A novel optical flow-based representation for temporal video segmentation

Temporal video segmentation is a field of multimedia research enabling us to temporally split video data into semantically coherent scenes. In order to develop methods challenging temporal video segmentation, detecting scene boundaries is one of the more widely used approaches. As a result, representation of temporal information becomes important. We propose a new temporal video segment representation to formalize video scenes as a sequence of temporal motion change information. The idea here is that some sort of change in the optical flow character determines motion change and cuts between consecutive scenes. The problem is eventually reduced to an optical flow-based cut detection problem from which the average motion vector concept is put forward. This concept is used for proposing a pixel-based representation enriched with a novel motion-based approach. Temporal video segment points are classified as cuts and noncuts according to the proposed video segment representation. Consequently, the proposed method and representation is applied to benchmark data sets and the results are compared to other state-of-the art methods.