Background subtraction based on modified online robust principal component analysis

Han, Guoqiang; Wang, Jinkuan; Xi, Cai

doi:10.1007/s13042-016-0562-7

Cited by 15 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To save the time of generating the histogram, the PCA is introduced to make the image parameter handler much simpler. It aims to change the multiple indices to the fewer comprehensive values and to transform the high‐dimensional space into low‐dimensional space [13].…”

Section: Methodsmentioning

confidence: 99%

Improved GMM‐based method for target detection

Zhao

Guo-dong

et al. 2020

IET Networks

View full text Add to dashboard Cite

The Gaussian mixture model (GMM) is prone to large-scale misdetection in the static case where the background and foreground have similar colours. This study presents an improved GMM method to solve this problem. First, the principal component analysis is used to transform the high-dimensional space into the low-dimensional one with three colour channels, which aims to reduce runtime. Then, the images are processed by GMM to obtain the foreground areas. At the same time, the mean and difference of pixel features in red, green and blue and hue, saturation and value (HSV) colour models are calculated to analyse the similar-coloured components. The areas with similar colours are classified in this process, and thus the foreground is separated from similar-coloured background. Then, all of the extracted areas are targets. The experimental results show that the presented method identified the target areas with high accuracy and high efficiency. Compared with conventional GMM, the presented method obtained the detection-accuracy improvement by about 6% on average.

show abstract

Section: Methodsmentioning

confidence: 99%

Improved GMM‐based method for target detection

Zhao

Guo-dong

et al. 2020

IET Networks

View full text Add to dashboard Cite

show abstract

“…This section describes the fast principal component analysis method, focusing on the incremental PCP algorithm [24,25] (which, in turn, is based on [26], which is used to improve the classification modeling of background video is a ubiquitous pre-processing step in many computer vision applications used to detect moving objects in digital video.…”

Section: Robust Principal Component Analysis (Rpca)mentioning

confidence: 99%

A Hybrid Approach for Moving Object Detection Using TV-L1 Features and RPCA–MOG

2023

IJIES

View full text Add to dashboard Cite

Robust Principal Component Analysis (RPCA) has recently been active everywhere for dimension reduction in image processing, display and pattern recognition. Methods based on low-rank sparse representations, which make some specific significant assumptions, have recently received a lot of attention in background modelling. Meanwhile, a powerful analysis framework is needed to handle background areas or foreground motion at various scales. this paper presents a hybrid approach along with total variation L1 (TV-L1) features and reproductive RPCA model in low rank background subtraction modelling and sparse matrix with mixture of Gaussians (MoG) as foreground modelling. The hybrid structure with TV-L1 features imposes a hierarchical RPCA on the singular values of the low-rank component and MOG sparsity indicators. The proposed work was evaluated on the CDnet2014 (ChangeDetection.net) dataset, obtained result as accuracy was 92.9%, 86.7% 95.7% for Highway, Escalator, and Indoor respectively. The proposed method is compared with traditional methods and obtained relative reconstruction error is 0.01529 as a lower side.

show abstract

“…One of the important reasons for the poor practical performance in such scenes is that most of the current approaches are pixellevel [3][4][5][6][7][8][9][10][11][12][13][14][15][16], and construct background models of observed scenes as sets of independent pixel processes, thereby overlooking the spatial correlations between pixels. To alleviate this problem, many region-level methods have been proposed to model spatial structures of scenes, including a joint domain-range representation of neighboring pixels [17], the use of spatiotemporal frameworks [18][19][20], block-wise models [21,22], graph learning methods [23], region-based Mixture of Gaussians (RMoG) [24,25], and frame-based methods [26,27]. Generally, methods in this category take into account the spatial connections between neighboring pixels to refine the raw pixel level classification.…”

Section: Introductionmentioning

confidence: 99%

Background Subtraction Via Regional Multi-Feature-Frequency Model in Complex Scenes

Lei

et al. 2022

SSRN Journal

View full text Add to dashboard Cite

Background subtraction based on modified online robust principal component analysis

Cited by 15 publications

References 45 publications

Improved GMM‐based method for target detection

Improved GMM‐based method for target detection

A Hybrid Approach for Moving Object Detection Using TV-L1 Features and RPCA–MOG

Background Subtraction Via Regional Multi-Feature-Frequency Model in Complex Scenes

Contact Info

Product

Resources

About