Abnormal event detection with semi-supervised sparse topic model

Most research on anomaly detection has focused on event that is different from its spatial–temporal neighboring events. However, it is still a significant challenge to detect anomalies that involve multiple normal events interacting in an unusual pattern. To address this problem, a novel semi-supervised method based on sparse topic model is proposed to detect anomalies in video surveillance. Short local trajectory method is used to extract motion information in order to improve the robustness of trajectories. For the purpose of strengthening the relationship of interest points on the same trajectory, the Fisher kernel method is applied to obtain the representation of trajectory which is quantized into visual word. Then, the sparse topic model is proposed to explore the latent motion patterns and achieve a sparse representation for the video scene. Finally, a semi-supervised learning method is applied to enhance the discrimination of model and improve the performance of anomaly detection. Experiments are conducted on QMUL dataset and AVSS dataset. The results demonstrated the superior efficiency of the proposed method.

[1]  Chang-Tsun Li,et al.  Video anomaly detection based on wake motion descriptors and perspective grids , 2014, 2014 IEEE International Workshop on Information Forensics and Security (WIFS).

[2]  Hanqing Lu,et al.  Dynamic scene understanding by improved sparse topical coding , 2013, Pattern Recognit..

[3]  R. Venkatesh Babu,et al.  Sparse representation based anomaly detection with enhanced local dictionaries , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[4]  Wen-Hsien Fang,et al.  Gaussian Process Regression-Based Video Anomaly Detection and Localization With Hierarchical Feature Representation , 2015, IEEE Transactions on Image Processing.

[5]  Dinesh Manocha,et al.  Realtime Anomaly Detection Using Trajectory-Level Crowd Behavior Learning , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[6]  Te-Won Lee,et al.  On the multivariate Laplace distribution , 2006, IEEE Signal Processing Letters.

[7]  Martin D. Levine,et al.  Online Dominant and Anomalous Behavior Detection in Videos , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Iman Gholampour,et al.  Incorporating fully sparse topic models for abnormality detection in traffic videos , 2014, 2014 4th International Conference on Computer and Knowledge Engineering (ICCKE).

[9]  Junsong Yuan,et al.  Sparse reconstruction cost for abnormal event detection , 2011, CVPR 2011.

[10]  Gabriela Csurka,et al.  Adapted Vocabularies for Generic Visual Categorization , 2006, ECCV.

[11]  Qingshan Liu,et al.  Abnormal detection using interaction energy potentials , 2011, CVPR 2011.

[12]  Gian Luca Foresti,et al.  Surveillance-Oriented Event Detection in Video Streams , 2011, IEEE Intelligent Systems.

[13]  Jin Young Choi,et al.  Visual Path Prediction in Complex Scenes with Crowded Moving Objects , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Li-min Xia,et al.  Recognition of suspicious behavior using case-based reasoning , 2015 .

[15]  Amitabha Mukerjee,et al.  Anomaly Localization in Topic-Based Analysis of Surveillance Videos , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[16]  Li-min Xia夏利民,et al.  Recognition of suspicious behavior using case-based reasoning , 2015 .

[17]  Thomas B. Moeslund,et al.  Abnormal event detection using local sparse representation , 2014, 2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[18]  Jin Young Choi,et al.  Two-stage online inference model for traffic pattern analysis and anomaly detection , 2014, Machine Vision and Applications.

[19]  Raja Bala,et al.  Adaptive Sparse Representations for Video Anomaly Detection , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[20]  Jean-Marc Odobez,et al.  Extracting and locating temporal motifs in video scenes using a hierarchical non parametric Bayesian model , 2011, CVPR 2011.

[21]  Hanqing Lu,et al.  Bilayer Sparse Topic Model for Scene Analysis in Imbalanced Surveillance Videos , 2014, IEEE Transactions on Image Processing.

[22]  Janusz Konrad,et al.  Action Recognition Using Sparse Representation on Covariance Manifolds of Optical Flow , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[23]  Thomas Mensink,et al.  Improving the Fisher Kernel for Large-Scale Image Classification , 2010, ECCV.

[24]  Cordelia Schmid,et al.  Dense Trajectories and Motion Boundary Descriptors for Action Recognition , 2013, International Journal of Computer Vision.