A Visual Attention Based Region-of-Interest Determination Framework for Video Sequences(Image Processing and Multimedia Systems, <Special Section>Recent Advances in Circuits and Systems-Part 1)

スポンサーリンク

概要

• 論文の詳細を見る

• This paper presents a framework for automatic video region-of-interest determination based on visual attention model. We view this work as a preliminary step towards the solution of high-level semantic video analysis. Facing such a challenging issue, in this work, a set of attempts on using video attention features and knowledge of computational media aesthetics are made. The three types of visual attention features we used are intensity, color, and motion. Referring to aesthetic principles, these features are combined according to camera motion types on the basis of a new proposed video analysis unit, frame-segment. We conduct subjective experiments on several kinds of video data and demonstrate the effectiveness of the proposed framework.

• 社団法人電子情報通信学会の論文
• 2005-07-01

著者

• Chu Wei

  Department Of Computer Science And Information Engineering National Taiwan University

• Wu Ja

  Graduate Institute Of Networking And Multimedia National Taiwan University

• CHENG Wen

  Graduate Institute of Networking and Multimedia, National Taiwan University

• Cheng Wen

  Graduate Institute Of Networking And Multimedia National Taiwan University

関連論文

• A Visual Attention Based Region-of-Interest Determination Framework for Video Sequences(Image Processing and Multimedia Systems, Recent Advances in Circuits and Systems-Part 1)
• An Efficient Matrix-Based 2-D DCT Splitter and Merger for SIMD Instructions(Image Processing and Multimedia Systems, Recent Advances in Circuits and Systems-Part 1)

スポンサーリンク