Automatic kernel width selection for neural network based video object segmentation

Abstract

Background modelling Neural Networks (BNN5) represent an approach to motion based object segmentation in video sequences. BNNs are probabilistic classifiers with nonparametric, kernel-based estimation of the underlying probability density functions. The paper presents an enhancement of the methodology, introducing automatic estimation and adaptation of the kernel width. The proposed enhancement eliminates the need to determine kernel width empirically. The selection of a kernel-width appropriate for the features used for segmentation is critical to achieving good segmentation results. The improvement makes the methodology easier to use and more adaptive, and facilitates the evaluation of the approach.