Title :
Study on extraction method of land-use information: A case study of Jinzhou city
Author :
Pei, Liang ; Xu, Zhaoyang ; Dai, Jiguang
Author_Institution :
Coll. of Geomatics, LiaoNing Tech. Univ., Fuxin, China
Abstract :
This paper presents a new classification method based on a combination of GIS and BP (back propagation) artificial neural network, taking the TM image of the area of Jinzhou city in 2000 as the testing one. BP neural network can be optimized by means of selecting GIS data aided training sample, improving training algorithm, calculating the number of nodes in the hidden layer and so on. Compared with traditional methods, optimized BP neural network is an effective classification method with better self-learning, generalization, adaptive capacity and high classification accuracy.
Keywords :
geographic information systems; geomorphology; geophysical image processing; geophysical techniques; image classification; neural nets; terrain mapping; AD 2000; Jinzhou city; TM image; adaptive capacity; back propagation artificial neural network; classification method; extraction method; geographic information system; land-use information; training algorithm; Accuracy; Artificial neural networks; Classification algorithms; Geographic Information Systems; Image classification; Remote sensing; Training; Artificial neural networks; BP; Classification; Remote sensing;
Conference_Titel :
Geoinformatics, 2010 18th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-7301-4
DOI :
10.1109/GEOINFORMATICS.2010.5568049
