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.
Liste complète des métadonnées

Cited literature [24 references]  Display  Hide  Download
Contributor : Team Perception <>
Submitted on : Monday, July 31, 2017 - 5:19:53 PM
Last modification on : Thursday, May 24, 2018 - 6:05:33 PM




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. pp.4144-4151, ⟨10.1109/IROS.2017.8206274⟩. ⟨hal-01542987v2⟩



Record views


Files downloads