A context-aware video display scheme for mobile devices

Abstract

A fully automatic and computationally efficient method is proposed for intelligent display of soccer video on small multimedia mobile devices. The rapid progress of the multimedia signal processing has contributed to the extensive use of multimedia devices with small LCD panel. With these flourishing mobile devices with small display, the video sequences captured for normal viewing on standard TV or HDTV may give the small-display-viewers uncomfortable experiences in understanding what is happening in a scene. For instance, in a soccer video sequence taken by a longshot camera technique, the tiny objects (e.g., soccer ball and players) may not be clearly viewed on the small LCD panel. Thus, an intelligent display technique is needed for small-display-viewers. To this end, one of the key technologies is to determine region of interest, which is a part of the scene that viewers pay more attention to than other regions. In this paper, we only focus on soccer video display for mobile devices. Instead of taking visual saliency into account, we take domain-specific approach to exploit the characteristics of the soccer video. We propose a context-aware soccer video display scheme, which includes three folds: ground color learning, shot classification, and ROI determination. The experimental results show the propose scheme is capable of context-aware video display on mobile devices.