|
|||||
|
|
Multi-scale sparse feature point correspondence by graph cuts |
|
| Authors: | ZHANG Hong MU Ying YOU YuHu & LI JunWei Image Processing Center Beihang University Beijing China Beijing Research Institute of Special Electromechanical Technology Beijing National Key Laboratory on Optical Features of Environment Target Beijing |
| Affiliation: | ZHANG Hong 1,MU Ying 1,YOU YuHu 2 & LI JunWei 3 1 Image Processing Center,Beihang University,Beijing 100191,China,2 Beijing Research Institute of Special Electromechanical Technology,Beijing 100012,3 National Key Laboratory on Optical Features of Environment , Target,Beijing 100854 |
| Abstract: | This paper presents a global stereo sparse matching technique based on graph cut theory to obtain accurate correspondence of stereo point pair in vision measurement applications.First, in order to obtain accurate location of feature points, a new multi-scale corner detection algorithm is proposed where wavelet coefficients are used to determine feature points by calculating an auto-correlation matrix.A sparse graph is constructed based on the feature points according to the graph cut theory.Then, the featur... |
| Keywords: | multi-scale feature point extraction graph cut theory stereo correspondence sparse point matching |
| 本文献已被 CNKI 等数据库收录！ | |