Gaussian Mixture Model in Improved HLS Color Space for Human Silhouette Extraction

Setiawan, Nurul Arif; Hong, Sheng; Kim, Jang-Woon; Lee, Chil-Woo

doi:10.1007/11941354_76

Cited by 25 publications

(27 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In order to increase the model adaptation capabilities, each image point is characterized by a mixture of (typically 3-5) Gaussians. A number of Gaussians can either be constant (defined when the algorithm is run) or it can vary depending on the scene characteristics [25]. Regardless of the implementation, this approach allows for handling situations such as when an object is left or taken from the scene.…”

Section: Gaussian Mixture Modelmentioning

confidence: 99%

“…KaewTraKulPong and Bowden [12] used an expectation maximization approach for improving the learning rate of the background model. Setiawan et al [25] applied the GMM method to an improved hue-luminance-saturation color space in order to achieve better sensitivity to color changes. An important work by Zivkovic and Van der Heijden [33] resulted in an improved adaptation of the GMM model to changes in the analyzed scene by automatic selection of the number of Gaussian components.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Parallel implementation of background subtraction algorithms for real-time video processing on a supercomputer platform

Szwoch

Ellwart

Czyżewski

2012

J Real-Time Image Proc

View full text Add to dashboard Cite

Results of evaluation of the background subtraction algorithms implemented on a supercomputer platform in a parallel manner are presented in the article. The aim of the work is to chose an algorithm, a number of threads and a task scheduling method, that together provide satisfactory accuracy and efficiency of a real-time processing of high-resolution camera images, maintaining the cost of resources usage at a reasonable level. Two selected algorithms: the Gaussian mixture models and the Codebook, are presented and their computational complexity is discussed. Various approaches to the parallel implementation, including assigning the image pixels to threads, the task scheduling methods and the thread management systems, are presented. The experiments were performed on a supercomputer cluster, using a single machine with 12 physical cores. The accuracy and performance of the implemented algorithms were evaluated for varying image resolutions and numbers of concurrent processing threads. On a basis of the evaluation results, an optimal configuration for the parallel implementation of the system for real-time video content analysis on a supercomputer platform was proposed.

show abstract

Section: Gaussian Mixture Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Parallel implementation of background subtraction algorithms for real-time video processing on a supercomputer platform

Szwoch

Ellwart

Czyżewski

2012

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…So, some authors prefer to use other color space which are more robust to these critical situations and have independent components. These color spaces are the following ones: Normalized RGB [115,116], YUV [88,100,117], HSV [100], HSI [148], Luv [101], Improved HLS Color Space [118]. Kristensen et al [119] have studied the influence of the seven color spaces.…”

Section: Color Features: In the Original Mog Stauffer Andmentioning

confidence: 99%

Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey

Bouwmans¹,

Baf²,

Vachon³

2010

CSENG

163

View full text Add to dashboard Cite

Abstract:Mixture of Gaussians is a widely used approach for background modeling to detect moving objects from static cameras. Numerous improvements of the original method developed by Stauffer and Grimson [1] have been proposed over the recent years and the purpose of this paper is to provide a survey and an original classification of these improvements. We also discuss relevant issues to reduce the computation time. Firstly, the original MOG are reminded and discussed following the challenges met in video sequences. Then, we categorize the different improvements found in the literature. We have classified them in term of strategies used to improve the original MOG and we have discussed them in term of the critical situations they claim to handle. After analyzing the strategies and identifying their limitations, we conclude with several promising directions for future research.

show abstract

“…In the last decade, several studies have attempted to improve the performance of GMM in environments with multiple dimming and high condensation background. Initial ideas focused on substitution of using color characteristics [2] Setiawan et al [24]or infrared camera [23]. Hybrid models such as GMM and K-means [3], GMM and fuzzy logic [1], Markov Random Fields [22],GMM and adaptive background [9,25], have been proposed to overcome GMM drawbacks.…”

Section: Introductionmentioning

confidence: 99%

Improved Parameters Updating Algorithm for the Detection of Moving Objects

Farou

Séridi

Akdag

2015

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Gaussian Mixture Model in Improved HLS Color Space for Human Silhouette Extraction

Cited by 25 publications

References 7 publications

Parallel implementation of background subtraction algorithms for real-time video processing on a supercomputer platform

Parallel implementation of background subtraction algorithms for real-time video processing on a supercomputer platform

Background Modeling using Mixture of Gaussians for Foreground Detection - A Survey

Improved Parameters Updating Algorithm for the Detection of Moving Objects

Contact Info

Product

Resources

About