Panoramic Video Separation with Online Grassmannian Robust Subspace Estimation

In this work, we propose a new total variation (TV)-regularized robust principal component analysis (RPCA) algorithm for panoramic video data with incremental gradient descent on the Grassmannian. The resulting algorithm has performance competitive with state-of-the-art panoramic RPCA algorithms and can be computed frame-by-frame to separate foreground/background in video with a freely moving camera and heavy sparse noise. We show that our algorithm scales favorably in computation time and memory. Finally we compare foreground detection accuracy and computation time of our method versus several existing methods.

[1]  David Zhang,et al.  Fast total-variation based image restoration based on derivative alternated direction optimization methods , 2015, Neurocomputing.

[2]  Marc Teboulle,et al.  A fast Iterative Shrinkage-Thresholding Algorithm with application to wavelet-based image deblurring , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[3]  Sajid Javed,et al.  On the Applications of Robust PCA in Image and Video Processing , 2018, Proceedings of the IEEE.

[4]  Fatih Murat Porikli,et al.  CDnet 2014: An Expanded Change Detection Benchmark Dataset , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[5]  Mehran Yazdi,et al.  New trends on moving object detection in video images captured by a moving camera: A survey , 2018, Comput. Sci. Rev..

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

[7]  Angshul Majumdar,et al.  Removing sparse noise from hyperspectral images with sparse and low-rank penalties , 2016, J. Electronic Imaging.

[8]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[9]  Luc Van Gool,et al.  The 2018 DAVIS Challenge on Video Object Segmentation , 2018, ArXiv.

[10]  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..

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

[12]  Brendt Wohlberg,et al.  Video background modeling under impulse noise , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[13]  Marc Van Droogenbroeck,et al.  Low-rank plus sparse decomposition for exoplanet detection in direct-imaging ADI sequences. The LLSG algorithm , 2016, 1602.08381.

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

[15]  Laura Balzano,et al.  Incremental gradient on the Grassmannian for online foreground and background separation in subsampled video , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Xiaochun Cao,et al.  Total Variation Regularized RPCA for Irregularly Moving Object Detection Under Dynamic Background , 2016, IEEE Transactions on Cybernetics.

[17]  Robert D. Nowak,et al.  High-dimensional Matched Subspace Detection when data are missing , 2010, 2010 IEEE International Symposium on Information Theory.

[18]  Jeffrey A. Fessler,et al.  Improved Robust PCA using low-rank denoising with optimal singular value shrinkage , 2014, 2014 IEEE Workshop on Statistical Signal Processing (SSP).

[19]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

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

[21]  Robert D. Nowak,et al.  Online identification and tracking of subspaces from highly incomplete information , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[22]  John Wright,et al.  Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization , 2009, NIPS.

[23]  Alan Edelman,et al.  The Geometry of Algorithms with Orthogonality Constraints , 1998, SIAM J. Matrix Anal. Appl..

[24]  Vinita Vasudevan,et al.  A Hierarchical Singular Value Decomposition Algorithm for Low Rank Matrices , 2017, ArXiv.

[25]  Raj Rao Nadakuditi,et al.  OptShrink: An Algorithm for Improved Low-Rank Signal Matrix Denoising by Optimal, Data-Driven Singular Value Shrinkage , 2013, IEEE Transactions on Information Theory.

[26]  Tao Tao,et al.  Iterative online subspace learning for robust image alignment , 2013, 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG).

[27]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[28]  Raj Rao Nadakuditi,et al.  Panoramic Robust PCA for Foreground–Background Separation on Noisy, Free-Motion Camera Video , 2017, IEEE Transactions on Computational Imaging.