Hyperspectral Image Analysis Using Genetic Programming 2005
Inhaltsverzeichnis
Reference
Brian J. Ross, A.G. Gualtieri, F. Fueten, P. Budkewitsch: Hyperspectral Image Analysis Using Genetic Programming. Applied Soft Computing, v.5, n.2, Jan 2005, pp.147-156.
DOI
http://dx.doi.org/10.1016/j.asoc.2004.06.003
Abstract
Genetic programming is used to evolve mineral identification functions for hyperspectral images. The input image set comprises 168 images from different wavelengths ranging from 428 nm (visible blue) to 2507 nm (invisible shortwave in the infrared), taken over Cuprite, Nevada, with the AVIRIS hyperspectral sensor. A composite mineral image indicating the overall reflectance percentage of three minerals (alunite, kaolnite, buddingtonite) is used as a reference or “solution” image. The training set is manually selected from this composite image, and results are cross-validated with the remaining image data not used for training. The task of the GP system is to evolve mineral identifiers, where each identifier is trained to identify one of the three mineral specimens. A number of different GP experiments were undertaken, which parameterized features such as thresholded mineral reflectance intensity and target GP language. The results are promising, especially for minerals with higher reflectance thresholds, which indicate more intense concentrations.
Extended Abstract
Bibtex
Used References
Aguilar, D.P.K., D.P.M. Cobo, D..R.P. Utrero and D.M.A.H. Nieves (2000). Abundance Extractions from AVIRIS Image Using a Self-Organizing Neural Network. In: Proceedings of the Ninth Annual JPL Airborne Earth Science Workshop.
Brumby, S.P., J. Theiler, S. Perkins, N.R. Harvey and J.J. Szymanski (2001). Genetic programming approach to extracting features from remotely sensed imagery. In: Proceedings FUSION 2001.
Civco, D.L. (1993). Artificial neural networks for land-cover classification and mapping. Interna- tional Journal of Geographical Information Sys- tems 7(2), 173–186.
Clark, R.N. and G.A. Swayze (1995). Mapping Min- erals, Amorphous Materials, Environmental Ma- terials, Vegetation, Water, Ice and Snow, and Other Materials: The USGS Tricorder Algorithm. In: Proceedings of the Fifth Annual JPL Air- borne Earth Science Workshop (R.O. Green, Ed.). pp. 39–40. JPL Publication 95-1.
Daida, J.M., J.D. Hommes, T.F. Bersano-Begey, S.J. Ross and J.F. Vesecky (1996). Algorithm Discov- ery Using the Genetic Programming Paradigm: Extracting Low-Contrast Curvilinear Features from SAR Images of Arctic Ice. In: Advances in Genetic Programming II (P. Angeline and K.E. Kinnear, Eds.). pp. 417–442. MIT Press.
Dreyer, P. (1993). Classification of Land Cover Us- ing Optimized Neural Nets on SPOT Data. Pho- togrammetric Engineering and Remote Sensing 59(5), 617–621.
Foody, G.M. and M.K. Arora (1997). An evaluation of some factors affecting the accuracy of classifica- tion by an artificial neural network. International Journal of Remote Sensing 18(4), 799–810.
Green, R.O., M.L. Eastwood, C.M. Sarture, T.G. Chrien, M. Aronsson, B.J. Chippendale, J.A. Faust, B.E. Pavri, C.J. Chovit, M. Solis, M.R. Olah and O. Williams (1998). Imaging Spectrom- etry and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS). Remote Sensing of En- vironment 65, 227–248.
Harvey, N.R., S.P. Brumby, S.J. Perkins, R.B. Porter, J. Theiler, A.C. Young, J.J. Szymanski and J.J. Bloch (2000). Parallel evolution of image process- ing tools for multispectral imagery. In: Proceed- ings Imaging Spectrometry IV: SPIE-4132. Intl. Soc. for Opt. Eng.. pp. 72–80.
Howard, D. and S.C. Roberts (1999). A Staged Ge- netic Programming Strategy for Image Analysis. In: Proc. GECCO-99 (W. Banzhaf et al, Ed.). pp. 1047–1052.
Larch, D. (1994). Genetic Algorithms for Terrain Cat- egorization of Landsat Images. In: Proceedings SPIE-2231: Algorithms for Multispectral and Hy- perspectral Imagery. Intl. Soc. for Opt. Eng.. pp. 2–6.
Merenyi, E., R.B. Singer and W.H. Farrand (1993). Classification of the LCVF AVIRIS Test Site with a Kohonen Artificial Neural Network. In: Proceedings of the Fourth Annual JPL Airborne Earth Science Workshop. pp. 117–120.
Montana, D.J. (1995). Strongly Typed Genetic Pro- gramming. Evolutionary Computation 3(2), 199– 230.
Neville, R.A., C. Nadeau, J. Levesque, T. Szeredi, K. Staenz, P. Hauff and G.A. Borstad (1998). Hyperspectral Imagery for Mineral Exploration: Comparison of Data from Two Airborne Sensors. In: Proceedings Imaging Spectrometry VI: SPIE- 3438. Intl. Soc. for Opt. Eng.. pp. 74–83.
Perkins, S.J., J. Theiler, S.P. Brumby, N.R. Har- vey R.B. Porter, J.J. Szymanski and J.J. Bloch (2000). GENIE: A Hybrid Genetic Algorithm for Feature Classification in Multi-Spectral Images. In: Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation III (B. Bosacchi, D.B. Fogel and J.C. Bezdel, Eds.). pp. 52–62.
Rauss, P.J., J.M. Daida and S. Chaudhary (2000). Classification of Spectral Imagery Using Genetic Programming. In: GECCO-2000 (D. Whitley et al., Ed.). Morgan Kaufmann. pp. 726–733.
Resmini, R.G., M.E. Jappus, W.S Aldrich, J.C. Harsanyi and M. Anderson (1997). Mineral map- ping with Hyperspectral Digital Imagery Col- lection Experiment (HYDICE) sensor data at Cuprite, Nevada, U.S.A.. International Journal of Remote Sensing 18(7), 1553–1570.
Ridd, M.K., N.D. Ritter, N.A. Bryant and R.O Green (1992). AVIRIS Data and Neural Networks Ap- plied to an Urban Ecosystem. In: Proceedings of the Second Annual JPL Airborne Earth Science Workshop. pp. 129–131.
Staenz, K. and D.J. Williams (1997). Retrieval of sur- face reflectance from hyperspectral data using a look-up table approach. Canadian Journal Re- mote Sensing 23, 345–368.
Yang, H., F. van der Meer, W. Bakker and Z.J. Tan (1999). A back-propagation neural network for mineralogical mapping from AVIRIS data. Inter- national Journal of Remote Sensing 20(1), 97– 110.
Zongker, D. and B. Punch (1995). lil-gp 1.0 User’s Manual. Dept. of Computer Science, Michigan State University.
Links
Full Text
http://www.cosc.brocku.ca/~bross/research/gp_hyper.pdf
