Adaptive eigen-backgrounds for object detection

Rymel, J.; Renno, J.; Greenhill, D.; Orwell, James; Jones, Graeme A.

doi:10.1109/icip.2004.1421436

Cited by 28 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, foreground segmentation is accomplished by computing the difference between the input image and its reconstruction. In the same idea, many improvements of SL-PCA [10] were developed to be more robust and fast [33][34][35][36][37][38][39][40][41][42][43][44][45]. In the same category, Yamazaki et al [30] and Tsai et al [46] have used an Independent Component Analysis (SL-ICA).…”

Section: Fig (4) Dynamic Backgroundsmentioning

confidence: 99%

“…These approaches can be divided into improvements and variants of PCA. The improvements consist to enhance the adaptation and the robustness by using incremental and robust PCA algorithms [33][34][35][36][37][38][39][40][41][42][43][44][45]. The variants consist to use an other subspace learning algorithms as the Independent Component Analysis (ICA) [30,46], Incremental Non-negative Matrix Factorization (INMF) [31,47] and Incremental Rank-(R 1 ,R 2 ,R 3 ) Tensor (IRT) [32].…”

Section: Fig (4) Dynamic Backgroundsmentioning

confidence: 99%

See 1 more Smart Citation

Subspace Learning for Background Modeling: A Survey

Bouwmans¹

2010

CSENG

View full text Add to dashboard Cite

Background modeling is often used to detect moving object in video acquired by a fixed camera. Recently, subspace learning methods have been used to model the background in the idea to represent online data content while reducing dimension significantly. The first method using Principal Component Analysis (PCA) was proposed by Oliver et al.[1] and a representative patent using PCA concerns the detection of cars and persons in video surveillance [2]. Numerous improvements and variants were developed over the recent years. The purpose of this paper is to provide a survey and an original classification of these improvements. Firstly, we classify the improvements of the PCA in term of strategies and the variants in term of the used subspace learning algorithms. Then, we present a comparative evaluation of the variants and evaluate them with the state-of-art algorithms (SG, MOG, and KDE) by using the Wallflower dataset.

show abstract

Section: Fig (4) Dynamic Backgroundsmentioning

confidence: 99%

Section: Fig (4) Dynamic Backgroundsmentioning

confidence: 99%

Subspace Learning for Background Modeling: A Survey

Bouwmans¹

2010

CSENG

View full text Add to dashboard Cite

show abstract

“…Others [150,96] proposed PCA methods with computationally efficient background updating scheme, while Doug et al [36] proposed illumination invariant approach based on a multi-subspace PCA, each subspace representing different lighting conditions. Instead of the conventional background and foreground definition, Porikli [136] decomposes a image into "intrinsic" background and foreground images.…”

Section: -5mentioning

confidence: 99%

Background Subtraction on Embedded Hardware

Jodoin¹,

Pierard

Wang³

et al. 2014

Background Modeling and Foreground Detection for Video Surveillance

View full text Add to dashboard Cite

“…In this context, some authors proposed different algorithms of incremental PCA. The incremental PCA proposed by Rymel et al [7] need less computation but the background image is contamined by the foreground object. To solve this, Li et al [8] proposed an incremental PCA which is robust in presence of outliers.…”

Section: Introductionmentioning

confidence: 99%

Background Modeling via Incremental Maximum Margin Criterion

Marghes

Bouwmans

2011

Computer Vision – ACCV 2010 Workshops

View full text Add to dashboard Cite

Abstract. Subspace learning methods are widely used in background modeling to tackle illumination changes. Their main advantage is that it doesn't need to label data during the training and running phase. Recently, White et al. [1] have shown that a supervised approach can improved significantly the robustness in background modeling. Following this idea, we propose to model the background via a supervised subspace learning called Incremental Maximum Margin Criterion (IMMC). The proposed scheme enables to initialize robustly the background and to update incrementally the eigenvectors and eigenvalues. Experimental results made on the Wallflower datasets show the pertinence of the proposed approach.

show abstract

Adaptive eigen-backgrounds for object detection

Cited by 28 publications

References 8 publications

Subspace Learning for Background Modeling: A Survey

Subspace Learning for Background Modeling: A Survey

Background Subtraction on Embedded Hardware

Background Modeling via Incremental Maximum Margin Criterion

Contact Info

Product

Resources

About