The Community for Technology Leaders
CVPR 2011 (2011)
Providence, RI
June 20, 2011 to June 25, 2011
ISBN: 978-1-4577-0394-2
pp: 3313-3320
Bin Zhao , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Li Fei-Fei , Comput. Sci. Dept., Stanford Univ., Stanford, CA, USA
E. P. Xing , Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
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.
video sequence, online detection, unusual event detection, video stream, normality, abnormality, time constraints, statistical limitation, parametric models, unsupervised dynamic sparse coding approach, query signals, event dictionary, principled convex optimization formulation, sparse reconstruction code, online dictionary, concept drift, surveillance video, Youtube videos

Bin Zhao, Li Fei-Fei and E. P. Xing, "Online detection of unusual events in videos via dynamic sparse coding," CVPR 2011(CVPR), Providence, RI, 2011, pp. 3313-3320.
164 ms
(Ver 3.3 (11022016))