%0 Journal Article %T Multi-model particle filter-based tracking with switching dynamical state to study bedload transport %+ Laboratoire Hubert Curien (LHC) %+ Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (IRSTEA) %+ Erosion torrentielle neige et avalanches (UR ETGR (ETNA)) %A Lafaye de Micheaux, Hugo %A Ducottet, Christophe %A Frey, Philippe %Z [Departement_IRSTEA]Eaux [ADD1_IRSTEA]Hydrosystèmes et risques naturels %< avec comité de lecture %@ 0932-8092 %J Machine Vision and Applications %I Springer Verlag %V 29 %N 5 %P 735-747 %8 2018 %D 2018 %R 10.1007/s00138-018-0925-z %K Detector confidence %K Bedload transport %K Switching dynamical state %K Visual object tracking %K Multiple targets tracking %K Particle filter %Z Computer Science [cs]/Image Processing [eess.IV] %Z Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Journal articles %X 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. %G English %2 https://ujm.hal.science/ujm-01782169/document %2 https://ujm.hal.science/ujm-01782169/file/paper-mva.pdf %L ujm-01782169 %U https://ujm.hal.science/ujm-01782169 %~ UNIV-ST-ETIENNE %~ IOGS %~ CNRS %~ IRSTEA %~ PARISTECH %~ AGREENIUM %~ UDL %~ INRAE %~ ANR %~ ETNA