Real-time foreground segmentation for the moving camera based on H.264 video coding information

Wei Di Hong, Tien Hsu Lee, Pao Chi Chang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

9 引文 斯高帕斯(Scopus)

摘要

Foreground segmentation for video frames has played an important role in many video applications, such as video surveillance, video indexing, etc. Due to most videos are compressed, foreground segmentation can benefit from utilizing such coding information and save much processing time. In this paper, we propose a real-time foreground segmentation algorithm for the moving camera based on the H.264 video coding information. In the proposed algorithm, we first utilize the relative global motion model to calculate the approximate global motion vector and get the motion vector difference of each block. Then, according to the block partition modes, we assign different weightings and apply spatio-temporal refinement to these motion vector differences for further improving the accuracy of segmentation results. Finally, we segment out the foreground blocks by an adaptive threshold. With the aid of H.264 video coding information, the proposed segmentation algorithm is more practical than many other methods based on spatial domain information in computational complexity.

原文???core.languages.en_GB???
主出版物標題Proceedings - CIS Workshops 2007, 2007 International Conference on Computational Intelligence and Security Workshops, CISW 2007
發行者Institute of Electrical and Electronics Engineers Inc.
頁面385-390
頁數6
ISBN(列印)0769530486, 9780769530482
DOIs
出版狀態已出版 - 2007
事件2007 International Conference on Future Generation Communication and Networking, FGCN 2007 - Jeju Island, Korea, Republic of
持續時間: 6 12月 20078 12月 2007

出版系列

名字Proceedings of Future Generation Communication and Networking, FGCN 2007
1

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2007 International Conference on Future Generation Communication and Networking, FGCN 2007
國家/地區Korea, Republic of
城市Jeju Island
期間6/12/078/12/07

指紋

深入研究「Real-time foreground segmentation for the moving camera based on H.264 video coding information」主題。共同形成了獨特的指紋。

引用此