Please wait a minute...
img

Wechat

Remote Sensing Technology and Application  2003, Vol. 18 Issue (6): 399-403    DOI: 10.11873/j.issn.1004-0323.2003.6.399
    
A Method of Classification of Remote Sensing Based on SOFM Model
MAO Ke-biao1,2, QIN Zhi-hao1, ZHANG Wan-chang1
(1.International Institute for Earth System,Nanjing University,Nanjing210093,China;2.Department of Urban and Resource Science,Nanjing University,Nanjing210093,China)
Download:  PDF (0KB) 
Export:  BibTeX | EndNote (RIS)      
Abstract  

Classification is always an important research orientation of remote sensing. In This paper, we extract endmeber pixed information at first, then use artificial neural network (SOFM) algorithm to classify the rest pixels, and estimate the percent of the different land use from Landsat ETM image in the Heihe River Basin. ETM were orthorectified using a digital photogrammetric software package with ground control points collected through differential GPS. We make a topographical and atmosphere correction and got fractions of land use (water (f1), vegetation (f2), and soil (f3), building (f4)) from land use map. We extract the endmember information from the image and classify the rest pixels.Experimental results indicate that classification by SOFM is better than the supervised classification by comparing with the land use statistics.

Key words:  ANN      SOFM      Mixed pixel      Pure pixel      Data miningg     
Received:  11 June 2003      Published:  25 November 2011
TP 75  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors

Cite this article: 

MAO Ke-biao, QIN Zhi-hao, ZHANG Wan-chang. A Method of Classification of Remote Sensing Based on SOFM Model. Remote Sensing Technology and Application, 2003, 18(6): 399-403.

URL: 

http://www.rsta.ac.cn/EN/10.11873/j.issn.1004-0323.2003.6.399     OR     http://www.rsta.ac.cn/EN/Y2003/V18/I6/399

〔1〕Gong P, Zhang A. Noise Effect on Linear Spectral Unmixing〔J〕. Geographic Information Sciences, 1999,5:52~57.
〔2〕Settle J J, Drake N A. Linear Mixing and the Estimation od Ground Cover Proportions〔J〕. International Journal of Remote Sensing, 1993,14:1159~1177.
〔3〕Foody G M. Relating the Land-cover Composition of Mixed Pixels to Artificial Neural Network Classification〔J〕. Photogrammetric Engineering &Remote sensing, 1996, 62:491~499.
〔4〕王喜鹏,张养贞.应用神经网络模型分解AVHRR混合像元〔J〕.遥感学报,1998,2(1):51~56.
〔5〕朱述龙,基于混合像元的遥感图像分类技术〔J〕.解放军测绘学院学报,1995,12(4):276~278.
〔6〕李郁竹,曾燕.应用NOAA/AVHRR测算局地水稻种植面积方法研究〔J〕.遥感学报,1998,5(2):125~130.
〔7〕Jiawei Han, Micheline Kamber.Data Mining: Concepts and Techniques〔M〕.北京:机械工业出版社,2000.
〔8〕Laskaris N, Fotopoulos S.An Efficient Data Mining Technique with Application in Multivariate Image Analysis〔J〕.IEEE Transactions on Geoscience and Remote Sensing, 1997,27(6):1103~1106.
〔9〕Marchisio G B, Wen-Hao LI. GeoBrowe: An Integrated Environment for Satellite Image Retrieval and Mining〔J〕.IEEE Transactions on Geoscience and Remote Sensing,1998,31(2): 669~673.
〔10〕Leen-Kiat Soh, Tasatsoulis C. Data Ming in Remote Sensed Images: A General Model and Application〔J〕. IEEE Transactions on Geoscience and Remote Sensing, 1998,31(4):798~800.
〔11〕Leen-Kiat Soh, Costas Tasatsoulis. Segmentation of Satellite Imagery of Natural Scenes Using Data Mining〔J〕. IEEE Transactions on Geoscience and Remote Sensing, 1999,37(2): 1086~1099.
〔12〕毛克彪,田庆久.空间数据挖掘技术及其应用〔J〕.遥感技术与应用,2002,17(4):198~204.
〔13〕边肇祺,张学工.模式识别〔M〕.北京:清华大学出版社,1999.
〔14〕许东,吴铮著.基于MATLAB6.X的系统分析与设计-神经网络〔M〕.西安:西安电子科技大学出版社,2002,5:28~35.
〔15〕赵书河.多源遥感图像决策级融合及其应用研究〔D〕.博士学位论文,南京:南京大学,2003.44~45.
〔16〕Zhang W C, Yamaguchi Y, Ogaw K. Evaluation of the Preprocessing of the Remotely Sensed Data on the Actual Evapotraspiration, Surface Soil Moisture Mapping by an Approach Using Landsat,DEM and Meteorological Data〔J〕.Geocarto Inter, 2000, 15(4):57~67.
〔17〕Civico D L. Topographic Normalization of Landsat Thematic Mapper Digital Imagery〔J〕. PE &RS, 1989, 55(9):1303~1309.
〔18〕Gilabert M A, Conese C, Maselli F. An Atmospheric Correction Method for the Automatic Retrieval of Surface Reflectance from TM Images〔J〕. Int J Remote Sensing, 1994, 15(10): 2065~2086.

No Suggested Reading articles found!