Abstract
The registration of multitemperal remote sensing images before and after a disaster is a challenging problem. The main reason is that there is a dearth of homologous features that can be used as tie points for registration of variform objects. This paper proposes a new registration method based on robust kernel pattern vector (KPV) for water objects in the remote sensing images, which have complex deformation before and after a disaster. We show how the variform objects can be precisely registered using their robust kernel pattern vectors (RKPVs). The contribution can be divided into three parts. First, a novel shape descriptor, named as kernel pattern vector (KPV), is defined. Second, a robust kernel principal component analysis (RKPCA) method is proposed, which can not only capture the common pattern of the variform objects but can also act as the Criterion for outlier detection. Finally, a registration approach is derived based on the implicit RKPVs. We demonstrate the power of the proposed approach by comparing it with other existing methods using two real cases: one for lake monitoring in the Jiayu region, and the other for damage mapping of earthquake-induced barrier lake at Tangjiashan (2008 Wenchuan Earthquake). The results show that the method is effective in capturing the common structural pattern of the variform objects before and after a disaster.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abadpour A, Kasaei S, Amiri S M. Fast registration of remotely sensed images for earthquake damage estimation. Eurasip J ApplSig Process, 2006, 2006: 1–10
Foody G F. Status of land cover classication accuracy assessment. Remote Sens Environ, 2002, 80: 185–201
Canty M J. Image Analysis, Classication and Change Detection in Remote Sensing: With Algorithms for ENVI/IDL. London: CRC/Taylor and Francis, 2006
Veltkamp R C, Hagedoorn M. State of the art in shape matching. In: Lew M S, ed. Principles of Visual Information Retrieval. London: Springer-Verlag, 2000. 87–119
Li H, Manjunath B S, Mitra S K. A contour-based approach to multisensor image registration. IEEE trans Image Process, 1995, 4: 320–334
Dai X, Khorram S. A feature-based image registration algorithm using improved chain-code representation combined with invariant moments. IEEE Trans Geosci Remote, 1999, 37: 2351–2362
Habib A, AI-Ruzoug R. Semi-automatic registration of multi-source satellite imagery with varying geometric resolutions. Photogramm Eng Rem S, 2005, 71: 325–332
Wang A W, Liu Y, Zheng B, et al. A method of shape based multi-sensor image registration. In: Proceeding of Urban Remote Sensing Event, 2009 Joint. Shanghai: IEEE, 2009. 325–332
Cui M, Wonka P, Razdan A, et al. A new image registration scheme based on curvature scale space curve matching. Visual Comput, 2007, 23: 607–618
Huang L, Li Z. Feature-based image registration using the shape context. Int J Remote Sens, 2010, 31: 2169–2177
Muller K R, Mika S, Ratsch G, et al. An introduction to kernel-based learning algorithms. IEEE Trans Neural Networ, 2001, 12: 181–201
Yang J, Jin Z, Yang J Y, et al. Essence of kernel Fisher discriminant: KPCA plus LDA. Pattern Recogn, 2004, 37: 2097–2100
Sahbi H. Kernel PCA for similarity invariant shape recognition. Neurocomputing, 2007, 70: 3034–3045
Scholkopf B, Smola A, Muller K R. Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput, 1998, 10: 1299–1319
Lu C D, Zhang T Y, Du X Z, et al. A robust kernel PCA algorithm. In: Proceedings of International Conference on Machine Learning and Cybernetics, Vols 5. IEEE, 2004. 3084–3087
Wang L, Pang Y W, Shen D Y, et al. An iterative algorithm for robust kernel principal component analysis. In: Proceedings of International Conference on Machine Learning and Cybernetics, Vols 6. IEEE, 2007. 3484–3489
Alzate C, Suykens J A K. Kernel component analysis using an epsilon-insensitive robust loss function. IEEE Trans Neural Networ, 2008, 19: 1583–1598
Li J, Narayanan R M. A shape-based approach to change detection of lakes using time series remote sensing images. IEEE Trans Geosci Remote, 2003, 41: 2466–2477
Xu M, Cao C X, Zhang H, et al. Change detection of earthquake-induced barrier lake based on remote sensing image classication. Int J Remote Sens, 2010, 31: 3521–3534
Wolf L, Shashua A. Learning over sets using kernel principal angles. J Mach Learn Res, 2004, 4: 913–931
Scholkopf B, Mika S, Burges C J C, et al. Input space versus feature space in kernel-basedmethods. IEEE Trans Neural Networ, 1999, 10: 1000–1017
Ding M T, Tian Z, Xu H X. Adaptive kernel principal component analysis. Signal Process, 2010, 90: 1542–1553
Toutin T. Review article: geometric processing of remote sensing images: models, algorithms and methods. Int J Remote Sens, 2004, 25: 1893–1924
Takahashi T, Kurita T. Robust de-noising by kernel PCA. In: International Conference on Artical Neural Networks, Vol 2415. Berlin/Heidelberg: Springer-Verlag, 2002. 739–744
Kwok J T Y, Tsang I WH. The pre-image problem in kernel methods. IEEE Trans Neural Networ, 2004, 15: 1517–1525
Parsons T, Ji C, Kirby E. Stress changes from the 2008 Wenchuan earthquake and increased hazard in the Sichuan basin. Nature, 2008, 454: 509–510
Li X B, Tian Z. Multiscale stochastic hierarchical image segmentation by spectral clustering. Sci China Ser F-Inf Sci, 2007, 50: 198–211
Zhang L L, Zhang Y N, Wang M, et al. Adaptive river segmentation in SAR images. Chinese J Electron, 2009, 26: 438–442
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ding, M., Jin, Z., Tian, Z. et al. Object registration for remote sensing images using robust kernel pattern vectors. Sci. China Inf. Sci. 55, 2611–2623 (2012). https://doi.org/10.1007/s11432-011-4478-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11432-011-4478-2