Detection of thrown objects using ToF cameras

Abstract

This paper deals with the issue of thrown or dropped object detection as an application of the 3D time-of-flight (ToF) camera. The use of distance information provided by the ToF camera makes the segmentation step straight forward. Then, instead of high computational motion detection and estimation algorithms, mainly a labeling and tracking procedure is used. This approach provides real time low complexity object detection and trajectory estimation. The method is validated on 50 video sequences taken with the ToF camera.