An automated parallel image registration technique based on the correlation of wavelet features

IEEE Transactions on Geoscience and Remote Sensing - Tập 40 Số 8 - Trang 1849-1864 - 2002
J. Le Moigne1, W.J. Campbell1, R.F. Cromp2,1
1Applied Information Sciences Branch, NASA Goddard Space Flight Center-Code 935, Greenbelt, MD, USA
2Raytheon, Inc., Aberdeen, MD, USA

Tóm tắt

With the increasing importance of multiple multiplatform remote sensing missions, fast and automatic integration of digital data from disparate sources has become critical to the success of these endeavors. Our work utilizes maxima of wavelet coefficients to form the basic features of a correlation-based automatic registration algorithm. Our wavelet-based registration algorithm is tested successfully with data from the National Oceanic and Atmospheric Administration (NOAA) Advanced Very High Resolution Radiometer (AVHRR) and the Landsat Thematic Mapper (TM), which differ by translation and/or rotation. By the choice of high-frequency wavelet features, this method is similar to an edge-based correlation method, but by exploiting the multiresolution nature of a wavelet decomposition, our method achieves higher computational speeds for comparable accuracies. This algorithm has been implemented on a single-instruction multiple-data (SIMD) massively parallel computer, the MasPar MP-2, as well as on the CrayT3D, the Cray T3E, and a Beowulf cluster of Pentium workstations.

Từ khóa

#Image registration #Remote sensing #Wavelet coefficients #Testing #Atmospheric waves #Radiometry #Satellites #Correlation #Clustering algorithms #Concurrent computing

Tài liệu tham khảo

10.1109/IGARSS.1998.702890 10.1080/01431169508954417 10.1109/36.297982 el-ghazawi, 1997, wavelet-based image registration on parallel computers, Supercomputing 97, 10.1145/509593.509613 le moigne, 2001, multi-sensor registration of earth remotely sensed imagery, Proc 8th SPIE Int Symposium Remote Sensing 10.1109/ICIP.2000.901003 10.1117/12.236024 10.1016/S0031-3203(98)00086-7 kinsgbury, 1999, shift invariant properties of the dual-tree complex wavelet transforms, Proc ICASSP 10.1109/83.366480 10.1109/78.738243 le moigne, 2000, use of wavelets for image registration, Proc SPIE Aerosense 2000 &#x201C Wavelet Applications VII&#x201D 10.1016/0031-3203(95)00115-8 li, 1995, automatic eo/ir sensor image registration, Proc ICIP 10.1109/34.93805 10.1109/TGRS.1986.289597 10.1117/12.155816 10.1109/83.236535 zhang, 1996, autoamtic image to site model registration, Proc ICASP, 4, 2166 10.1109/36.54357 10.1137/1031128 10.1109/34.799911 10.1109/34.192463 10.1109/36.295052 10.1117/12.235996 10.1109/18.119725 10.1016/0031-3203(92)90005-4 coifman, 1995, translation-invariant de-noising, Wavelets and Statistics Lecture Notes, 10.1007/978-1-4612-2544-7_9 10.1109/36.3000 le moigne, 1994, parallel registration of multi-sensor remotely sensed imagery using wavelet coefficients, Proc 1994 SPIE Wavelet Applications Conf, 432 10.1109/IGARSS.1995.521123 10.1109/ICPP.1996.537376 nasa, 2001, Exploring our home planet earth science enterprise strategic plan 10.1109/FMPC.1995.380442 10.1145/146370.146374 10.1109/34.121790 10.1109/ICIP.1995.537620 10.1109/IGARSS.1990.688646 10.1080/01431168908903907 10.1109/TGRS.1989.35948 djamdji, 1993, geometrical registration of images. the multiresolution approach, Photogram Eng Remote Sens J, 59 10.1109/ICIP.1995.537621 10.1117/12.162061 10.1109/IGARSS.1990.688569 daubechies, 1991, ten lessons on wavelets, CMBS-NSF Series Applications in Mathematics chui, 1992, Introduction to Wavelets 10.1109/34.142909 boddy, 1994, planning for image processing, Proc Goddard Conf Space Applications Artificial Intelligence 1999, special issue on image registration, Pattern Recognit, 32 10.1109/42.585765 10.1109/83.650116 10.1109/CVPR.1996.517123 yuan, 1994, north america land cover change detection using historical mss data: three pilot studies, Proc ECO RIO 94 Int Symp Resource and Environmental Monitoring 10.1109/83.772236 fonseca, 1996, registration techniques for multisensor sensed imagery, Photogramm Eng Remote Sens J, 62, 1049 10.1145/170088.170397 10.1109/36.175340 10.1109/36.718860 10.1109/TGE.1977.6498970 10.1007/978-3-642-88087-2 10.1080/01431169008955172 10.1109/TAES.1974.307828 10.1109/TC.1972.5008923 10.1109/36.20292 10.1080/01431168908903926 10.1080/01431168808954847 skole, 1993, tropical deforestation and habitat fragmentation in the brazilian amazon: satellite data from 1978 to 1988, Science, 260, 1905, 10.1126/science.260.5116.1905 jedlovec, 1993, Calibration navigation and registration of MAMS data for FIFE townshend, 1992, Improved global data for land applications a proposal for a new high resolution data set Report of the Land Cover Working Group of IGBP-DIS 10.1109/TPAMI.1982.4767240 10.1016/1049-9652(91)90045-L chen, 1994, symmetric phase-only matched filtering of fourier–mellin transforms for image registration and recognition, IEEE Trans Pattern Anal Machine Intelll, 16, 1156, 10.1109/34.387491 anuta, 1970, spatial registration of multispectral and multitemporal digital imagery using fast fourier transform techniques, IEEE Trans Geosci Electron, ge 8 10.1117/12.217579 lucas, 1981, an iterative image registration technique with an application to stereo vision, 1981 DARPA Image Understanding Workshop 10.1109/83.650848 10.1109/36.368221 10.1109/78.258092 lee, 1990, a new method for automated control point selection in image registration, Proc Close-Range Photogrammetry Meets Machine Vision