High Quality Compression of Educational Videos Using Content-Adaptive Framework

摘要

With multimedia E-learning becoming popular, better compression algorithms are required that are space efficient but maintain the quality of video data, particularly slide and blackboard text. In this paper, an educational video compression technique is presented that dynamically allocates the space according to the content importance of each video segment in the educational videos. We present a phase correlation based motion estimation and compensation algorithm to encode important moving objects in efficient manner. Temporal coherence is exploited in a two phase manner. First, the frames with high similarity are categorized and encoded efficiently. Secondly, the compression ratio is adapted according to the frame content. The algorithm is compared with the state-of-the-art standards such as H.261, MPEG-4, etc. on large database. The comparison shows that for similar bit rates, the video quality for our algorithm is significantly better than the other methods.