Skip to content

Latest commit

 

History

History
29 lines (17 loc) · 1.76 KB

README.md

File metadata and controls

29 lines (17 loc) · 1.76 KB

Image Stitching (or Panorama)

KR-CN-JP: 파노라마 - 全景画卷 - パノラマ
Keywords: ORB (Oriented FAST and rotated BRIEF), RANSAC (RANdom SAmple Consensus)
Key-translations: Least Squares Image Matching(最小二乘影像匹配)

2 pipelines were implemented for image stitching, in this case, panorama. They are ORB + RANSAC and ORB + Least Squares. For datasets, Please follow this link.

Fig 1. Case 22 by ORB + RANSAC

Fig 2. Case 22 by ORB + Least Squares

Fig 3. Case 26 by ORB + RANSAC

Fig 4. Case 26 by ORB + Least Squares

1. Citation:
[1] Zaragoza, Julio, et al. "As-projective-as-possible image stitching with moving DLT." Proceedings of the IEEE conference on computer vision and pattern recognition. 2013.
[2] Bethel, J. "Least squares image matching for CE604." Purdue University (1997).
[3] Rublee, Ethan, et al. "ORB: An efficient alternative to SIFT or SURF." ICCV. Vol. 11. No. 1. 2011.
[4] Fischler, Martin A., and Robert C. Bolles. "Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography." Communications of the ACM 24.6 (1981): 381-395.

2. Assistive Materials:
[1] Bethmann, Folkmar, and Thomas Luhmann. "Least-squares matching with advanced geometric transformation models." Photogrammetrie-Fernerkundung-Geoinformation 2011.2 (2011): 57-69.