17 August 1994 Automatic image-matching algorithm based on wavelet decomposition
Author Affiliations +
Proceedings Volume 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision; (1994) https://doi.org/10.1117/12.182855
Event: Spatial Information from Digital Photogrammetry and Computer Vision: ISPRS Commission III Symposium, 1994, Munich, Germany
Abstract
The matching of stereo images is a key problem for digital photogrammetry. This paper presents an automatic image matching algorithm based on the wavelet decomposition. The matching strategy consists of two parts. First a rotating and wavelets weighted Laplacian variance coarse matching algorithm is operated on each level of image pyramids, which are generated by the orthogonal wavelet decomposition, to obtain a matching precision within 2 pixels. The wavelets' coefficients are used as the weight function in similarity measure. Second the well known least squares matching is performed to obtain the higher matching precision based on the results of the coarse matching. The potential of this matching method is shown in the experimental results of Mars remote sensing imagery.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiuguang Zhou, Egon Dorrer, "Automatic image-matching algorithm based on wavelet decomposition", Proc. SPIE 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision, (17 August 1994); doi: 10.1117/12.182855; https://doi.org/10.1117/12.182855
PROCEEDINGS
10 PAGES


SHARE
Back to Top