On-line scene change detection of multicast video

Network-based computing is becoming an increasingly important area of resea rch, whereby computational elements within a distributed infrastructure pro cess/enhance the data that traverses through its path. We refer to these co mputations as online processing and this paper investigates scene change de tection in the context of MBone-based proxies in the network. On-line proce ssing varies from traditional offline processing schemes, where for example , the whole video scope is known as a priori, which allows multiple scans o f the stored video files during video processing. The on-line processing sy stem is designed to meet the requirements of real-time video multicasting o ver the Internet and to utilize the successful video parsing techniques ava ilable today. The proposed algorithms do scene change detection and extract key frames from video bitstreams sent through the MBone network. We study several algorithms based on histogram differences and evaluate them with re spect to precision, recall, and processing latency. (C) 2001 Academic Press .