People Detection and Tracking from a Top-View Position Using a Time-of-Flight Camera

This paper outlines a method for the detection and tracking of people in depth images, acquired with a low-resolution Time-of-Flight (ToF) camera. This depth sensor is placed perpendicular to the ground in order to provide distance information from a top-view position. With usage of intrinsic and extrinsic camera parameters a ground plane is estimated and compared to the measured distances of the ToF sensor in every pixel. Differences to the expected ground plane define foreground information, which is used as regions of interest (ROIs). These regions are analyzed to distinguish persons from other objects by using a matched filter on the height-segmented depth measurements of each ROI. The proposed method separates crowds into individuals and facilitates a multi-object tracking system based on a Kalman filter. Experiments have proven the applicability of the system for different crowding scenarios but also revealed inaccuracies of the detection of people in special cases.