Hyperspectral analysis, the support vector machine, and land and benthic habitats

2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data

Volumn , Issue , 2004, Pages 354-363

  Gualtieri, J A ^a  

^a NASA HEADQUARTERS   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AGRICULTURAL MACHINERY; INFRARED SPECTROMETERS; SIGNAL TO NOISE RATIO; SOLAR RADIATION; SUPPORT VECTOR MACHINES;

GEO-STATIONARY ORBITS; HYPERSPECTRAL ANALYSIS; HYPERSPECTRAL REMOTE SENSING; HYPERSPECTRAL SENSORS; PROPAGATION OF LIGHTS; REALISTIC SIMULATION; SHALLOW WATER REMOTE SENSING; SPATIAL RESOLUTION;

REMOTE SENSING;

EID: 52749092873     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/WARSD.2003.1295215     Document Type: Conference Paper

References (44)

1. G. F. Hughes, "On the mean accuracy of statistical pattern recognizers," IEEE Transactions on Information Theory, vol. 14, no. 1, pp. 55-63, 1968.
2. R. E. Bellman, Adaptive Control Processes: A Guided Tour. Princeton, New Jersey, U.S.A.: Princeton University Press, 1961.
3. V. N. Vapnik and A. J. Chervonenkis, Theory of pattern Recognition. Nauka, 1974, in Rusian.
4. V. N. Vapnik, Estimation of dependencies based on empirical data. Springer, 1982.
5. -, Statistical Learning Theory. John-Wiley and Sons, Inc., 1998.
6. B. E. Boser, I. M. Guyon, and V. N. Vapnik, "A training algorithm for optimal margin classifiers," in Fifth Annual Workshop on Computational Learning Theory. ACM, June 1992, pp. 144-152.
7. C. Cortes and V. N. Vapnik, "Support vector networks," Machine Learning, vol. 20, pp. 1-25, 1995.
8. B.-C. Kuo and D. Landgrebe, "Improved statistics estimation and feature extraction for hyperspectral data classification," Ph.D. dissertation, School of Electrical Engineering and Computer Science, Purdue University, Dec. 2001, avaiable as TR-ECE 01-6 from http://dynamo.ecn.purdue.edu/?landgreb/KuoTR.
9. Q. Z. J. D. Landgrebe, "High dimensional data with limited training samples," Ph.D. dissertation, School of Electrical Engineering and Computer Science, Purdue University, Dec. 2001, available as TR-ECE 01-5 from http://dynamo.ecn.purdue.edu/?landgreb/JacksonTR.
10. S. Tadjudin and D. Landgrebe, "Classification of high dimensional data with limited training samples," Ph.D. dissertation, School of Electrical Engineering and Computer Science, Purdue University, May 1998, available as TR-ECE-98-9 from http://dynamo.ecn.purdue.edu/?landgreb/Saldju TR.
11. D. Landgrebe, "Indian pines aviris hyperpsectral radiance data: 92av3c," 1992, a 145 ?145 pixel and 220 band subset in BIL format of radiance data that has been scaled and offset to digital numbers, DN, from radiance, rad in units W/(cm2 ? nm ? sr) according to DN = 500∗rad + 1000 as 2bit signed integers. It is available at ftp://ftp.ecn.purdue.edu/biehl/MultiSpec/92AV3C. Ground truth is also available at ftp://ftp.ecn.purdue.edu/pub/biehl/PC MultiSpec/ThyFiles.zip. The full data set is called Indian Pines 1 f920612t01p02 r02 as listed in the AVIRIS JPL repository (http://aviris.jpl.nasa.gov/ql/list92.html). The flight line is Lat Start: 40:36:39 Long Start:-87:02:21 Lat End: 40:10:17 Long End:-87:02:21 Start Time:19:42:43GMT End Time:19:46:2GMT. See also http://dynamo.ecn.purdue.edu/?biehl/MultiSpec/aviris documentation.html%.
12. -, "Information extraction principles and methods for multispectral and hyperspectral image data," in Information Processing for Remote Sensing, H. Chen, Ed. World Scientific Publishing Co., 1999, ch. 1, also available at http://dynamo.ecn.purdue.edu/?landgreb/publications.html.
13. C. J. C. Burges, "A tutorial on support vector machines for pattern recognition," Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 121-167, 1998, also available at http://svm.research. bell-labs.com/SVMdoc.html.
14. S. Gunn, "Support vector machines for classification and regression," Image Speech and Intelligent Systems Group, University of Southampton, Tech. Rep., November 1997, the site http://www. isis.ecs.soton.ac.uk/resources/svminfo/contains the tutorial and matlab code which implements SVM's.
15. Support-Vector-Machines, "Web sites for svm," 2001, http://www.kernel-machines.org/index.html, http://www.dcs.rhbnc.ac. uk/research/compint/areas/comp learn/svm/index.%shtml, http://wwwsyseng.anu.edu.au/lsg/.
16. J. A. Gualtieri and R. F. Cromp, "Support vector machines for hyperspectral remote sensing classification," in 27'th AIPR Workshop, Advances in Computer Assisted Recognition, Proceeding of the SPIE, Vol. 3584, R. J. Merisko, Ed. SPIE, 1998, pp. 221-232.
17. C. Cortes, "Prediction of generalization ability in learning machines," Ph.D. dissertation, University of Rochester, 1995.
18. M. Aizerman, E. Braverman, and L. I. Rozoner, "Theoretical foundations of the potential function method in pattern recognition," Automation and Remote Control, vol. 25, pp. 821-837, 1964.
