A Novel Cut Detection Strategy based on Visual Rhythm

S.M. Santos, H.M. Gomes, and D.L. Borges (Brazil)

Keywords

Cut detection, visual rhythm, video summarization

Abstract

Within the context of the automatic analysis of digital video contents, the accurate detection of shot transitions plays an important role, and might be useful for video indexing and summarization, amongst other tasks. This work proposes a novel strategy based on the concept of visual rhythm to automatically detect sharp transitions or cuts in arbitrary videos. A comparative performance evaluation demonstrated that the proposed method presented much higher recall rates at a cost of a little lower average precision rate, when compared to a previous approach.

Important Links:



Go Back