Kayak Tracking using a Direct Lidar Model

Abstract

This paper proposes a direct approach for extended object tracking (EOT) using light detection and ranging (lidar) measurements. The method does not use any clustering operations, but processes the individual laser beams directly in an extended Kalman filter (EKF), and resolves data association by means of techniques reminiscent of the probabilistic data association filter (PDAF). The method is particularly tailored to tracking of kayaks, and parameterizes the shape of the kayak as a stick whose length is part of the state vector. The proposed method is evaluated through a simulation study and tested on real lidar data.

Research and Application of Panoramic Visual Perception-Assisted Navigation Technology for Ships

“…Maritime targets mainly include ships, buoys, and reefs. Due to insufficient datasets, current research on the visual perception of maritime targets is mainly focused on ships [8], and small targets such as buoys mainly use LiDAR for perception [9,10]. Few visual perception methods have been developed that can perceive other targets.…”