzy clustering algorithm is adopted to classify moving targets. In this course, euclid distance with weights is used as criterion, and iteration method is built to classify vehicles. Experimental results show this method has a high classification rate in recognizing vehicle, and this algorithm is simple.

关键词： video surveillance target classification fuzzy clustering intelligent transportation system

作者: Ruili Zeng Yunkui Xiao Gang Li Lingling Zhang Guoben He

作者单位: Mathematics&Computer Institute Xihua University Chengdu Sichuan China School of Precision Instrument Department of Automobile Engineering Academy of Military Transportation Tianjin China School of Precision Instrument & Opto-Electronic Engineering Tianjin University Tianjin China

会议类型: 国际会议

会议名称: 2010 3rd IEEE International Conference on Computer Science and Information Technology(第三届IEEE计算机科学与信息技术国际会议 ICCSIT 2010)

会议地点: 成都

会议语种:英文

页码: 288-291

在线出版日期: 2010-07-07（万方平台首次上网日期，不代表论文的发表时间）