Evolving Retrieval Algorithms with a Genetic Programming Scheme

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


Reference

James P. Theiler and Neal R. Harvey and Steven P. Brumby and John J. Szymanski and Steve Alferink and Simon J. Perkins and Reid B. Porter and Jeffrey J. Bloch: Evolving Retrieval Algorithms with a Genetic Programming Scheme. Proceedings of SPIE 3753 Imaging Spectrometry V, pp. 416-425, 1999.

DOI

http://citeseer.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.8669&rank=1

Abstract

The retrieval of scene properties (surface temperature, material type, vegetation health, etc.) from remotely sensed data is the ultimate goal of many earth observing satellites. The algorithms that have been developed for these retrievals are informed by physical models of how the raw data were generated. This includes models of radiation as emitted and/or reflected by the scene, propagated through the atmosphere, collected by the optics, detected by the sensor, and digitized by the electronics. To some extent, the retrieval is the inverse of this “forward” modeling problem. But in contrast to this forward modeling, the practical task of making inferences about the original scene usually requires some ad hoc assumptions, good physical intuition, and a healthy dose of trial and error. The standard MTI data processing pipeline will employ algorithms developed with this traditional approach. But we will discuss some preliminary research on the use of a genetic programming scheme to “evolve” retrieval algorithms. Such a scheme cannot compete with the physical intuition of a remote sensing scientist, but it may be able to automate some of the trial and error. In this scenario, a training set is used, which consists of multispectral image data and the associated “ground truth;” that is, a registered map of the desired retrieval quantity. The genetic programming scheme attempts to combine a core set of image processing primitives to produce an IDL (Interactive Data Language) program which estimates this retrieval quantity from the raw data.

Extended Abstract

Bibtex

Used References

1. B. W. Smith, C. C. Borel, W. B. Clodius, J. Theiler, B. Laubscher, and P. G. Weber, “End-to-end performance modeling of passive remote sensing systems,” in Infrared Imaging Systems: Design, Analysis, Modeling, and Testing VII, G. C. Holst, ed., Proc SPIE 2743, pp. 285–289, 1996.

2. P. G. Weber, C. C. Borel, W. B. Clodius, B. J. Cooke, and B. W. Smith, “Design considerations, modeling and analysis for the Multispectral Thermal Imager,” in Infrared Imaging Infrared Imaging Systems: Design, Analysis, Modeling, and Testing X, G. C. Holst, ed., Proc. SPIE 3701, 1999.

3. P. G. Weber, J. Theiler, B. W. Smith, S. P. Love, B. J. Cooke, W. B. Clodius, C. C. Borel, and S. C. Bender, “Measurement strategies for remote sensing applications,” in 1998 IEEE Aerospace Conference, Colorado March 6-13, 1999.

4. P. Kraft, N. R. Harvey, and S. Marshall, “Parallel genetic algorithms in the optimization of morphological filters: a general design tool,” J. Electronic Imaging 6, pp. 504–516, 1997.

5. N. R. Harvey and S. Marshall, “GA optimisation of spatio-temporal grey-scale soft morphological filters with applications in archive film restoration,” in Evolutionary Image Analysis, Signal Processing and Telecommu- nications (Proc. 1st European Workshop, EvoIASP’99 and EuroEcTel’99), R. Poli, H.-M. Voigt, S. Cagnoni, D. Corne, G. Smith, and T. Fogarty, eds., pp. 31–45, Springer-Verlag, (G ̈ oteburg, Sweden), 1999.

6. This work is also described at the following website: http://www.spd.eee.strath.ac.uk/users/harve/bbc epsrc film dirt.html.

7. C. C. Borel, “Nonlinear spectral mixing theory to model multispectral signatures,” in Proc. 11th Thematic Conference on Geologic Remote Sensing, Vol. II, pp. 11–20, (Las Vegas, NV), 1996.

8. C. C. Borel and S. A. W. Gerstl, “Nonlinear spectral mixing models for vegetative and soil surfaces,” Remote Sensing of the Environment 47, pp. 403–416, 1994.

