ABSTRACT
Anomaly detection in crowd scene has attracted an increasing attention in video surveillance, but a precise detection still remains a challenge. This paper presents a novel online learning method to automatically detect abnormal behaviors in crowd scene. Our focus is mainly on the deviation between the real motion and the predicted one. Through online defining experts, analyzing their motions, and dynamically updating the learned model, anomaly can be identified by the final expert joint decision. The outputs are represented as the anomaly probability of an examined frame. Compared with most of existing methods, the proposed one needs neither tracking each individual straight to the end nor requires any complex training procedure. We test the proposed method on public datasets, and the results show its effectiveness.
- PETS2009 dataset. http://www.cvg.rdg.ac.uk/PETS2009/a.html.Google Scholar
- UMN dataset. http://mha.cs.umn.edu/movies/.Google Scholar
- H. Cheng and J. Hwang. Integrated video object tracking with applications in trajectory-based event detection. J. Visual Communication and Image Representation, 22(7):673--685, 2011. Google ScholarDigital Library
- Y. Cong, J. Yuan, and J. Liu. Abnormal event detection in crowded scenes using sparse representation. Pattern Recognition, 2012. Google ScholarDigital Library
- X. Cui, Q. Liu, M. Gao, and D. Metaxas. Abnormal detection using interaction energy potentials. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 3161--3167, Jun. 2011. Google ScholarDigital Library
- P. Dollár, S. Belongie, and P. Perona. The fastest pedestrian detector in the west. In Proc. British Machine Vision Conference, pages 1--11, Sept. 2010.Google ScholarCross Ref
- O. Junior, D. Delgado, V. Gonçalves, and U. Nunes. Trainable classifier-fusion schemes: an application to pedestrian detection. In Proc. IEEE Conf. Intelligent Transportation Systems, pages 1--6, Oct. 2009.Google ScholarCross Ref
- V. Mahadevan, W. Li, V. Bhalodia, and N. Vasconcelos. Anomaly detection in crowded scenes. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 1975--1981, Jun. 2010.Google ScholarCross Ref
- R. Mehran, A. Oyama, and M. Shah. Abnormal crowd behavior detection using social force model. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 935--942, Jun. 2009.Google ScholarCross Ref
- Q. Wang, J. Fang, and Y. Yuan. Multi-cue based tracking. Neurocomputing, 131:227--236, 2014. Google ScholarDigital Library
- Q. Wang, Y. Yuan, P. Yan, and X. Li. Saliency detection by multiple-instance learning. IEEE T. Cybernetics, 43(2):660--672, 2013.Google ScholarCross Ref
- S. Wang and Z. Miao. Anomaly detection in crowd scene. In Proc. Int. Conf. Signal Processing, pages 1220--1223, Oct. 2010.Google ScholarCross Ref
- S. Wu, B. Moore, and M. Shah. Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 2054--2060, Jun. 2010.Google ScholarCross Ref
- Y. Yuan, J. Fang, and Q. Wang. Robust superpixel tracking via depth fusion. IEEE Trans. Circuits Syst. Video Techn., 24(1):15--26, 2014.Google ScholarDigital Library
- Y. Zhang, L. Qin, H. Yao, and Q. Huang. Abnormal crowd behavior detection based on social attribute-aware force model. In Proc. Int. Conf. Image Processing, pages 2689--2692, Oct. 2012.Google ScholarCross Ref
Index Terms
- Anomaly Detection in Crowd Scene via Online Learning
Recommendations
Online Learning with Self-Organizing Maps for Anomaly Detection in Crowd Scenes
ICPR '10: Proceedings of the 2010 20th International Conference on Pattern RecognitionDetecting abnormal behaviors in crowd scenes is quite important for public security and has been paid more and more attentions. Most previous methods use offline trained model to perform detection which can’t handle the constantly changing crowd ...
Deep learning for anomaly detection in multivariate time series: Approaches, applications, and challenges
AbstractAnomaly detection has recently been applied to various areas, and several techniques based on deep learning have been proposed for the analysis of multivariate time series. In this study, we classify the anomalies into three types, ...
Highlights- The methods for anomaly detection on multivariate time series are reviewed.
- The ...
Crowd Behavior Representation Using Motion Influence Matrix for Anomaly Detection
ACPR '13: Proceedings of the 2013 2nd IAPR Asian Conference on Pattern RecognitionIn this paper, we propose a new method to detect abnormal behavior in crowd video. The motion influence matrix is proposed to represent crowd behaviors. It is generated based on concept of human perception with block-level motion vectors which describe ...
Comments