Video Identification Using Spatio-temporal Salient Points

Automatic identification of video is a key technique to various applications such as content based retrieval, copyright protection and broadcast monitoring. In this paper, we present a novel video identification scheme via spatio-temporal salient points. To achieve higher robustness to content preserved manipulations, especially geometric distortions, salient points are detected from both spatial and temporal aspects. The salient points are found to be invariant in a series of distortions. In addition, we have compared our approach with a state-of-the-art one on diverse sequences and superior performances on detection accuracy have been observed in the proposed work.