Multiscale background modelling and segmentation

Abstract

A new multiscale approach to motion based segmentation of objects in video sequences is presented. While image features extracted at multiple scales are commonly used within the pattern recognition community, they have seldom been employed for background modelling and subtraction. The paper describes a methodology for maintaining an explicit background model at multiple scales. Biological inspiration is used to contrive simple, yet effective mechanisms for feature extraction, incorporation of information across multiple scales and segmentation. Results of experiments conducted using sequences from the domain of traffic surveillance are presented in the paper. They suggest that the proposed method is able to achieve good segmentation results. In addition, the evaluated variant of a multiscale segmentation algorithm is far less computationally intensive, able to achieve processing of higher frame rates in real time and requires an order of magnitude less memory resources than the commonly-used approach compared against.