Robust Multiple Targets Tracking Using Object Segmentation and Trajectory Estimation in Video
學年 94
學期 1
發表日期 2005-10-10
作品名稱 Robust Multiple Targets Tracking Using Object Segmentation and Trajectory Estimation in Video
作品名稱(其他語言)
著者 Hsiao, Ying-Tung; Chuang, Cheng-Long; Jiang, Joe-Air; Chien, Cheng-Chih
作品所屬單位 淡江大學電機工程學系
出版者 N.Y.: IEEE (Institute of Electrical and Electronic Engineers)
會議名稱 Systems, Man and Cybernetics, 2005 IEEE International Conference on
會議地點 Waikoloa, United States
摘要 In this paper, a novel robust unsupervised video object tracking algorithm is proposed. The proposed algorithm combines several techniques: mathematical morphology, region growing, region merging, and trajectory estimation, for tracking several predetermined video objects, simultaneously. A modified mathematical morphological edge detector was employed to sketch the contour of the video frame; and an edge-based object segmentation algorithm was applied to the contour for partitioning the predetermined objects; moreover, according to the motion of the objects, the proposed algorithm can estimate and partition the objects in following video frames, automatically. The proposed algorithm is also robustness against mobile cameras. The experimental results show that the proposed algorithm can precisely partition and track multiple video objects
關鍵字
語言 en
收錄於
會議性質 國際
校內研討會地點
研討會時間
通訊作者
國別 USA
公開徵稿
出版型式
出處 Systems, Man and Cybernetics, 2005 IEEE International Conference on, Hawaii, USA, pp.1080-1085
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/70551 )

機構典藏連結