Visual attention based region of interest coding for video-telephony applications

Abstract

Bottom up approaches to Visual Attention (VA) have been applied successfully in a variety of applications, where no domain information exists, e.g. general purpose image and video segmentation. On the other hand, when humans are looking for faces in a scene they perform an implicit conscious search. Therefore, using simple bottom up approaches for identifying visually salient areas in scenes containing humans are not so efficient. In this paper we introduce the inclusion of a top-down channel in the VA architecture proposed in the past (i.e., Itti et al) to account for conscious search in video telephony applications. In such kind of applications the existence of human faces is almost always guaranteed. The regions, in the video-telephony stream, identified by the proposed algorithm as being visually salient are encoded with higher precision compared to the remaining ones. This procedure leads to a significant bit-rate reduction while the visual quality of the VA based encoded video stream is only slightly deteriorated, as the visual trial tests show. Furthermore, extended experiments concerning both static images as well as low-quality video show the efficiency of the proposed method, as far as the compression ratios achieved is concerned. The comparisons are made against standard JPEG and MPEG-1 encoding respectively.