Time-Embedding 2D Locality Preserving Projection for Video Summarization

In this paper we present an effective approach to creating quality video summarization. Considering the video frame sequence and visual similarity, we defined a novel distance formula, which is equivalent to Euclidean distance in respect of norm. A time embedding two dimensional locality preserving projection (TE-2DLPP) is proposed. Experiments show that the new algorithm has better time performance. From the resulting frame cluster, a summary storyboard of the video is created in TE-2DLPP feature subspace, and the obtained experimental results are encouraging.