Stereo matching for large-scale high-resolution satellite images using new tiling technique
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Stereo matching has been grabbing the attention of researchers because it plays an important role in computer vision, remote sensing and photogrammetry. Although most methods perform well with small size images, experiments applying them to large-scale data sets under uncontrolled conditions are still lacking. In this paper, we present an empirical study on stereo matching for large-scale high-resolution satellite images. A new method is studied to solve the problem of huge size and memory requirement when dealing with large-scale high resolution satellite images. Integrating the tiling technique with the well-known dynamic programming and coarse-to-fine pyramid scheme as well as using memory wisely, the suggested method can be utilized for huge stereo satellite images. Analyzing 350 points from an image of size of 8192 x 8192, disparity results attain an acceptable accuracy with RMS error of 0.5459. Taking the trade-off between computational aspect and accuracy, our method gives an efficient stereo matching for huge satellite image files.
Abstract
Stereo matching has been grabbing the attention of researchers because it plays an important role in computer vision, remote sensing and photogrammetry. Although most methods perform well with small size images, experiments applying them to large-scale data sets under uncontrolled conditions are still lacking. In this paper, we present an empirical study on stereo matching for large-scale high-resolution satellite images. A new method is studied to solve the problem of huge size and memory requirement when dealing with large-scale high resolution satellite images. Integrating the tiling technique with the well-known dynamic programming and coarse-to-fine pyramid scheme as well as using memory wisely, the suggested method can be utilized for huge stereo satellite images. Analyzing 350 points from an image of size of 8192 x 8192, disparity results attain an acceptable accuracy with RMS error of 0.5459. Taking the trade-off between computational aspect and accuracy, our method gives an efficient stereo matching for huge satellite image files.
참고문헌 (15)
- Vincent Tao, "3D reconstruction methods based on the Rational Function Model", Photogrammetric Enginerring & Remote Sensing, 68(7), pp.705~771 (2002)
- Barbara Zitová, "Image registration methods : a survey", Image and Vision Computing, 21, pp.977~1000 (2003)
- G. Gupta, "Region growing stereo matching method for 3D building reconstruction", Int. J Computational Vision and Robotics, 2(1), pp.89~98 (2011)
- Hae-Yeoun Lee, "Extraction of digital elevation models from satellite stereo images through stereo matching based on epipolarity and scene geometry", Image and Vision Computing, 21, pp.789~706 (2003)
- Nalpantidis Lazaros, "Review of stereo vision algorithm : From software to hardware", International Journal of Optomechatronics, 2(4), pp.435~462 (2008)
- Zhen Xiong, "A novel interest-point-matching algorithm for high-resolution satellite images", IEEE Transaction on Geoscience and Remote Sensing, 47(12), pp.4189~4200 (2009)
- Changming Sun, "Fast stereo matching using rectangular subregioning and 3D maximum-surface techniques", International Journal of Computer Vision, 47, pp.99~117 (2002)
- Multi-Resolution Rectangular Subregioning stereo matching using fast correlation and dynamic programming techniques, "Changming Sun", CMIS, ~, pp.Report No. 98 (1998), 246
- Arturo Donate, "Efficient path-based stereo matching with subpixel accuracy", IEEE Transactions on Systems, Man, and Cybernetics, 41(1), pp.183~195 (2011)
- Carlos Leung, "Iterated dynamic programming and quadtree subregioning for fast stereo matching", Image and Vision Computing, 26, pp.1371~1383 (2008)
- Andreas Geiger, "Efficient large-scale stereo matching", Proceeding of the 10th Asian conference on Computer vision, pp.25~38 (2010)
- Daniel Scharstein, "A taxonomy and evaluation of dense two-frame stereo correspondence algorithms", International Journal of Computer Vision, 47, pp.7~42 (2002)
- M. J. McDonnell, "Box-filtering techniques", Computer Graphics and Image Processing, 17, pp.65~70 (1981)
- Jia Guo, "Programming with tiles", Proceeding of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming, pp.111~122 (2008)
- Daniel Scharstein, "A taxonomy and evaluation of dense two-frame stereo correspondence algorithms", International Journal of Computer Vision, 47, pp.7~42 (2002)