Toward a real-time tracking of dense point-sampled geometry

François Destelle (1) , Céline Roudet (1) , Marc Neveu (1) , Albert Dipanda (1)

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]

In this paper, we address the problem of tracking temporal deformations between two arbitrary densely sampled point-based surfaces. We propose an intuitive and efficient resolution to the point matching problem within two frames of a sequence. The proposed method utilizes two distinct space partition trees, one for each point cloud, which both are defined on a unique discrete space. Our method takes advantage of multi-resolution concerns, voxel adjacency relations, and a specific distance function. Experimental results obtained from both simulated and real reconstructed data sets demonstrate that the proposed method can handle efficiently the tracking process even for very large point clouds. Moreover, our method is easy to implement and very fast, which provides possibilities for real-time tracking applications.

Mots clés: Computer Vision; 3D Processing

Domaines: Autre [cs.OH]

François Destelle, Céline Roudet, Marc Neveu, Albert Dipanda. Toward a real-time tracking of dense point-sampled geometry. 19th IEEE International Conference on Image Processing (ICIP), Sep 2012, Orlando, United States. pp. 381-384, ⟨10.1109/ICIP.2012.6466875⟩. ⟨hal-00811481⟩