Segmentation of human body parts in video frames based on intrinsic distance

Abstract

We propose an intrinsic-distance based segmentation approach for segmenting human body parts in video frames. First, since the human body can be seen as a set of articulated parts, we utilize the moving articulated attributes to identify body part candidate regions automatically. The candidate regions and the background candidate regions are generated by voting and assigned to the spatiotemporal volume, which is comprised of frames of the video. Then, the intrinsic distance is used to estimate the boundaries of each body part. Our intrinsic distance-based segmentation technique is applied in the spatiotemporal volume to extract the optimal boundaries of the intrinsic distance in a video and obtain segmented frames from the segmented volume. The segmented results show that the proposed approach can tolerate incomplete and imprecise candidate regions because it provides temporal continuity. Furthermore, it can reduce over growing in the original intrinsic distance-based algorithm, since it can handle ambiguous pixels. We expect that this research can provide an alternative to segmenting a sequence of body parts in a video.