Decomposition into Low-rank plus Additive Matrices for Background/Foreground Separation: A Review for a Comparative Evaluation with a Large-Scale Dataset

@article{Bouwmans2017DecompositionIL,
  title={Decomposition into Low-rank plus Additive Matrices for Background/Foreground Separation: A Review for a Comparative Evaluation with a Large-Scale Dataset},
  author={Thierry Bouwmans and Andrews Sobral and Sajid Javed and Soon Ki Jung and El-hadi Zahzah},
  journal={Comput. Sci. Rev.},
  year={2017},
  volume={23},
  pages={1-71}
}
Recent research on problem formulations based on decomposition into low-rank plus sparse matrices shows a suitable framework to separate moving objects from the background. [...] Key Result Finally, experimental results on a large-scale dataset called Background Models Challenge (BMC 2012) show the comparative performance of 32 different robust subspace learning/tracking methods.Expand
Robust PCA Using Matrix Factorization for Background/Foreground Separation
TLDR
A fast background/foreground separation algorithm in which the low-rank constraint is solved by a matrix factorization scheme, thus heavily reducing the computation cost and improving the robustness and flexibility of the traditional nuclear norm. Expand
Robust Low-Rank and Sparse Decomposition for Moving Object Detection: from Matrices to Tensors. (Détection d'objets mobiles dans des vidéos par décomposition en rang faible et parcimonieuse: de matrices à tenseurs)
TLDR
A double-constrained version of robust principal component analysis is proposed to improve the foreground detection in maritime environments for automated video-surveillance applications and the problem of background model initialization as a reconstruction process from missing/corrupted data is addressed. Expand
Generalized nuclear norm and Laplacian scale mixture based low-rank and sparse decomposition for video foreground-background separation
TLDR
This paper adopts the generalized nuclear norm (GNN) and the Laplacian scale mixture (LSM) modeling to approximate the low-rank and sparse matrices, respectively, and proposes a generalized formulation which is called GNNLSM for nonconvex low- rank and sparse decomposition based on the GNN and the LSM. Expand
Background Subtraction via Fast Robust Matrix Completion
  • Behnaz Rezaei, S. Ostadabbas
  • Computer Science, Engineering
  • 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
  • 2017
TLDR
The results showed faster computation, at least twice as when IALM solver is used, while having a comparable accuracy even better in some challenges, in subtracting the backgrounds in order to detect moving objects in the scene. Expand
Subtraction via Fast Robust Matrix Completion
Background subtraction is the primary task of the majority of video inspection systems. The most important part of the background subtraction which is common among different algorithms is backgroundExpand
A Batch-Incremental Video Background Estimation Model Using Weighted Low-Rank Approximation of Matrices
TLDR
This work builds a batch-incremental background estimation model by using a special weighted low-rank approximation of matrices that is superior to the existing state-of-the-art background estimation algorithms such as GRASTA, ReProCS, incPCP, and GFL. Expand
Foreground-Background Separation via Generalized Nuclear Norm and Structured Sparse Norm Based Low-Rank and Sparse Decomposition
TLDR
This paper introduces the generalized nuclear norm and structured sparse norm (GNNSSN) method based LRSD for video foreground-background separation, and extends the proposed model to a robust model against noise for practical applications. Expand
Background subtraction with multi-scale structured low-rank and sparse factorization
TLDR
This paper proposes a novel approach with multi-scale structured low-rank and sparse factorization for background subtraction, different from the conventional methods that only enforce the smoothness between the spatial neighbors, to explore the structured smoothness with both appearance consistency and spatial compactness in the low- Rank and sparsefactorization framework. Expand
Total Variation and Rank-1 Constraint RPCA for Background Subtraction
TLDR
This work proposes a novel BS method employing the more refined prior representations for the static and dynamic components of the video sequences using the framework of schemes-based robust principal component analysis (RPCA). Expand
Generalized singular value thresholding operator based nonconvex low-rank and sparse decomposition for moving object detection
TLDR
The results show that the proposed method for nonconvex low-rank and sparse decomposition based on the generalized singular value thresholding (GSVT) operator is more effective than representative LRSD based moving objects detection algorithms. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 543 REFERENCES
Stochastic decomposition into low rank and sparse tensor for robust background subtraction
TLDR
This work applies the idea of stochastic optimization on tensor for robust low-rank and sparse error separation and reduces the memory and computational complexities of this iterative multi-dimensional tensor data optimization scheme for decomposition. Expand
Robust PCA via Principal Component Pursuit: A review for a comparative evaluation in video surveillance
TLDR
This work aims to initiate a rigorous and comprehensive review of RPCA-PCP based methods for testing and ranking existing algorithms for foreground detection and investigates how these methods are solved and if incremental algorithms and real-time implementations can be achieved. Expand
Background Recovery by Fixed-Rank Robust Principal Component Analysis
TLDR
Comprehensive tests show that, by fixing the rank of the low-rank matrix to a known value, the fixed-rank algorithm produces more reliable and accurate results than existing low- rank RPCA algorithm. Expand
Double Nuclear Norm-Based Matrix Decomposition for Occluded Image Recovery and Background Modeling
TLDR
This paper presents a method called double nuclear norm-based matrix decomposition (DNMD) for dealing with the image data corrupted by continuous occlusion, which uses a unified low-rank assumption to characterize the real image data and continuous Occlusion. Expand
Handbook of Robust Low-Rank and Sparse Matrix Decomposition: Applications in Image and Video Processing
TLDR
This handbook provides a complete overview of the concepts, theories, algorithms, and applications related to robust low-rank and sparse matrix decompositions for researchers, developers, and graduate students in computer vision, image and video processing, real-time architecture, machine learning, and data mining. Expand
Foreground detection based on low-rank and block-sparse matrix decomposition
TLDR
This paper proposes to use a RPCA method based on low-rank and block-sparse matrix decomposition to achieve foreground detection and Experimental results on different datasets show the pertinence of the proposed approach. Expand
SBMI-LTD: stationary background model initialization based on low-rank tensor decomposition
TLDR
Since, maximum norm regularizer is more robust than nuclear norm against large number of outliers, therefore the proposed extended tensor based decomposition framework with maximum norm provides an accurate estimation of background scene. Expand
A fast tri-factorization method for low-rank matrix recovery and completion
TLDR
This paper proposes a Fast Tri-Factorization (FTF) method to approximate the nuclear norm minimization problem and mitigate the computation cost of performing SVDs, and develops two alternating direction method (ADM) based iterative algorithms for solving the above three problems. Expand
Foreground detection via robust low rank matrix factorization including spatial constraint with Iterative reweighted regression
TLDR
This paper proposes to use a low-rank matrix factorization with IRLS scheme (Iteratively reweighted least squares) and to address in the minimization process the spatial connexity of the pixels and results show the pertinence of the proposed approach. Expand
Robust principal component analysis via capped norms
TLDR
This paper presents a novel non-convex formulation for the RPCA problem using the capped trace norm and the capped l1-norm, and presents two algorithms to solve the non-Convex optimization: one is based on the Difference of Convex functions (DC) framework and the other attempts to solved the sub-problems via a greedy approach. Expand
...
1
2
3
4
5
...