Abstract
In this paper, we propose an algorithm for identifying regions of interest (ROIs) in video, particularly for the keyframes extracted from a home video. The camera motion is introduced as a new factor that can influence the visual saliency. The global motion parameters are used to generate location-based importance maps. These maps can be combined with other saliency maps calculated using other visual and high-level features. Here, we employed the contrast-based saliency as an important low level factor along with face detection as a high level feature in our approach.
Keywords
home computing, image motion analysis, video cameras, video retrieval, video signal processingROI, camera motion, contrast-based saliency, home videos, location-based importance map, regions-of-interest identification
