Application of scalable visual sensitivity profile in image and video coding

Computational visual attention models have facilitated various aspects of the evolution in visual communication systems. In this paper, we apply the proposed computational model for scalable visual sensitivity profile (SVSP) to image/video processing. SVSP generates a hierarchy of saliency maps that simulate the bottom-up and top-down attention of the human visual system (HVS). It can detect the most significant visual information in a picture and spatially prioritize the information to augment the visual quality, such as in noise-shaping and region-of-interest (ROI) coding of JPEG2000. Furthermore, ROI scalable video coding (SVC) also benefits from the proposed SVSP due to its hierarchical nature, as multiple perceptually prioritized ROIs can be extracted by simply segmenting the SVSP in multiple thresholds in a scalable manner. It can be applied to automatically evaluate the quality for ROI scalability, and thus has the potential to reduce the workload of subjective tests for ROI SVC algorithms in the current MPEG activities. Extensive experiments are conducted to show the performances that justify the effectiveness of the proposed SVSP model.