Region-Level Motion-Based Foreground Detection with Shadow Removal Using MRFs

Huang, Shih-Shinh; Fu, Li‐Chen; Hsiao, Pei‐Yung

doi:10.1007/11612032_88

Cited by 5 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, regions which have the same classification label and similar colors are merged to derive a more consistent foreground mask. Experimental results [210] on gradual illumination changes and shadows demonstrate the robustness of this method, but the computational complexity of the technique has not been mentioned. In similar studies, Huang et al [213][211][214] used motion information captured through the difference of consecutive frames to model the background in stationary areas.…”

Section: Motion Featuresmentioning

confidence: 99%

See 1 more Smart Citation

On the Role and the Importance of Features for Background Modeling and Foreground Detection

Bouwmans¹,

Silva²,

Marghes³

et al. 2016

Preprint

View full text Add to dashboard Cite

Background modeling has emerged as a popular foreground detection technique for various applications in video surveillance. Background modeling methods have become increasing efficient in robustly modeling the background and hence detecting moving objects in any visual scene. Although several background subtraction and foreground detection have been proposed recently, no traditional algorithm today still seem to be able to simultaneously address all the key challenges of illumination variation, dynamic camera motion, cluttered background and occlusion. This limitation can be attributed to the lack of systematic investigation concerning the role and importance of features within background modeling and foreground detection. With the availability of a rather large set of invariant features, the challenge is in determining the best combination of features that would improve accuracy and robustness in T. Bouwmans Lab. MIA,

show abstract

Section: Motion Featuresmentioning

confidence: 99%

“…-Motion features: Motion features are usually obtained via optical flow but with the limitation of the computational time. Motion features allow the model to deal with irrelevant background motion and clutter [493][213] [212][211] [214][210] [209] (See Section 8).…”

Section: -Stereo Featuresmentioning

confidence: 99%

On the Role and the Importance of Features for Background Modeling and Foreground Detection

Bouwmans¹,

Silva²,

Marghes³

et al. 2016

Preprint

View full text Add to dashboard Cite

show abstract

“…Many proposed algorithms in the literature (Cucchiara et al , 2003; Wang et al , 2006) try to solve this problem at a pixel level by analysing the spectral content of each individual point with the undesirable resulting effect to remove just a few shadow points. Recently, several ratio‐based approaches for shadow elimination have been proposed (Yang et al , 2008; Rosito, 2009); moreover, a Markov random field‐based spatial relationship has been recently used for shadow removing (Huang et al , 2006; Wang et al , 2006). However, they usually do not remove all the shadow points, but only some of them.…”

Section: Shadow Removingmentioning

confidence: 99%

Real‐time smart surveillance using motion analysis

et al. 2010

View full text Add to dashboard Cite

In the last years, smart surveillance has been one of the most active research topics in computer vision because of the wide spectrum of promising applications. Its main point is about the use of automatic video analysis technologies for surveillance purposes. In general, a processing framework for smart surveillance consists of a preliminary motion detection step in combination with high-level reasoning that allows automatic understanding of evolutions of observed scenes. In this paper, we propose a surveillance framework based on a set of reliable visual algorithms that perform different tasks: a motion analysis approach that segments foreground regions is followed by three procedures, which perform object tracking, homographic transformations and edge matching, in order to achieve the real-time monitoring of forbidden areas and the detection of abandoned or removed objects. Several experiments have been performed on different real image sequences acquired from a Messapic museum (indoor context) and the nearby archaeological site (outdoor context) to demonstrate the effectiveness and the flexibility of the proposed approach.

show abstract

“…In Porikli and Thornton's work [4], they apply a shadow weak classifier as a pre-filter first, then model the selected shadow pixels using multivariate Gaussians. Huang et al [5] first segmented each frame into regions based on motion similarity. The intensities of the shadow regions are assumed to be similar to those of the corresponding background regions by a scale.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Foreground Object Extraction for Real-Time Video Surveillance with Lighting Variations

Zeng

Lai

2007

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07

View full text Add to dashboard Cite

In this paper we present an adaptive foreground object extraction algorithm for real-time video surveillance. The proposed algorithm improves the previous Gaussian mixture background models (GMMs) by applying a two-stage foreground/background classification procedure to remove the undesirable subtraction results due to shadow, automatic white balance, and sudden illumination change. The traditional background subtraction technique usually cannot work well for situations with lighting variations in the scene. In the proposed two-stage classification, an adaptive classifier is applied to the foreground pixels in a pixel-wise manner based on the normalized color and brightness gain information. Secondly, the remaining foreground candidate pixels are grouped into regions and the corresponding background regions are compared to check if they are foreground regions. Experimental results on some real surveillance video are shown to demonstrate the robustness of the proposed adaptive foreground extraction algorithm under a variety of different environments with lighting variations.

show abstract

Region-Level Motion-Based Foreground Detection with Shadow Removal Using MRFs

Cited by 5 publications

References 14 publications

On the Role and the Importance of Features for Background Modeling and Foreground Detection

On the Role and the Importance of Features for Background Modeling and Foreground Detection

Real‐time smart surveillance using motion analysis

Adaptive Foreground Object Extraction for Real-Time Video Surveillance with Lighting Variations

Contact Info

Product

Resources

About