The Journal of Machine Learning Research
Scene Segmentation for Behaviour Correlation
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part IV
Bregman Iterative Algorithms for $\ell_1$-Minimization with Applications to Compressed Sensing
SIAM Journal on Imaging Sciences
A duality based approach for realtime TV-L1 optical flow
Proceedings of the 29th DAGM conference on Pattern recognition
Probabilistic latent semantic analysis
UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Sparse reconstruction cost for abnormal event detection
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Online detection of unusual events in videos via dynamic sparse coding
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Human action recognition by learning bases of action attributes and parts
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
| Hi-index | 0.01 |
The explosive growth of cameras in public areas demands a technique which develops a fully automated surveillance and monitoring system. In this paper, we propose a novel unsupervised approach to automatically explore motion patterns occurring in dynamic scenes under an improved sparse topical coding (STC) framework. Given an input video, it is segmented into a sequence of clips without overlapping. Optical flow features are extracted from each pair of consecutive frames, and quantized into discrete visual flow words. Each video clip is interpreted as a document and visual flow words as words within the document. Then the improved STC is applied to explore latent patterns which represent the common motion distributions of the scene. Finally, each video clip is represented as a weighted summation of these patterns with only a few non-zero coefficients. The proposed approach is purely data-driven and scene independent, which make it suitable for very large range applications of scenarios, such as rule mining and abnormal event detection. Experimental results and comparisons on various public datasets demonstrate the promise of the proposed approach.