教師資料查詢 | 類別: 會議論文 | 教師: 顏淑惠 Yen Shwu-huey (瀏覽個人網頁)

標題:Abnormal Event Detection Using HOSF
學年102
學期1
發表日期2013/12/16
作品名稱Abnormal Event Detection Using HOSF
作品名稱(其他語言)
著者Yen, Shwu-Huey; Wang, Chun-Hui
作品所屬單位淡江大學資訊工程學系
出版者
會議名稱The International Conference on IT Convergence and Security (ICITCS 2013)
會議地點Macau
摘要In this paper a simple and effective crowd behavior normality method is proposed. We use the histogram of oriented social force (HOSF) as the feature vector to encode the observed events of a surveillance video. A dictionary of codewords is trained to include typical HOSFs. To detect whether an event is normal is accomplished by comparing how similar to the closest codeword via z-value. The proposed method includes the following characteristic: (1) the training is automatic without human labeling; (2) instead of object tracking, the method integrates particles and social force as feature descriptors; (3) z-score is used in measuring the normality of events. The method is testified by the UMN dataset with promising results.
關鍵字normality;crowd;social force (SF);histogram of oriented social force (HOSF);z-value
語言英文
收錄於
會議性質國際
校內研討會地點
研討會時間20131216~20131218
通訊作者
國別澳門
公開徵稿Y
出版型式電子版
出處Proceedings of the International Conference on IT Convergence and Security (ICITCS 2013), 4p.
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!