Image mosaic with relaxed motion

详细信息    查看全文

• 作者：Xianyong Fang (1) fangxianyong@ahu.edu.cn
  Jiejie Zhu (2) jjzhu@cs.ucf.edu
  Bin Luo (1) luobinahu@yahoo.com.cn
• 关键词：Image mosaic &#8211 ; Relaxed motion &#8211 ; Block matching algorithm &#8211 ; Low contrast filter &#8211 ; TV − ; L 1 model &#8211 ; Angle invariance &#8211 ; Rotation invariance
• 刊名：Signal, Image and Video Processing
• 出版年：2012
• 出版时间：November 2012
• 年：2012
• 卷：6
• 期：4
• 页码：647-667
• 全文大小：1.8 MB
• 参考文献：1. Szeliski R.: Image alignment and stitching: a tutorial. Found. Trends Comput. Graph. Comput. Vis. 2(1), 1–104 (2006)
  2. Szeliski R.: Video mosaics for virtual environments. IEEE Comput. Graph. Appl. 16(2), 22–30 (1996)
  3. Peleg, S., Herman, J.: Panoramic mosaics by manifold projection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR ’97), pp. 338. IEEE Computer Society, Washington (1997)
  4. Bartoli, A., Zisserman, A.: Direct estimation of non-rigid registration. In: Proceedings of British Machine Vision Conference 2004 (BMVC 2004), pp. 899–908. British Machine Vision Association, Kingston University, London (2004)
  5. Huang Y.-W., Chen C.-Y., Tsai C.-H., Shen C.-F., Chen L.-G.: Survey on block matching motion estimation algorithms and architectures with new results. J. VLSI Signal Process. 42, 297–320 (2006)
  6. Zitova B., Flusser J.: Image registration methods: a survey. Image Vis. Comput. 21, 977–1000 (2003)
  7. Cho, S.-H., Chung, Y.-K., Lee, J.Y.: Automatic image mosaic system using image feature detection and taylor series. In: Proceedings of the Seventh International Conference on Digital Image Computing: Techniques and Applications (DICTA 2003), pp. 549–560. CSIRO Publishing, Macquarie University, Sydney (2003, Dec)
  8. Brown, M., Lowe, D.G.: Recognising panoramas. In: Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV ’03), pp. 1218–1225. IEEE Computer Society, Washington (2003)
  9. Fang X., Zhang M., Pan Z., Wang P.: A new method of manifold mosaic for large displacement images. J. Comput. Sci. Technol. 21(2), 218–223 (2006)
  10. Brown M., Lowe D.G.: Automatic panoramic image stitching using invariant features. Int. J. Comput. Vis. 74(1), 59–73 (2007)
  11. Mikolajczyk K., Schmid C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1615–1630 (2005)
  12. Lowe D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
  13. Szeliski, R., Shum, H.-Y.: Creating full view panoramic image mosaics and environment maps. In: Proceedings of the 24th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH ’97), pp. 251–258. ACM Press/Addison-Wesley Publishing Co, New York (1997)
  14. Zhou, L.: Image matching using resolution pyramids with geometric constraints. Patent number US 6785427 (2004, Aug)
  15. Chen, T., Huang, T.S.: Optimizing image registration by mutually exclusive scale components. In: Proceedings of IEEE 11th International Conference on Computer Vision (ICCV 2007), pp. 1–8. IEEE, Rio de Janeiro (2007, Oct)
  16. Chan T.F., Esedoglu S.: Aspects of total variation regularized l 1 function approximation. SIAM J. Appl. Math. 75(5), 1817–1837 (2004)
  17. Harris, C., Stephens, M.: A combined corner and edge detection. In: Proceedings of The Fourth Alvey Vision Conference, pp. 147–151 (1988)
  18. Fischler M.A., Bolles R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24, 381–395 (1981)
  19. Hartley R.I., Zisserman A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2004)
  20. Brown, M., Hartley, R.I., Nister, D.: Minimal solutions for panoramic stitching. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR ’07), vol. 0, pp. 1–8. IEEE Computer Society, Los Alamitos (2007)
  21. Jin, H.: A three-point minimal solution for panoramic stitching with lens distortion. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), vol. 0, pp. 1–8. IEEE Computer Society, Anchorage (2008)
  22. Rudin L.I., Osher S., Fatemi E.: Nonlinear total variation based noise removal algorithms. Phys. D 60(1–4), 259–268 (1992)
