| Author Name | Affiliation | | LIU Ya-hui | School of Automation,Beijing University of Posts and Telecommunications,Beijing 100876,China | | JIA Qing-xuan | School of Automation,Beijing University of Posts and Telecommunications,Beijing 100876,China | | SUN Han-xu | School of Automation,Beijing University of Posts and Telecommunications,Beijing 100876,China | | SONG Jing-zhou | School of Automation,Beijing University of Posts and Telecommunications,Beijing 100876,China |
|
| Abstract: |
| To solve the problem of wide-baseline stereo image matching based on multiple cameras,the paper puts forward an image matching method of combining maximally stable extremal regions (MSER) with Scale Invariant Feature Transform (SIFT) . It uses MSER to detect feature regions instead of difference of Gaussian. After fitted into elliptical regions,those regions will be normalized into unity circles and represented with SIFT descriptors. The method estimates fundamental matrix and removes outliers by auto-maximum a posteriori sample consensus after initial matching feature points. The experimental results indicate that the method is robust to viewpoint changes,can reduce computational complexity effectively and improve matching accuracy. |
| Key words: image matching scale invariant feature transform maximally stable extremal region wide-baseline |
| DOI：10.11916/j.issn.1005-9113.2010.02.015 |
| Clc Number:TP391.41 |
| Fund: |
