An Intensity-Based Method for the 3-D Motion and Structure Estimation from Binocular Image Sequences

Раздел: Статьи

Luo A.,Burkhardt H

An Intensity-Based Method for the 3-D Motion and Structure Estimation from Binocular Image Sequences

Category:
Keywords: Shape from motion,Stereo and integration,Motion estimation,Piecewise smooth model of 3-D surfaces and Bayesian estimation

abstract:

This paper presents a new algorithm for estimating the 3-D motion and structure from stereo image sequences. In order to overcome the inherent ambiguities of the motion and structure estimation from a monocular image sequence and to improve the performan ce of the binocular stereo methods, both the intensity-based methods are directly integrated. Being different from other methods computing the structure from stereo and motion, this method does not need to match separate monocular optical ows, so that th e high complexity of the algorithm is avoided. Instead of simplified models that are often unreasonable, new models for 3-D piecewise smooth structure and occlusion are put forward for Bayesian estimation. The experiments show that the algorithm is e ect ive and robust to improve the 3-D motion and structure estimation

На статью

Graphics & Media Lab. >> Библиотека | Курсы | Графикон

Верстка, дизайн, программирование Людмила Попова
Выпускающий редактор Дмитрий Ватолин
Подготовка материала Ольга Карпенко