Fast multi-view people localization using a torso-high reference plane

Chun Chieh Hsu, Hua Tsung Chen, W. J. Tsai, Suh Yin Lee

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

People locations bring rich information for a wide spectrum of applications in intelligent video surveillance systems. In addition to localization accuracy, computational efficiency is another significant issue to be highly concerned in people localization. As an essential early stage, people localization has to be accomplished in a very short time, enabling further semantic analysis. However, most state-of-the-art people localization methods pay little attention to computational efficiency. Hence, in this paper we propose an effective and efficient multi-view people localization scheme with several acceleration mechanisms. First, a torso-high reference plane is introduced since in general the torso part (after foreground segmentation) is more intact and stable than the other parts of a human body, and thus can predict potential people locations more reliably. Then, a novel and computationally efficient bitwise-operation scheme is proposed to predict people locations at the intersection regions of foreground line samples from multiple views. After rule-based validation, people locations can be accurately obtained and visualized on a real world plane. Experiments on multi-view surveillance videos not only validate the high accuracy of the proposed method in locating people under crowded scenes with serious occlusions, but also demonstrate an outstanding computational speed.

原文English
主出版物標題2017 IEEE Visual Communications and Image Processing, VCIP 2017
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1-4
頁數4
ISBN(電子)9781538604625
DOIs
出版狀態Published - 2 7月 2017
事件2017 IEEE Visual Communications and Image Processing, VCIP 2017 - St. Petersburg, United States
持續時間: 10 12月 201713 12月 2017

出版系列

名字2017 IEEE Visual Communications and Image Processing, VCIP 2017
2018-January

Conference

Conference2017 IEEE Visual Communications and Image Processing, VCIP 2017
國家/地區United States
城市St. Petersburg
期間10/12/1713/12/17

指紋

深入研究「Fast multi-view people localization using a torso-high reference plane」主題。共同形成了獨特的指紋。

引用此