Tracking a Varying Number of People with a Visually-Controlled Robotic Head

Yutong Ban 1 Xavier Alameda-Pineda 1 Fabien Badeig 1 Sileye Ba 2, 1 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Multi-person tracking with a robotic platform is one of the cornerstones of human-robot interaction. Challenges arise from occlusions, appearance changes and a time-varying number of people. Furthermore, the final system is constrained by the hardware platform: low computational capacity and limited field-of-view. In this paper, we propose a novel method to simultaneously track a time-varying number of persons in three-dimension and perform visual servoing. The complementary nature of the tracking and visual servoing enables the system to: (i) track multiple objects while compensating for large ego-movements and (ii) visually-control the robot to keep the person-of-interest in the field-of-view. We implement a variational approximation allowing us to effectively solve the inference problem through the use of closed-form solutions. Importantly, this leads to a computationally light system that runs at 10 FPS. The experiments on the NAO-MPVS dataset confirm the importance of using motor information when tracking multiple persons.
Type de document :
Communication dans un congrès
IEEE/RSJ International Conference on Intelligent Robots and Systems, Sep 2017, Vancouver, Canada. IEEE, pp.4144-4151, 2017, 〈http://www.iros2017.org/〉. 〈10.1109/IROS.2017.8206274〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-01542987
Contributeur : Team Perception <>
Soumis le : lundi 31 juillet 2017 - 17:19:53
Dernière modification le : jeudi 24 mai 2018 - 18:05:33

Identifiants

Collections

Citation

Yutong Ban, Xavier Alameda-Pineda, Fabien Badeig, Sileye Ba, Radu Horaud. Tracking a Varying Number of People with a Visually-Controlled Robotic Head. IEEE/RSJ International Conference on Intelligent Robots and Systems, Sep 2017, Vancouver, Canada. IEEE, pp.4144-4151, 2017, 〈http://www.iros2017.org/〉. 〈10.1109/IROS.2017.8206274〉. 〈hal-01542987v2〉

Partager

Métriques

Consultations de la notice

794

Téléchargements de fichiers

342