Joint Detection and Tracking of Occluded Target Using Lidar

Abstract

Target tracking in transportation vehicles is important from both civilian and military perspectives. Objects that obstruct the sensor's field of view create occlusion regions in target tracking. The literature has developed dynamic solutions to address the problems arising from the target entering the sensor's occlusion spot behind an obstacle and detecting occlusion regions. In this study, target tracking using lidar is performed with a stationary vehicle obstacle and a moving vehicle in the Gazebo simulation environment. A solution is proposed for velocity disturbances during entry into the occlusion region in this environment. After comparing the performance of target tracking filters in the simulation environment, the algorithms are tested in a real-world scenario where a similar simulation environment is set up. Two different Bernoulli filters are implemented based on the nearest neighbor and probabilistic data association mechanisms. The results are evaluated using the Optimal Sub-Pattern Assignment metrics.