Recognition of Object Surfaces from Stereo Data using a Three-Dimensional Markov Random Field Model

H. Takizawa and S. Yamamoto (Japan)

Keywords

Stereo vision, Surface reconstruction, Three-dimensional Markov Random Field model, Fitness, Interrelation

Abstract

In the present paper, we propose a method for reconstruct ing the surfaces of objects from stereo data. Both the fitness of stereo data to surfaces and interrelation between the sur faces are defined in the framework of a three-dimensional (3-D) Markov Random Field (MRF) model. The surface reconstruction is accomplished by searching for the most likely state of the MRF model. In addition, experimental results obtained for an actual scene are shown.

Important Links:



Go Back