PEGASUS: An Information Mining System for TV News Videos

Content -based video retrieval (CBVR ) problems have gained significant importance in today’s intelligence world demanding further insight. Compared to the traditional video indexing systems, CBVR systems do not require the intensive human effort in the semantic annotation. In this paper, we propose the PEGASUS system. PEGASUS is an integrated news video search system containing two utilities: a fast multi-modality indexing system, and an interactive framework for the search on semantic topics. The indexing system is constructed based on the features from both the visual and speech portions of the videos. In the retrieval phase, the user submits a query generated from the desired semantic topic. The initial return by the system is based on the Automatic Speech Recognition information search.The results are then refined by performing a series of relevance feedback processes using other features, such as the optical character recognition (OCR) output, and global color statistics of the key-frames. The advantages of the PEGASUS system are that the queries are better formulated by key word histograms and the relevant result sets can be expanded using content analysis. We have participated in the TREC Video Retrieval Evaluation (TRECVID) forum, which has been organized by the U.S. National Institute of Standards and Technologies (NIST). Semantic topics have been tested on the PEGASUS system, and very satisfactory results were obtained.