Detecting temporal changes in satellite imagery using ANN

作者: P. Mathur , R. GoviI

DOI: 10.1109/RAST.2005.1512647

关键词: Satellite imageryInstruction setExtrapolationDynamic dataArtificial neural networkComputer scienceMan-Made DisastersNonlinear systemArtificial intelligenceMachine learningPattern recognition problemPattern recognition

摘要: One of the most interesting aspects world is that it can be considered made up patterns. In pattern recognition problem have a dynamic nature and non-adaptive algorithms (instruction sets) will fail to give realistic solution model them. these cases, adaptive are used among them, neural networks greatest hit. For example, defense applications very frequently need record, detect, identify classify images objects or signals coming from various directions sources - static dynamic. There many in remote sensing where study data needed such as deforestation, effects natural man disasters, migration paths rivers due Earth's plates. Artificial Neural Networks (ANN) play role modeling because their capability nonlinear processes unknown patterns based on learning model, forecast certain outcomes by extrapolation. this we present results classifying using SOFM classification detect temporal changes

参考文章(5)
Teuvo Kohonen, Self-organized formation of topologically correct feature maps Biological Cybernetics. ,vol. 43, pp. 509- 521 ,(1988) , 10.1007/BF00337288
Gail A. Carpenter, Stephen Grossberg, Art 2: Self-Organization Of Stable Category Recognition Codes For Analog Input Patterns Intelligent Robots and Computer Vision VI. ,vol. 0848, pp. 272- 280 ,(1988) , 10.1117/12.942747
G.A. Carpenter, S. Grossberg, The ART of adaptive pattern recognition by a self-organizing neural network IEEE Computer. ,vol. 21, pp. 77- 88 ,(1988) , 10.1109/2.33
Gail A. Carpenter, Stephen Grossberg, System for self-organization of stable category recognition codes for analog input patterns Applied Optics. ,vol. 26, pp. 4919- 4930 ,(1987) , 10.1364/AO.26.004919