Title :
An Algorithm for Image Match Propagation
Author :
Liu, Rong ; He, Liang ; Lu, Kaiyun
Author_Institution :
Dept. of Surveying, East China Inst. of Technol. Fuzhou, Fuzhou, China
Abstract :
Stereo matching is an important part of 3D reconstruction. This paper proposes an improved match propagation algorithm. Firstly, the feature points are extracted and matched by SIFT algorithm then they are used as seed points for the image match propagation in neighborhood. Secondly, these dense correspondences are re-sampled to quasi-dense correspondences. Finally, the mismatched points and outliers are eliminated by epipolar constraint. Experiments show that this improved algorithm can be applied in the similar structure of images with great change of depth.
Keywords :
feature extraction; image matching; image reconstruction; stereo image processing; transforms; 3D reconstruction; SIFT algorithm; epipolar constraint; feature point extraction; feature point matching; mismatched point elimination; outlier elimination; quasidense correspondences; scale-invariant feature transform; seed points; stereo image match propagation algorithm; Computer vision; Feature extraction; Image reconstruction; Reliability; Stereo image processing; Three dimensional displays; SIFT algorithm; epipolar constraint; propagation; quasi-dense matching;
Conference_Titel :
Industrial Control and Electronics Engineering (ICICEE), 2012 International Conference on
Conference_Location :
Xi´an
Print_ISBN :
978-1-4673-1450-3
DOI :
10.1109/ICICEE.2012.203
