Foreground Detection via IMMC

Introduction

Background subtraction is one of the basic low level operations in video analysis. The aim is to separate static information called “background” from the moving objects called “foreground”. The background needs to be modeled and updated over time to allow robust foreground detection. In this work, we propose the use of a discriminative subspace learning model called incremental maximum margin criterion (IMMC) [1]. The objective is first to enable a robust supervised initialization of the background and secondly a robust classification of pixels as background or foreground. Furthermore, IMMC also allows us an incremental update of the eigenvectors and eigenvalues. Experimental results on different datasets demonstrate the performance of this proposed approach in the presence of illumination changes.

Principle

The background subtraction framework that is based on IMMC includes the following stages: (1) Background initialization via MMC using N frames. (2) Foreground detection that consists in classifying pixels as foreground or background. (3) Background maintenance via IMMC to update the background

image. The steps (2) and (3) are executed repeatedly as time progresses.

Reference

[1] J. Yan, B. Zhang, S. Yan, Q. Yang, H. Li, and Z. Chen, “IMMC: incremental maximum margin criterion,” ACM International Conference on Knowledge Discovery and Data Mining, KDD 2004, pages 725–730, 2004.

Publications

Journal

D. Farcas, C. Marghes, T. Bouwmans, “Background Subtraction via Incremental Maximum Margin Criterion: A discriminative approach” , Machine Vision and Applications, Volume 23, Issue 6, pages 1083-1101, October 2012. [pdf]

Conference

C. Marghes, T. Bouwmans, "Background Modeling via Incremental Maximum Margin Criterion", International Workshop on Subspace Methods, ACCV 2010 Workshop Subspace 2010, Queenstown, New Zealand, November 2010. [pdf]

D. Farcas, T. Bouwmans, "Background Modeling via a Supervised Subspace Learning", International Conference on Image, Video Processing and Computer Vision, IVPCV 2010, pages 1-7, Orlando, USA , July 2010. [pdf]