19. B. Schölkopf, C. Burges, and A. Smola, Eds., Advances in Kernel Methods. MIT Press, 1998.
20. C.-C. Chang and C.-J. Lin, "Libsvm-a library for support vector machines," the demo is available from http://www.csie.ntu.edu. tw/?cjlin/libsvm/.
21. T. Joachims, 2001, the SVMlight package is written in gcc and distributed for free for scientific use from http://ais.gmd.de/\?thorsten/svm light/It can use one of several quadratic optimizers. For our application we used the A. Smola's PR LOQO package
22. -, "Making large-scale svm learning practical," in Advances in Kernel Methods-Support Vector Learning, B. Schölkopf, C. Burges, and A. Smola, Eds. MIT Press, 1998, currently available at http://www-ai.cs.uni-dortmund.de/DOKUMENTE/Joachims 98b.ps.gz.
23. A. Smola, 1998, the PR LOQO quadratic optimization package is distributed for research purposes by A. Smola at http://svm. first.gmd.edu.de/software/loqosurvey.html.
24. S. Tadjudin and D. Landgrebe, "Classification of high dimensional data with limited training samples," Ph.D. dissertation, School of Electrical Engineering and Computer Science, Purdue University, May 1998, available as TR-ECE-98-9 from http://dynamo.ecn.purdue.edu/?landgreb/Saldju TR.
25. -, "Covariance estimation with limited training samples," IEEE Transactions on Geoscience and Remote Sensing, vol. 37, no. 4, pp. 2113-2118, 1999.
26. J. A. Gualtieri, S. R. Chettri, R. F. Cromp, and L. F. Johnson, "Support vector machine classifiers as applied to aviris data," in Summaries of the Eighth JPL Airborne Earth Science Workshop: JPL Publication 99-17, R. Green, Ed. NASA/JPL, Feb 1999, pp. 217-227, available at http://aviris.jpl.nasa.gov/docs/workshops/99 docs/toc.htm.
27. T. Kutser, A. G. Dekker, and W. Skirving, "Modeling spectral discrimination of gret barrier reef benthic communities by remote sensing instruments," Limnol. Oceanogr., vol. 48, no. 1,part 2, pp. 497-510, 2003.
28. J. Wang and G. Anderson, "Validation of fascod3 and modtran3: Comparison of model calculations with interferometer observations from spectre and itra, in passive infrared remote sensing of clouds and the atmosphere ii," vol. 35, 1996, this software is available from http://www-vsbm.plh.af.mil/soft/modtran.html.
29. Hydrolight: written by C. D. Mobley of Sequoia Scientific Inc. http://www.sequoiasci.com/default.asp.
30. http://eo1.gsfc.nasa.gov/Technology/Hyperion.html.
31. http://eo1.gsfc.nasa.gov/Technology/ALIhome1.htm.
32. http://eo1.gsfc.nasa.gov
33. http://www.hymap.com
34. B.-C. Gao, M. J. Montes, Z. Ahmad, and C. O. Davis, "Atmospheric correction algorithm for hyperspectral remote sensing of ocean color from space," Applied Optics, vol. 39, no. 6, pp. 887-896, 2000.
35. J. Montes, B.-C. Gao, and C. O. Davis, "A new algorithm for atmospheric correction of hyperspectral remote sensing data," in Geo-Spatial Image and Data Exploitation II, Proceedings of the SPIE Vol. 4383. SPIE, 2001, pp. 23-30.
36. Z. Lee, K. L. Carder, C. Mobley, R. G. Steward, and J. S. Patch, "Hypersepctral remote sensing for shallow waters. 1. a semianalytic model," Applied Optics, vol. 37, no. 27, pp. 6329-6338, 1998.
37. -, "Hypersepctral remote sensing for shallow waters. 2. deriving bottom depths and water properties by optimization," Applied Optics, vol. 38, no. 18, pp. 3831-3843, 1999.
38. Z. Lee, K. L. Carder, R. F. Chen, and T. G. Peacock, "Properties of the water column and bottom derived from airborne visible infrared imageing spectrometer (aviris) data," J. G. R., vol. 106, no. C6, pp. 11 639-11 651, 2001.
39. Z. Lee and K. L. Carder, "Effect of spectral band numbers on the retrieval of water column and bottom properties from ocean color data," Appl. Optics, vol. 41, no. 12, pp. 2191-2201, 2003.
40. AVIRIS scenes 03 and part of 04 from flightline f00041201p03 r08 over Kaneohe Bay on April 12, 2000 from an altitude of 20km yielding a pixel size of 17m. The flight line direction is down in the figure and which is approx NW, making N at approximately 135 ? counterclockwise from vertical. Cross track on the the flightline is approximately 10.5 km (614×17m).
41. E. J. Hochberg, M. J. Atkinson, and S. A. 2003, "Spectral reflectance of coral reef bottom-types worldwideand implicatons for coral remote sensing," Remote Sensing of Environment, vol. 85, pp. 159-173, 2003.
42. J. C. Bremmer and M. S. Maxwell, "Cosatal zone imager," Swales Aerospsace, Tech. Rep., June 2003.
43. R. O. Green and B. Pavri, "Aviris inflight calibration experiment measurements, analyses, and results in 2000," in Ninth JPL Airborne Earth Science Workshop. JPL, Feb 2000.
44. A. Smola, 2001, the PR LOQO quadratic optimization package is distributed for research purposes by A. Smola at http://www. kernel-machines.org/code/prloqo.tar.gz.