High-performance automatic image registration for remote sensing

Image registration is one of the crucial steps in the analysis of remotely sensed data. A new acquired image must be transformed, using image registration techniques, to match the orientation and scale of previous related images. Image registration requires intensive computational effort not only because of its computational complexity, but also due to the continuous increase in image resolution and spectral bands. Thus, high-performance computing techniques for image registration are critically needed. Very few works have addressed image registration on contemporary high-performance computing systems. Furthermore, issues of load balancing, scalability, and formal analysis of algorithmic efficiency were seldom considered. This dissertation introduces high-performance automatic image registration (HAIR) algorithms. High performance is achieved by: (1) reduction in search data, (2) reduction in search space, and (3) parallel processing. Reduction in search data is achieved by performing registration using only subimages. A new metric called registrability is used to select those subimages such that accuracy is maintained. In addition, a histogram comparison is used to discard anomalous subimages, such as those with clouds. Further data reduction is obtained using an iterative refinement search (IRA), which exploits the wavelet multi-resolution representation. This technique starts searching images with lower resolution first, then refining the results using higher resolution images to use the least possible data points in the overall registration task. Reduction of search space is achieved through two methods. First, iterative refinement reduces dramatically the number of solutions examined. In addition, genetic algorithms were also used to further expedite the search. Parallel processing techniques have been utilized to provide coarse-grain load-balanced parallel algorithms based on iterative refinement as well as genetic algorithms. Two hybrid algorithms have been also devised in order to integrate the strengths of iterative refinement, genetic algorithms, automatic subimage selection, and parallelism. The proposed algorithms were shown, experimentally and analytically, to provide substantial improvements in both accuracy and performance when applied to remote sensed images. Test images included LandSat Thematic Mapper (TM), Advanced Very High Resolution Radiometry (AVHRR), Geostationary Operational Environmental Satellite-8 (GOES-8), and Synthetic Aperture Radar (SAR). The parallel algorithms have exhibited good load-balancing scalability on contemporary parallel computers, including Cray T3E and Beowulf Parallel Clusters.

[1]  David W. Paglieroni,et al.  GOES landmark positioning system , 1996, Optics & Photonics.

[2]  Morgan McGuire,et al.  Techniques for multiresolution image registration in the presence of occlusions , 2000, IEEE Trans. Geosci. Remote. Sens..

[3]  William Gropp,et al.  Implementing MPI: the 1994 MPI Implementors' Workshop , 1994, Proceedings Scalable Parallel Libraries Conference.

[4]  Eric C. Olson,et al.  A geometric approach to subpixel registration accuracy , 1987, Computer Vision Graphics and Image Processing.

[5]  Thomas S. Huang,et al.  Image Sequence Analysis: Motion Estimation , 1981 .

[6]  John A. Richards,et al.  Remote Sensing Digital Image Analysis , 1986 .

[7]  Jim R. Parker,et al.  Algorithms for image processing and computer vision , 1996 .

[8]  Guy Marchal,et al.  Fast multimodality image registration using multiresolution gradient-based maximization of mutual information , 1997 .

[9]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[10]  Christopher Justice,et al.  The impact of misregistration on change detection , 1992, IEEE Trans. Geosci. Remote. Sens..

[11]  J. L. Moigne.  Parallel registration of multisensor remotely sensed imagery using wavelet coefficients , 1994 .

[12]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[13]  Michael J. Flynn,et al.  Some Computer Organizations and Their Effectiveness , 1972, IEEE Transactions on Computers.

[14]  Shmuel Peleg,et al.  Image sequence enhancement using sub-pixel displacements , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  S. P. Kim,et al.  Subpixel accuracy image registration by spectrum cancellation , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  M. J. Quinn,et al.  Parallel Computing: Theory and Practice , 1994 .

[17]  J. E. Brown,et al.  Brown , 1975 .

[18]  Michael T. Heath,et al.  Scientific Computing: An Introductory Survey , 1996 .

[19]  Bernd Jähne,et al.  Digital Image Processing: Concepts, Algorithms, and Scientific Applications , 1991 .

[20]  Tarek El-Ghazawi,et al.  Towards an intercomparison of automated registration algorithms for multiple source remote sensing data , 1997 .

[21]  J. Michael Fitzpatrick,et al.  Image registration for a transputer-based distributed system , 1989, IEA/AIE '89.

[22]  Bin Cong,et al.  Scalable Parallel Computing: Technology, Architecture, Programming , 1999, Scalable Comput. Pract. Exp..

