Proceedings-Artikel
A Precise Tracking Algorithm Based on Raw Detector Responses and a Physical Motion Model
Oliver Birbach; Udo Frese
In: Proceedings of the IEEE International Conference on Robotics and Automation. IEEE International Conference on Robotics and Automation (ICRA-12), May 6-10, Karlsruhe, Germany, IEEE, 2013.
Abstract
We present a method to simultaneously track multiple objects which are subject to physical motion and can be evaluated through raw detector responses in video. Due to their two-staged design, popular tracking-by-detection approaches lack precision in the estimated trajectories due to detector inefficiencies, e.g., lighting, deformation or background clutter. Instead of separating the tasks of detection and tracking, we propose to integrate both in a single probabilistic objective function for determining the object’s states in a sequence. Both thereby support each other accounting for detection inefficiencies and leading to a robust and precise single target tracker. Based on this, we extend it to multiple targets by solving the problem of determining trajectory limits and sorting out any multiple target ambiguities probabilistically. We apply our method to the task of tracking thrown balls with the goal of accurate trajectory prediction for the task of ball catching with a humanoid robot. Our results show improved tracking accuracy wrt to ground truth on average by around 18%, which is dominated by increased accuracy at the beginning of the trajectory.