Depth-based detection with region comparison features

Abstract

Most object detection approaches proposed over the years rely on visual features that help to segregate objects from their backgrounds. For instance, segregation may be facilitated by depth features because they provide direct access to the third dimension. Such access enables accurate object-background segregation. Although they provide a rich source of information, depth images are sensitive to background noise. This paper addresses the issue of handling background noise for accurate foreground–background segregation. It presents and evaluates the Region Comparison (RC) features for fast and accurate body part detection. RC features are depth features inspired by the well-known Viola–Jones detector. Their performances are compared to the recently proposed Pixel Comparison (PC) features, which were designed for fast and accurate object detection from Kinect-generated depth images. The results of our evaluation reveal that RC features outperform PC features in detection accuracy and computational efficiency. From these results we may conclude that RC features are to be preferred over PC features to achieve accurate and fast object detection in noisy depth images.