1510

From Rendering to Tracking Point-based 3D Models

Christophe Dehais, Geraldine Morin, Vincent Charvillat
IRIT�ENSEEIHT, 2 rue Charles Camichel, B.P. 7122, 31071 Toulouse Cedex, France
Image and Vision Computing, Volume 28, Issue 9, September 2010, Pages 1386-1395 (15 March 2010)

@article{dehais2010rendering,

   title={From rendering to tracking point-based 3D models},

   author={Dehais, C. and Morin, G. and Charvillat, V.},

   journal={Image and Vision Computing},

   volume={28},

   number={9},

   pages={1386–1395},

   issn={0262-8856},

   year={2010},

   publisher={Elsevier}

}

Source Source   

790

views

This paper adds to the abundant visual tracking literature with two main contributions. First we illustrate the interest of using Graphic Processing Units (GPU) to support efficient implementations of computer vision algorithms and, secondly, we introduce the use of point-based 3D models as a shape prior for real-time 3D tracking with a monocular camera. The joint use of point-based 3D models together with GPU allows to adapt and simplify an existing tracking algorithm originally designed for triangular meshes. Point-based models are of particular interest in this context because they are the direct output of most laser scanners. We show that state-of-the-art techniques developed for point-based rendering can be used to compute in real-time intermediate values required for visual tracking. In particular apparent motion predictors at each pixel are computed in parallel and novel views of the tracked object are generated online to help wide-baseline matching. Both computations derive from the same general surface splatting technique which we implement, along with other low-level vision tasks, on the GPU, leading to a real-time tracking algorithm.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: