Modeling of Video Sequences by Gaussian Mixture: Application in Motion Estimation by Block Matching Method. (30th May 2010)

• Record Type: Journal Article
• Authors: Boudlal Boudlal, Abdenaceur Abdenaceur; Nsiri Nsiri, Benayad Benayad; Aboutajdine Aboutajdine, Driss Driss
• Other Names: Cetin Cetin A. Enis A. Enis Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2010(2010)
• Publication Date: 2010-05-30
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2010/210937
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : This article investigates a new method of motion estimation based on block matching criterion through the modeling of image blocks by a mixture of two and three Gaussian distributions. Mixture parameters (weights, means vectors, and covariance matrices) are estimated by the Expectation Maximization algorithm (EM) which maximizes the log-likelihood criterion. The similarity between a block in the current image and the more resembling one in a search window on the reference image is measured by the minimization of Extended Mahalanobis distance between the clusters of mixture. Performed experiments on sequences of real images have given good results, and PSNR reached 3 dB.