Yu-liang QIAO(乔玉良)
College of Mining Technology, Taiyuan University of Technology, T aiyuan 030024, China
Abstract-With rapid development of remote sensing technology, the resolution of remote sensing images is increasingly improved; then people ca n extract more useful data and information from these images. Thus, an important information extraction method from remote sensing images-image classification, becomes more and more important. Based on phenophase and band composition chara cteristics, this paper firstly discusses the important role of background parame ters in remote sensing images classification; then based on geographical informa tion system technology, the computerized automatic classification to high-mediu m-low-yield croplands in Dingxiang County of Shanxi Province in remote sensing images has been carried out by using compound layers classification method of m ulti-thematic information; compared the classification result to the visual int erpretation results, the accuracy increases from 70% to above 90%.
Key words-remote sensing classification; background par ameters; thematic information; band composition; geographical information system
Manuscript Number: 1674-8042(2010)04-0317-06
dio: 10.3969/j.issn.1674-8042.2010.04.04
Reference
[1]M. Baatz, A. Schabpe, 1999. Object Oriented and Multi Scale Image An alysis in Semantic Networks. Proc. of the 2nd International Symposium on Operati onalization of Remote Sensing， Enschede. ITC.
[2]A. J. Tatem, H. G. Lewis, P. Atkinson, et al, 2001. Super resolution target identification from remotely sensed images using a hopfield neural netwo rk. IEEE Transactions on Geosciences and Remote Sensing, 39 ( 4): 781-796.
[3]X. Yu, I. S. Reed, A. D. Stocker, 2003. Comparative performance anal ysis of adaptive multispectral detectors. IEEE Trans on Signal Process ing, 41(8): 235-240.
[4]F. A. