Anomaly Detection using a Convolutional Winner-Take-All Autoencoder

We propose a method for video anomaly detection using a winner-take-all convolutional autoencoder that has recently been shown to give competitive results in learning for classification task. The method builds on state of the art approaches to anomaly detection using a convolutional autoencoder and a one-class SVM to build a model of normality. The key novelties are (1) using the motion-feature encoding extracted from a convolutional autoencoder as input to a one-class SVM rather than exploiting reconstruction error of the convolutional autoencoder, and (2) introducing a spatial winner-take-all step after the final encoding layer during training to introduce a high degree of sparsity. We demonstrate an improvement in performance over the state of the art on UCSD and Avenue (CUHK) datasets.

[1]  David C. Hogg,et al.  Who knows who - Inverting the Social Force Model for finding groups , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[2]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Ramin Mehran,et al.  Abnormal crowd behavior detection using social force model , 2009, CVPR.

[4]  Brendan J. Frey,et al.  Winner-Take-All Autoencoders , 2014, NIPS.

[5]  Marc'Aurelio Ranzato,et al.  Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[7]  Kristen Grauman,et al.  Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates , 2009, CVPR.

[8]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[9]  Ehud Rivlin,et al.  Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Jonghyun Choi,et al.  Learning Temporal Regularity in Video Sequences , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[12]  Nuno Vasconcelos,et al.  Anomaly detection in crowded scenes , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Ce Liu,et al.  Exploring new representations and applications for motion analysis , 2009 .

[14]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[15]  Nicu Sebe,et al.  Learning Deep Representations of Appearance and Motion for Anomalous Event Detection , 2015, BMVC.

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

[17]  Cewu Lu,et al.  Abnormal Event Detection at 150 FPS in MATLAB , 2013, 2013 IEEE International Conference on Computer Vision.

[18]  Martial Hebert,et al.  A Discriminative Framework for Anomaly Detection in Large Videos , 2016, ECCV.

[19]  Richard Szeliski,et al.  A Database and Evaluation Methodology for Optical Flow , 2007, 2007 IEEE 11th International Conference on Computer Vision.