CFP last date
22 April 2024
Reseach Article

Image Stitching using Harris and RANSAC

by Rupali Chandratre, V. A Chakkarwar
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 89 - Number 15
Year of Publication: 2014
Authors: Rupali Chandratre, V. A Chakkarwar
10.5120/15706-4567

Rupali Chandratre, V. A Chakkarwar . Image Stitching using Harris and RANSAC. International Journal of Computer Applications. 89, 15 ( March 2014), 14-19. DOI=10.5120/15706-4567

@article{ 10.5120/15706-4567,
author = { Rupali Chandratre, V. A Chakkarwar },
title = { Image Stitching using Harris and RANSAC },
journal = { International Journal of Computer Applications },
issue_date = { March 2014 },
volume = { 89 },
number = { 15 },
month = { March },
year = { 2014 },
issn = { 0975-8887 },
pages = { 14-19 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume89/number15/15706-4567/ },
doi = { 10.5120/15706-4567 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T22:09:19.105032+05:30
%A Rupali Chandratre
%A V. A Chakkarwar
%T Image Stitching using Harris and RANSAC
%J International Journal of Computer Applications
%@ 0975-8887
%V 89
%N 15
%P 14-19
%D 2014
%I Foundation of Computer Science (FCS), NY, USA
Abstract

In this paper the problem of fully automated panoramic image stitching for 2D image is introduced. In this work, stitching two images using invariant local fea¬tures is used. This algorithm recognises multiple panoramas in an unordered image dataset and uses Harris Corner Detection for detecting the key point i. e. features. RANSAC method is used to choose the closest match between the two images by separating inliers and outliers. For the Image stitching using the inliers, homography matrix is used which requires least 8 feature points . Once the homography matrix is calculated between the two images, a panoramic view by wrapping the two images is generated. To get the efficient homography matrix, the feature points which fall onto the corresponding epipolar lines are selected. In this rectilinear projections are used to project the resulting image. In rectilinear projections images are viewed on two dimensional planes. Harris Corner Detection method is more robust for detecting the corners in the images than other methods. Hence, Harris Corner Detection with RANSAC which gives efficient image stitching.

References
  1. P. Burt and E. Adelson. A multiresolu¬tion spline with application to image mosaics. ACM Transactions on Graphics, 2(4):217–236, 1983.
  2. J. Beis and D. Lowe. Shape indexing using approximate nearest-neighbor search in high-dimensional spaces. In Proceedings of the In¬terational Conference on Computer Vision and Pattern Recognition (CVPR97), pages 1000– 1006, 1997.
  3. M. Brown and D. Lowe. Recognising panora¬mas. In Proceedings of the 9th International Conference on Computer Vision (ICCV03), volume 2, pages 1218–1225, Nice, October 2003.
  4. D. Brown. Close-range camera calibration. Photogrammetric Engineering, 37(8):855– 866, 1971.
  5. M. Brown, R. Szeliski, and S. Winder. Multi-image matching using multi-scale oriented patches. In Proceedings of the Interational Conference on Computer Vision and Pattern Recognition (CVPR05), San Diego, June 2005.
  6. S. Chen. QuickTime VR – An image-based approach to virtual environment navigation. In SIGGRAPH'95, volume 29, pages 29–38, 1995.
  7. D. Capel and A. Zisserman. Automated mosaicing with super-resolution zoom. In Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR98), pages 885–891, June 1998.
  8. J. Davis. Mosaics of scenes with moving objects. In Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR98), pages 354–360, 1998.
  9. P. Debevec and J. Malik. Recovering high dy¬namic range radiance maps from photographs. Computer Graphics, 31:369–378, 1997.
  10. M. Fischler and R. Bolles. Random sample consensus: A paradigm for model ?tting with application to image analysis and automated cartography. Communications of the ACM, 24:381–395, 1981.
  11. M. A. Fischler and R. C. Bolles. Random sample consensus: paradigms for model fitting with applications to image analysis and automated cartography. Commun. ACM, 24:381–395, June 1981
  12. D. Milgram. Computer methods for creating photomosaics. IEEETransactions on Computers, C-24(11):1113 – 1119,1975
  13. R. Hartley and A. Zisserman. Multiview Geometry in ComputerVision. Cambridge University Press, 2004. H. -Y. Shum and R. Szeliski. Construction of panoramic imagemosaics with global and local alignment. Internal Journal of Computer Vision, 36(2):101–130, 2000
  14. D. G. Lowe. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision, 60:91–110, November 2004.
  15. M. Brown and D. Lowe. Automatic panoramic image stitching using invariant features. International Journal of Computer Vision,74(1):59–73, 2007
  16. M. Brown and D. Lowe. Recognising panoramas. In ICCV,2003 J. Jia and C. -K. Tang. Image registration with global and localluminance alignment. In ICCV, 2003
  17. W. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon. Bundle adjustment: A modern synthesis. In Vision Algorithms: Theory and Practice, number 1883 in LNCS, pages 298–373. Springer-Verlag, Corfu, Greece, September1999.
  18. Harris, C. , Stephens, M. : A combined corner and edge detector. In: 4th Alvey Vision Conference, pp. 147–151 (1988)
Index Terms

Computer Science
Information Sciences

Keywords

Harris Corner detector Panoramic view Perspective transform rectilinear projection Feature points Key points