L2-SIFT: SIFT feature extraction and matching for large images in large-scale aerial photogrammetry

Publisher:
Elsevier B.V.
Publication Type:
Journal Article
Citation:
ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 91 pp. 1 - 16
Issue Date:
2014-01
Full metadata record
Files in This Item:
Filename Description Size
ThumbnailISPRS 2014 Yanbiao.pdfPublished Version5.89 MB
Adobe PDF
ThumbnailL2SIFT-ISPRS.pdfAccepted Manuscript Version12 MB
Adobe PDF
The primary contribution of this paper is an efficient feature extraction and matching implementation for large images in large-scale aerial photogrammetry experiments. First, a Block-SIFT method is designed to overcome the memory limitation of SIFT for extracting and matching features from large photogrammetric images. For each pair of images, the original large image is split into blocks and the possible corresponding blocks in the other image are determined by pre-estimating the relative transformation between the two images. Because of the reduced memory requirement, eatures can be extracted and matched from the original images without down-sampling. Next, a red-black tree data structure is applied to create a feature relationship to reduce the search complexity when matching tie points. Meanwhile, tree key exchange and segment matching methods are proposed to match the tie points along-track and across-track. Finally, to evaluate the accuracy of the features extracted and matched from the proposed L2-SIFT algorithm, a bundle adjustment with parallax angle feature parametrization (ParallaxBA) is applied to obtain the Mean Square Error (MSE) of the feature reprojections, where the feature extraction and matching result is the only information used in the nonlinear optimisation system. Seven different experimental aerial photogrammetric datasets are used to demonstrate the efficiency and validity of the proposed algorithm. It is demonstrated that more than 33 million features can be extracted and matched from the Taian dataset with 737 images within 21h using the L2-SIFT algorithm. In addition, the ParallaxBA involving more than 2.7 million features and 6 million image points can easily converge to an MSE of 0.03874. The C/C++ source code for the proposed algorithm is available at http://services.eng.uts.edu.au/~sdhuang/research.htm.
Please use this identifier to cite or link to this item: