Using Neural Networks to Correlate Satellite Imagery and Ground-Truth Data

Abstract : Current approaches to evaluating the condition of natural resources on Army training and testing lands are statistically based and attempt to generate rational mathematical formulae that characterize the relationship between satellite imagery and ground-truth data. Even in the hands of a well trained image processing expert, the application of standard image processing tools can yield varying results. Army land managers need an alternate approach for correlating satellite imagery to ground-truth measurements. This approach can be found in the application of neural networks. This report presents the research results of using neural networks as a computational tool to correlate ground-truth data with satellite imagery tor Hohenfels, Germany, and to turn the imagery into maps of the installation. Satellite imagery, Neural networks, Land Condition Trend Analysis (LCTA), Geographic Resource Analysis Support System (GRASS)

[1]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[2]  T. M. Lillesand,et al.  Use of multitemporal spectral profiles in agricultural land-cower classification , 1986 .

[3]  M. F. Tenorio,et al.  Self-Organizing Neural Network for Optimum Supervised Learning , 1989 .

[4]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Ehud D. Karnin,et al.  A simple procedure for pruning back-propagation trained neural networks , 1990, IEEE Trans. Neural Networks.

[6]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

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

[8]  GrossbergS..  Adaptive pattern classification and universal recoding , 1976 .

[9]  J. Stephen Judd,et al.  Neural network design and the complexity of learning , 1990, Neural network modeling and connectionism.

[10]  H. White,et al.  There exists a neural network that does not make avoidable mistakes , 1988, IEEE 1988 International Conference on Neural Networks.

[11]  David H. Wolpert,et al.  A Mathematical Theory of Generalization: Part II , 1990, Complex Syst..

[12]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .

[13]  Raymond L. Watrous.  Learning Algorithms for Connectionist Networks: Applied Gradient Methods of Nonlinear Optimization , 1988 .

[14]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[15]  J. C. Price.  Calibration of satellite radiometers and the comparison of vegetation indices , 1987 .

[16]  Steven D. Warren,et al.  U.S. Army Land Condition-Trend Analysis (LCTA) Plot Inventory Field Methods , 1992 .

[17]  Timur Ash,et al.  Dynamic node creation in backpropagation networks , 1989 .

[18]  Xiping Wu.  Neural network-based material modeling , 1992 .

[19]  David Zipser,et al.  Feature Discovery by Competive Learning , 1986, Cogn. Sci..

[20]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .