Multi-model particle filter-based tracking with switching dynamical state to study bedload transport
Abstract
Multi-object tracking is a difficult problem underlying many computer vision applications. In this work, we focus on bedload sediment transport experiments in a turbulent flow were sediments are represented by small spherical calibrated glass beads. The aim is to track all beads over long time sequences to obtain sediment velocities and concentration. Classical algorithms used in fluid mechanics fail to track the beads over long sequences with a high precision because they incorrectly handle both miss-detections and detector imprecision. Our contribution is to propose a particle filter-based algorithm including a multiple motion model adapted to our problem. Additionally, this algorithm includes several improvements such as the estimation of the detector confidence to account for the lack of precision of the detector. The evaluation was made using two test sequences-one from our experimental setup and one from a simulation created numerically-with their dedicated ground truths. The results show that this algorithm outperforms state-of-the-art concurrent algorithms.
Origin : Files produced by the author(s)
Loading...