9. G. Gisler and C. Borel, “Neural network identifications of spectral signatures,” in Proc. 11th Thematic Confer- ence on Geologic Remote Sensing, Vol. II, pp. 21–29, (Las Vegas, NV), 1996.

10. J. M. Daida, T. F. Bersano-Begey, S. J. Ross, and J. F. Vesecky, “Computer-assisted design of image classifica- tion algorithms: Dynamic and static fitness evaluations in a scaffolded genetic programming environment,” in Advances in Genetic Programming II, P. Angeline and K. Kinnear, eds., MIT Press, 1996.

11. J. M. Daida, J. D. Hommes, T. F. Bersano-Begey, S. J. Ross, and J. F. Vesecky, “Algorithm discovery 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. Kinnear, eds., MIT Press, 1996.

12. J. M. Daida, T. F. Bersano-Begey, S. J. Ross, and J. F. Vesecky, “Evolving feature-extraction algorithms: Adapting genetic programming for image analysis in geoscience and remote sensing,” in Proc. 1996 International Geoscience and Remote Sensing Symposium: Remote Sensing for a Sustainable Future, IEEE Press, 1996.

13. J. M. Daida, R. G. Onstott, T. F. Bersano-Begey, S. J. Ross, and J. F. Vesecky, “Ice roughness classification and ERS SAR imagery of arctic sea ice: Evaluation of feature-extraction algorithms by genetic programming,” in Proc. 1996 International Geoscience and Remote Sensing Symposium: Remote Sensing for a Sustainable Future, IEEE Press, 1996.

14. M. Dorigo and M. Colombetti, Robot Shaping: An Experiment in Behaviour Engineering, MIT Press, Cambridge, Massachusetts, 1998.

15. S. Perkins and G. Hayes, “Evolving complex visual behaviors using genetic programming and shaping,” in Proc. 7th European Workshop on Learning Robots, (Edinburgh), 1998.

16. M. Mitchell, An Introduction to Genetic Algorithms, MIT Press, Cambridge, Massachusetts, 1996. 17. J. R. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection, MIT Press, Cambridge, Massachusetts, 1992.

18. IDL (Interactive Data Language) is a commercial package for generic data and image processing, developed and marketed by Research Systems, Inc. (http://www.rsinc.com).

19. S. P. Brumby, J. Theiler, S. Perkins, N. Harvey, J. J. Szymanski, J. J. Bloch, and M. Mitchell, “Investigation of image feature extraction by a genetic algorithm,” in Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation II, B. Bosacchi, D. B. Fogel, and J. C. Bezdek, eds., Proc SPIE 3812, 1999.

20. C. C. Borel, W. B. Clodius, A. B. Davis, B. W. Smith, J. J. Szymanski, J. Theiler, P. V. Villeneuve, and P. G. Weber, “MTI core science retrieval algorithms,” in Imaging Spectrometry V, M. R. Descour and S. S. Shen, eds., Proc SPIE 3753, 1999.

21. “The MODIS Airborne Simulator (MAS) is an airborne scanning spectrometer that acquires high spatial resolu- tion imagery of cloud and surface features from its vantage point on-board a NASA ER-2 high-altitude research aircraft” (http://ltpwww.gsfc.nasa.gov/MODIS/MAS/Home.html).

22. M. D. King, W. P. Menzel, P. S. Grant, J. S. Myers, G. T. Arnold, S. E. Platnick, L. E. Gumley, S. C. Tsay, C. C. Moeller, M. Fitzgerald, K. S. Brown, and F. G. Osterwisch, “Airborne scanning spectrometer for remote sensing of cloud, aerosol, water vapor and surface properties,” J. Atmos. Oceanic Technol. 13, pp. 777–794, 1996.


Links

Full Text

http://citeseer.ist.psu.edu/viewdoc/download?doi=10.1.1.12.8669&rep=rep1&type=pdf

intern file

Sonstige Links