Electrical Engineering
      and Computer Sciences

Electrical Engineering and Computer Sciences

COLLEGE OF ENGINEERING

UC Berkeley

   

2009 Research Summary

Unsupervised Content-based Organization of Large Collections of Activity Videos

View Current Project Information

Parvez Ahammad, Chuohao Yeo, Kannan Ramchandran and S. Shankar Sastry

Army Research Office W911NF-06-1-0076, National Science Foundation CCR-0330514 and Agency for Science, Technology and Research

Given a large collection of videos containing activities, we are investigating the problem of organizing it in an unsupervised fashion into a hierarchy based on the similarity of actions embedded in the videos [1]. We use spatio-temporal volumes of filtered motion vectors to compute appearance-invariant action similarity measures efficiently [2], and use these similarity measures in hierarchical agglomerative clustering to organize videos into a hierarchy such that neighboring nodes contain similar actions. This naturally leads to a simple automatic scheme for selecting videos of representative actions (exemplars) from the database and for efficiently indexing the whole database. We compute a performance metric on the hierarchical structure to evaluate goodness of the estimated hierarchy, and show that this metric has potential for predicting the clustering performance of various joining criteria used in building hierarchies. Our results show that perceptually meaningful hierarchies can be constructed based on action similarities with minimal user supervision, while providing favorable clustering performance and retrieval performance [1].

[1]
P. Ahammad, C. Yeo, K. Ramchandran, and S. S. Sastry, "Unsupervised Discovery of Action Hierarchies in Large Collections of Activity Videos," Proceedings of IEEE International Workshop on Multimedia Signal Processing (MMSP), 2007.
[2]
C. Yeo, P. Ahammad, K. Ramchandran, and S. S. Sastry, "Compressed Domain Real-time Action Recognition," Proceedings of IEEE International Workshop on Multimedia Signal Processing (MMSP), 2006.