Automatic pan-and-scan algorithm for heterogeneous displays

Abstract

This paper presents a fully automatic algorithm for selecting the most appropriate areas of every video frame to show on heterogeneous display devices. The algorithm is used to analyze cinematic features in video and identify important parts of each frame. The proposed method is a client-server model. An importance map of video is created on the server and transmitted along with the video stream. The client uses this map to determine the cropping area of video frames to fit its display screen. An experimental comparison involving users’ satisfaction of 160 participants who compared the results of our algorithm with others, such as letterbox, and commercially cropped editions of well-known motion pictures was performed. The results show that the audience preferred the video processed by our algorithm as the algorithm requires little additional preprocessing and little extra information embedded in the video stream. The results suggest that this algorithm could improve the video viewing experience for mobile users.