Real-time particle filtering with heuristics for 3D motion capture by monocular vision

Abstract : Particle filtering is known as a robust approach for motion tracking by vision, at the cost of heavy computation in the high dimensional pose space. In this work, we describe a number of heuristics that we demonstrate to jointly improve robustness and real-time for motion capture. 3D human motion capture by monocular vision without markers can be achieved in real-time by registering a 3D articulated model on a video. First, we search the high-dimensional space of 3D poses by generating new hypotheses (or particles) with equivalent 2D projection by kinematic flipping. Second, we use a semi-deterministic particle prediction based on local optimization. Third, we deterministically resample the probability distribution for a more efficient selection of particles. Particles (or poses) are evaluated using a match cost function and penalized with a Gaussian probability pose distribution learned off-line. In order to achieve real-time, measurement step is parallelized on GPU using the OpenCL API. We present experimental results demonstrating robust real-time 3D motion capture with a consumer computer and webcam
Complete list of metadatas
Contributor : Médiathèque Télécom Sudparis & Institut Mines-Télécom Business School <>
Submitted on : Thursday, May 12, 2016 - 10:31:24 AM
Last modification on : Monday, June 17, 2019 - 5:04:07 PM

Links full text



David Antonio Gomez Jauregui, Patrick Horain, Manoj Kumar Rajagopal, Senanayak Sesh Kumar Karri. Real-time particle filtering with heuristics for 3D motion capture by monocular vision. MMSP 2010 : IEEE International Workshop on Multimedia Signal Processing, Oct 2010, Saint-Malo, France. pp.139 - 144, ⟨10.1109/MMSP.2010.5662008⟩. ⟨hal-01314817⟩



Record views