Anomaly Detection in Moving-Camera Video Sequences Using Principal Subspace Analysis

This paper presents a family of algorithms based on sparse decompositions that detect anomalies in video sequences obtained from slow moving cameras. These algorithms start by computing the union of subspaces that best represents all the frames from a reference (anomaly free) video as a low-rank projection plus a sparse residue. Then, they perform a low-rank representation of a target (possibly anomalous) video by taking advantage of both the union of subspaces and the sparse residue computed from the reference video. Such algorithms provide good detection results while at the same time obviating the need for previous video synchronization. However, this is obtained at the cost of a large computational complexity, which hinders their applicability. Another contribution of this paper approaches this problem by using intrinsic properties of the obtained data representation in order to restrict the search space to the most relevant subspaces, providing computational complexity gains of up to two orders of magnitude. The developed algorithms are shown to cope well with videos acquired in challenging scenarios, as verified by the analysis of 59 videos from the VDAO database that comprises videos with abandoned objects in a cluttered industrial scenario.

[1]  Hongyu Zhao,et al.  Low-Rank Modeling and Its Applications in Image Analysis , 2014, ACM Comput. Surv..

[2]  Narciso García,et al.  Detection of stationary foreground objects: A survey , 2016, Comput. Vis. Image Underst..

[3]  B. B. V. L. Deepak,et al.  Real-time object detection and Tracking using color feature and motion , 2015, 2015 International Conference on Communications and Signal Processing (ICCSP).

[4]  Jean Ponce,et al.  Detecting Abandoned Objects With a Moving Camera , 2010, IEEE Transactions on Image Processing.

[5]  Brendt Wohlberg,et al.  Incremental Principal Component Pursuit for Video Background Modeling , 2015, Journal of Mathematical Imaging and Vision.

[6]  Hong Liu,et al.  Robust abandoned object detection and analysis based on online learning , 2013, 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[7]  Eduardo A. B. da Silva,et al.  On the detection of abandoned objects with a moving camera using robust subspace recovery and sparse representation , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Eduardo A. B. da Silva,et al.  Anomaly detection with a moving camera using spatio-temporal codebooks , 2018, Multidimens. Syst. Signal Process..

[9]  Emdad Hossain,et al.  Person identification in surveillance video using gait biometric cues , 2012, 2012 9th International Conference on Fuzzy Systems and Knowledge Discovery.

[10]  Aksel Andreas Transeth,et al.  A Robotic Concept for Remote Inspection and Maintenance on Oil Platforms , 2009 .

[11]  Stephen P. Boyd,et al.  Proximal Algorithms , 2013, Found. Trends Optim..

[12]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[13]  Soon Ki Jung,et al.  Spatiotemporal Low-Rank Modeling for Complex Scene Background Initialization , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[14]  Dragoljub Pokrajac,et al.  Detecting and Recognizing Abandoned Objects in Crowded Environments , 2008, ICVS.

[15]  Joan Serrat,et al.  Video Alignment for Change Detection , 2011, IEEE Transactions on Image Processing.

[16]  Alexander Verl,et al.  Mobile robots for offshore inspection and manipulation , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Soon Ki Jung,et al.  Decomposition into Low-rank plus Additive Matrices for Background/Foreground Separation: A Review for a Comparative Evaluation with a Large-Scale Dataset , 2015, Comput. Sci. Rev..

[18]  Rogério Schmidt Feris,et al.  Robust Detection of Abandoned and Removed Objects in Complex Surveillance Videos , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[19]  James M. Rehg,et al.  GOSUS: Grassmannian Online Subspace Updates with Structured-Sparsity , 2013, 2013 IEEE International Conference on Computer Vision.

[20]  Hamid Krim,et al.  Optimal Operator Space Pursuit: A Framework for Video Sequence Data Analysis , 2012, ACCV.

[21]  Suleyman Tosun,et al.  Moving object detection by a mounted moving camera , 2015, IEEE EUROCON 2015 - International Conference on Computer as a Tool (EUROCON).

[22]  Soon Ki Jung,et al.  Motion-Aware Graph Regularized RPCA for background modeling of complex scenes , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[23]  Marc Van Droogenbroeck,et al.  Deep background subtraction with scene-specific convolutional neural networks , 2016, 2016 International Conference on Systems, Signals and Image Processing (IWSSIP).

[24]  Jpt staff.  Sensabot: A Safe and Cost-Effective Inspection Solution , 2012 .

[25]  Tao Tao,et al.  Iterative Grassmannian optimization for robust image alignment , 2013, Image Vis. Comput..

[26]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[27]  Charles Guyon,et al.  Robust Principal Component Analysis for Background Subtraction: Systematic Evaluation and Comparative Analysis , 2012 .

[28]  Kang-Hyun Jo,et al.  Detecting abandoned objects in crowded scenes of surveillance videos using adaptive dual background model , 2015, 2015 8th International Conference on Human System Interaction (HSI).

[29]  El-hadi Zahzah,et al.  LRSLibrary: Low-Rank and Sparse tools for Background Modeling and Subtraction in Videos , 2016 .

[30]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Hiroshi Murase,et al.  Moving camera background-subtraction for obstacle detection on railway tracks , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[32]  Hamid Krim,et al.  BI-sparsity pursuit for robust subspace recovery , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[33]  Gustavo Carvalho,et al.  An annotated video database for abandoned-object detection in a cluttered environment , 2014, 2014 International Telecommunications Symposium (ITS).

[34]  Chun Chen,et al.  Image Alignment by Online Robust PCA via Stochastic Gradient Descent , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[35]  José F. L. de Oliveira,et al.  DORIS-A MOBILE ROBOT FOR INSPECTION AND MONITORING OF OFFSHORE FACILITIES , 2014 .

[36]  Hamid Krim,et al.  Robust Subspace Recovery via Dual Sparsity Pursuit , 2014, ArXiv.

[37]  Marc Pollefeys,et al.  Geometric Change Detection in Urban Environments Using Images , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[39]  Eduardo A. B. da Silva,et al.  Detection of abandoned objects using robust subspace recovery with intrinsic video alignment , 2017, 2017 IEEE International Symposium on Circuits and Systems (ISCAS).

[40]  Wei-Yong Yan.  On principal subspace analysis , 1998 .

[41]  Eduardo A. B. da Silva,et al.  Abandoned object detection using operator-space pursuit , 2015, 2015 IEEE International Conference on Image Processing (ICIP).