LAPACK Users' guide (third ed.)
LAPACK Users' guide (third ed.)
X-means: Extending K-means with Efficient Estimation of the Number of Clusters
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Automated Scene Matching in Movies
CIVR '02 Proceedings of the International Conference on Image and Video Retrieval
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A framework for multimedia content abstraction and its application to rushes exploration
Proceedings of the 6th ACM international conference on Image and video retrieval
The trecvid 2007 BBC rushes summarization evaluation pilot
Proceedings of the international workshop on TRECVID video summarization
Skimming rushes video using retake detection
Proceedings of the international workshop on TRECVID video summarization
Detecting and clustering multiple takes of one scene
MMM'08 Proceedings of the 14th international conference on Advances in multimedia modeling
Snap2Play: a mixed-reality game based on scene identification
MMM'08 Proceedings of the 14th international conference on Advances in multimedia modeling
Region covariance: a fast descriptor for detection and classification
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
| Hi-index | 0.00 |
Grouping shots recorded in front of the same or similar setting is a useful tool for organizing a collection of rushes video. We propose an approach that clusters key frames extracted from rushes by visual similarity of the setting shown in the shot. A region descriptor based on the covariance of selected features is used to estimate the dissimilarity of two key frames. The metric based on the generalized eigenvalues is used to determine the distance of two region covariance matrices. Integral images support efficient covariance computation of arbitrary rectangular regions. Based on the determined similarity of image regions, a dissimilarity matrix of all key frames is calculated. This dissimilarity matrix is used to build the clusters which reflect the different settings. The proposed algorithm is evaluated on a subset of the TRECVID BBC 2007 rushes data set.