[23]  V. N. Dvornychenko,et al.  Bounds on (Deterministic) Correlation Functions with Application to Registration , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  A. El-Ghazaw,et al.  Wavelet-Based Image Registration on Parallel Computers , 1997, ACM/IEEE SC 1997 Conference (SC'97).

[25]  Robert F. Cromp,et al.  A scale space feature based registration technique for fusion of satellite imagery , 1997 .

[26]  Menas Kafatos.  Panel: Data Exchanges and Interoperability in Distributed Earth Science Information Systems , 1999, SSDBM.

[27]  Michael Werman,et al.  Reconstruction of high resolution 3D visual information , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Michal Irani,et al.  Super resolution from image sequences , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[29]  Qi Tian,et al.  Algorithms for subpixel registration , 1986 .

[30]  Tarek El-Ghazawi,et al.  Image registration by parts , 1997 .

[31]  Thomas S. Huang,et al.  Image sequence analysis , 1981 .

[32]  Michal Irani,et al.  Improving resolution by image registration , 1991, CVGIP Graph. Model. Image Process..

[33]  William K. Pratt,et al.  Correlation Techniques of Image Registration , 1974, IEEE Transactions on Aerospace and Electronic Systems.

[34]  J. Davenport.  Editor , 1960 .

[35]  Thomas L. Sterling,et al.  Achieving a balanced low-cost architecture for mass storage management through multiple fast Ethernet channels on the Beowulf parallel workstation , 1996, Proceedings of International Conference on Parallel Processing.

[36]  Tarek El-Ghazawi,et al.  Multi-Resolution Wavelet Decomposition on the MasPar Massively Parallel System , 1994 .

[37]  Jacqueline LeMoigne,et al.  Scope and applications of translation invariant wavelets to image registration , 1997 .

[38]  Harrison M. Wadsworth.  Handbook of Statistical Methods for Engineers and Scientists , 1990 .

[39]  P. Merkey,et al.  Beowulf: harnessing the power of parallelism in a pile-of-PCs , 1997, 1997 IEEE Aerospace Conference.

[40]  Thomas S. Huang,et al.  Image Sequence Processing and Dynamic Scene Analysis , 1983, NATO ASI Series.

[41]  R. Kwok,et al.  Automated Multisensor Registration: Requirements And Techniques , 1990, 10th Annual International Symposium on Geoscience and Remote Sensing.

[42]  Philip Husbands,et al.  Genetic algorithms in optimisation and adaptation , 1992 .

[43]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[44]  Dan Boneh,et al.  On genetic algorithms , 1995, COLT '95.

[45]  Marco Corvi,et al.  Multiresolution image registration , 1995, Proceedings., International Conference on Image Processing.

[46]  Weiqi Wang,et al.  Real-time image registration based on genetic algorithms , 1996, Electronic Imaging.

[47]  Tarek A. El-Ghazawi,et al.  2-phase GA-based image registration on parallel clusters , 2001, Future generations computer systems.

[48]  J. Le Moigne,et al.  Towards a parallel registration of multiple resolution remote sensing data , 1995 .

[49]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[50]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[51]  C. D. Kuglin,et al.  Video-Rate Image Correlation Processor , 1977, Optics & Photonics.

[52]  C. D. Kuglin,et al.  The phase correlation image alignment method , 1975 .

[53]  Dipankar Dasgupta,et al.  Digital image registration using structured genetic algorithm , 1992, Optics & Photonics.

[54]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[55]  M. L. Wolbarsht,et al.  NATO Advanced Study Institute. , 1986, IEEE transactions on medical imaging.

[56]  Michael L. Mauldin,et al.  Maintaining Diversity in Genetic Search , 1984, AAAI.

[57]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[58]  Ron Shonkwiler,et al.  Parallel Genetic Algorithms , 1993, ICGA.

[59]  D. H. Horrocks,et al.  A hardware architecture for a parallel genetic algorithm for image registration , 1994 .

[60]  Josiane Zerubia,et al.  Subpixel image registration by estimating the polyphase decomposition of cross power spectrum , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[61]  Tarek A. El-Ghazawi,et al.  Wavelet decomposition on high-performance computing systems , 1996, Proceedings of the 1996 ICPP Workshop on Challenges for Parallel Processing.

[62]  James C. Tilton.  Comparison of registration techniques for GOES visible imagery data , 1997 .

[63]  J. Campbell.  Introduction to remote sensing , 1987 .