Abstract

In this paper, we propose a new framework for 3D tracking by detection based on fully volumetric representations. On one hand, 3D tracking by detection has shown robust use in the context of interaction (Kinect) and surface tracking. On the other hand, volumetric representations have recently been proven effificient both for building 3D features and for addressing the 3D tracking problem. We leverage these benefifits by unifying both families of approaches into a single, fully volumetric tracking-by-detection framework. We use a centroidal Voronoi tessellation (CVT) representation to compactly tessellate shapes with optimal discretization, construct a feature space, and perform the tracking according to the correspondences provided by trained random forests. Our results show improved tracking and training computational effificiency and improved memory performance. This in turn enables the use of larger training databases than state of the art approaches, which we leverage by proposing a cross-tracking subject training scheme to benefifit from all subject sequences for all tracking situations, thus yielding better detection and less overfifitting.