Compact Representations of Videos Through Dominant and Multiple Motion Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer Vision
A Statistical Framework for Long-Range Feature Matching in Uncalibrated Image Mosaicing
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Retrieval of Commercials by Video Semantics
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Mosaic based representations of video sequences and their applications
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Structured Digital Video Indexing
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
Semantic Annotation and Indexing of News and Sports Videos
SOFSEM '02 Proceedings of the 29th Conference on Current Trends in Theory and Practice of Informatics: Theory and Practice of Informatics
Hi-index | 0.00 |
Compact yet intuitive representations of digital videos are required to combine high quality storage with interactive video indexing and retrieval capabilities. The advent of video mosaicing has provided a natural way to obtain content-based video representations which are both retrieval-oriented and compression-efficient. In this paper, an algorithm for extracting a robust mosaic representation of video content from sparse interest image points is described. The representation, which is obtained via visual motion clustering and segmentation, features the geometric and kinematic description of all salient objects in the scene, being thus well suited for video browsing, indexing and retrieval by visual content. Results of experiments on several TV sequences provide an insight into the main characteristics of the approach.