Robust background modelling using region-based codebooks

Abstract

Dynamic backgrounds and sudden illumination changes are two of the major problems associated with background subtraction techniques. In this paper, we present a novel approach to background subtraction that addresses both of these challenges. Based on the work of Kim et al., we develop an improved codebook background modelling and subtraction technique. We utilise image segmentation on the background image and model the background with a codebook for each pixel along with a pseudo background layer. We perceive background motion as an occlusion of one background layer by a nearby background layer. In other words, sliding of one background layer over a neighbouring layer causes background motion and will hence result in false segmentation. We present our approach of codeword spreading across layer boundaries to handle background motion and further propose a two-step update of the background codebook to handle both sudden and gradual illumination changes. Experimental results confirm the efficacy of our technique.