A New Parallel Neural Network System for Automatic Change Detection and Classification of Digital Images

Change detection and classification of images are the most important applications in remote sensing systems, that involves pattern identification of a pair of spatially registered images acquired for the same object at two different conditions. A neural network- based change detection and classification system using improved mathematical model of the back-propagation-training algorithm was developed. This model will accelerate the convergence of the network to the solution. Also, the developed model has been parallized to speed up the overall proposed system that will be suitable for processing of satellite images. This system is implemented on a distributed parallel machine using PVM (Parallel Virtual Machine) layer. Two case studies, photographic images and TM (Thematic Mapper) satellite images were used, to evaluate the performance of the new system. The output results are analyzed and compared with conventional system.

[1]  Adang Suwandi Ahmad,et al.  Design and Implementation of Parallel Batch-mode Neural Network on Parallel Virtual Machine , 1999 .

[2]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.

[3]  Bernard P. Zeigler,et al.  Theory of modeling and simulation , 1976 .

[4]  Alan H. Strahler,et al.  Change-vector analysis in multitemporal space: a tool to detect and categorize land-cover change pro , 1994 .

[5]  Hussein Alnuweiri,et al.  Acceleration of back propagation through initial weight pre-training with delta rule , 1993, IEEE International Conference on Neural Networks.

[6]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[7]  Thomas P. Vogl,et al.  Rescaling of variables in back propagation learning , 1991, Neural Networks.

[8]  Tom Tollenaere,et al.  SuperSAB: Fast adaptive back propagation with good scaling properties , 1990, Neural Networks.

[9]  Liang Jin,et al.  Stable dynamic backpropagation learning in recurrent neural networks , 1999, IEEE Trans. Neural Networks.

[10]  K. Rutchey,et al.  Inland Wetland Change Detection in the Everglades Water Conservation Area 2A Using a Time Series of Normalized Remotely Sensed Data , 1995 .

[11]  Ashbindu Singh,et al.  Review Article Digital change detection techniques using remotely-sensed data , 1989 .

[12]  D J Evans,et al.  Parallel processing , 1986 .

[13]  Peter N. Nikiforuk,et al.  A new supervised learning algorithm for multilayered and interconnected neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[14]  Jack Dongarra,et al.  PVM: Parallel virtual machine: a users' guide and tutorial for networked parallel computing , 1995 .

[15]  Vicente P. Soares,et al.  Eucalyptus forest change classification using multi-date Landsat TM data , 1995, Remote Sensing.

[16]  A. K. Rigler,et al.  Accelerating the convergence of the back-propagation method , 1988, Biological Cybernetics.

[17]  Carl G. Looney,et al.  Pattern recognition using neural networks , 1997 .