Video saliency detection using modified high efficiency video coding and background modelling

Abstract

Video saliency has a profound effect on our lives with its compression efficiency and precision. There have been several types of research done on image saliency but not on video saliency. This paper proposes a modified high efficiency video coding (HEVC) algorithm with background modelling and the implication of classification into coding blocks. This solution first employs the G-picture in the fourth frame as a long-term reference and then it is quantized based on the algorithm that segregates using the background features of the image. Then coding blocks are introduced to decrease the complexity of the HEVC code, reduce time consumption and overall speed up the process of saliency. The solution is experimented upon with the dynamic human fixation 1K (DHF1K) dataset and compared with several other state-of-the-art saliency methods to showcase the reliability and efficiency of the proposed solution.