Depth Fingerprinting for Obstacle Tracking using 3D Point Cloud

We present a method for automatic detection and tracking of obstacles on water surface that uses solely the point cloud obtained from the surroundings of the unmanned surface vehicle (USV). For this purpose, we use a calibrated pair of stereo cameras, affixed to the mast at the front of the USV. Reliable obstacle tracking in outdoor environment is a difficult task, but unlike the monocular approaches, our framework offloads a large part of the problem onto the method that provides a point cloud. In absence of other visual features, our method introduces \emph{depth fingerprint}, a histogram-like feature obtained from the point cloud of an object. The method has been evaluated on the yet unreleased MODD2 dataset and shows promising results, with the depth fingerprinting significantly outperforming tracking based solely on optimal assignment weighted by geometrical distance between object detections (Munkres algorithm). The proposed method is capable of running in real time on board of a small-sized USV.