Video Object Segmentation Using Multiple Features

Abstract

In this paper we present an algorithm for semi-automatic object extraction from video sequences using multiple features. This work is part of an ongoing effort to study video segmentation using multiple features, and the relative contribution of each one of them. For this reason, the algorithm here presented will be very simple and made up from of the shelf algorithms. We will show that even with a simple algorithm, with the right steps, we can successfully segment video objects in moderate complex sequences.