A PLURAL PERSON TRACKING BASED ON MOTION FEATURE CLUSTERING

摘要：

　　Recently, imaging technology spreads widely and is used, especially for security purpose such as detecting suspicious persons or intruders.However, there are problems and difficulties for applying to real situations such as crowd at station s concourse, and so on.Complex background,plural target persons, and so on are examples of such difficulties.Moreover, more pursuit targets will require more processing time.This means that it is hard to do real time processing.In this paper, a plural person tracking technique is proposed.The proposal is based on motion feature clustering.Under the crowded situation, a motion of person tends to be influenced by motions of circumference persons.Therefore,the proposition consists of clustering of motion features of person and tracking the cluster as a single motion object.Thereby, the proposition achieves efficient processing for tracking plural persons.

关键词： Motion Tracking Plural Persons Clustering Motion Features

作者: Hiroki Nagayasu Hitoshi Yamauchi Hironori Takimoto Mitsuru Jindai

作者单位: Faculty of Computer Science and Systems Engineering, Okayama Prefectural University,111 Kuboki, Soja-shi, Okayama, 719-1197 Japan

会议类型: 国际会议

会议名称: The 11th International Conference on Industrial Management(第十一届工业管理国际会议)

会议地点: 日本

会议语种:英文

页码: 640-644

在线出版日期: 2012-08-29（万方平台首次上网日期，不代表论文的发表时间）