Online detection of unusual events in videos via dynamic sparse coding

Authors:
Bin Zhao; Li Fei-Fei;E. P. Xing
Affiliations:
Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA;Comput. Sci. Dept., Stanford Univ., Stanford, CA, USA;Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Venue:
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Year:
2011

Citing 0
Cited 6

Abnormal event detection via multi-instance dictionary learning

IDEAL'12 Proceedings of the 13th international conference on Intelligent Data Engineering and Automated Learning
Dynamic scene understanding by improved sparse topical coding

Pattern Recognition
Multi-part sparse representation in random crowded scenes tracking

Pattern Recognition Letters
An on-line, real-time learning method for detecting anomalies in videos using spatio-temporal compositions

Computer Vision and Image Understanding
Sparse representation for robust abnormality detection in crowded scenes

Pattern Recognition
E-LAMP: integration of innovative ideas for multimedia event detection

Machine Vision and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Real-time unusual event detection in video stream has been a difficult challenge due to the lack of sufficient training information, volatility of the definitions for both normality and abnormality, time constraints, and statistical limitation of the fitness of any parametric models. We propose a fully unsupervised dynamic sparse coding approach for detecting unusual events in videos based on online sparse re-constructibility of query signals from an atomically learned event dictionary, which forms a sparse coding bases. Based on an intuition that usual events in a video are more likely to be reconstructible from an event dictionary, whereas unusual events are not, our algorithm employs a principled convex optimization formulation that allows both a sparse reconstruction code, and an online dictionary to be jointly inferred and updated. Our algorithm is completely un-supervised, making no prior assumptions of what unusual events may look like and the settings of the cameras. The fact that the bases dictionary is updated in an online fashion as the algorithm observes more data, avoids any issues with concept drift. Experimental results on hours of real world surveillance video and several Youtube videos show that the proposed algorithm could reliably locate the unusual events in the video sequence, outperforming the current state-of-the-art methods.