  23. Wang Y., Yang J., Yin W., Zhang Y.: A new alternating minimization algorithm for total variation image reconstruction. SIAM J. Imaging Sci. 1(3), 248–272 (2008)
  24. Yang, J., Yin, W., Zhang, Y., Wang, Y.: A Fast Algorithm for Edge-Preserving Variational Multichannel Image Restoration. Tech. Rep. TR08-09. Department of Computational and Applied Mathematics, Rice University (2008, July)
  25. Yang J., Zhang Y., Yin W.: An efficient tvl1 algorithm for deblurring multichannel images corrupted by impulsive noise. SIAM J. Sci. Comput. 31(4), 2842–2865 (2009)
  26. Geman D., Yang C.: Nonlinear image recovery with half-quadratic regularization. IEEE Trans. Image Process. 5(7), 932–946 (1995)
  27. Roche, A., Malandain, G., Pennec, X., Ayache, N.: The correlation ratio as a new similarity measure for multimodal image registration. In: MICCAI ’98: Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 1115–1124. Springer-Verlag, London (1998)
  28. Noble, A.: Descriptions of Image Surfaces. PhD thesis. Department of Engineering Science, Oxford University (1989)
  29. Kovesi, P.D.: MATLAB and Octave Functions for Computer Vision and Image Processing. School of Computer Science & Software Engineering, The University of Western Australia. Available from: http://www.csse.uwa.edu.au/~pk/research/matlabfns/
  30. Hartley R., Zisserman A.: Multiple View Geometry in Computer Vision. Cambridge University Press, New York (2003)
  31. Mor茅 J.J., Sorensen D.: Computing a trust region step. SIAM J. Sci. Stat. Comput. 4(3), 553–572 (1983)
  32. Coleman T.F., Li Y.: An interior trust region approach for nonlinear minimization subject to bounds. SIAM J. Optim. 6, 418–445 (1996)
  33. Byrd R., Schnabel R., Shultz G.: Approximate solution of the trust region problem by minimization over two-dimensional subspaces. Math. Progr. 40, 247–263 (1988)
  34. Umeyama S.: Least-squares estimation of transformation parameters between two point patterns. IEEE Trans. Pattern Anal. Mach. Intell. 13, 376–380 (1991)
  35. Strait, J., Smoky City Design, L.: The panorama factory (2009, May)
  36. d’Angelo, P., Behrmann, K.-U., Wilkins, D., Halley, E., Ukai, I., Postle, B., Jin, J., Mesec, Z., Jenny, A., Yaniv, Z., Januszewski, M., Patterson, G., Sharpless, T., Levy, Y.: Hugin—panorama photo stitcher (2010, Mar)
  37. Fang, X., Luo, B., Zhao, H., Tang, J., Zhai, S.: A new multi-resolution image stitching with local and global alignment. IET Comput. Vision (2010, to appear)
• 作者单位：1. Key Lab. of Intelligent Computing and Signal Processing of MOE, School of Computer Science and Technology, Anhui University, Anhui, China2. Computer Vision Lab, University of Central Florida, Orlando, USA
• ISSN：1863-1711

文摘

We propose a novel method to stitch images with relatively large roll or pitch called relaxed motion, which defies most existing mosaic algorithms. Our approach adopts a multi-resolution strategy, which combines the merits of both feature-based and intensity-based methods. The main contribution is a robust motion estimation procedure which integrates an adaptive multi-scale block matching algorithm called TV-BMA, a low contrast filter and a RANSAC motion rectification to jointly refine motion and feature matches. Based on TV − L 1 model, the proposed TV-BMA works on the coarsest layer to find a robust initial displacement field as the initial motion for source images. This motion estimation method can generate robust correspondences for further processing. In the subsequent camera calibration step, we also present two stable methods to estimate the camera matrix. To estimate the focal length, we combine the golden section search and the simplex method based on the angle invariance of feature vectors; to estimate the rotation matrix, we introduce a subspace trust region method, which matches features based on the rotation invariance. Extensive experiments show that our approach leads to improved accuracy and robustness for stitching images with relaxed motion.