Semantic annotation of soccer videos: automatic highlights identification
Computer Vision and Image Understanding - Special isssue on video retrieval and summarization
Structure analysis of soccer video with domain knowledge and hidden Markov models
Pattern Recognition Letters - Video computing
Sports video processing for description, summarization and search
Sports video processing for description, summarization and search
The segmentation of news video into story units
WAIM'05 Proceedings of the 6th international conference on Advances in Web-Age Information Management
Hi-index | 0.00 |
The Soccer Video Edition, SVE, system is an integrated toolset for content-based segmentation, indexing, summarization and retrieval of soccer video sequences. SVE implements a bimodal (visual and text) approach for soccer video exploitation. In this approach, automatic visual information extraction is used to generate a first, objective textual documentation of the video. This latter is then enriched semi-automatically through a recommendation system that relies on the game rules and spatio-temporal relations to propose documentation possibilities. The resulting semantic documentation provide for a faster and more precise video exploitation. This paper presents the SVE functionalities, their theoretical bases and some experimental evaluation results.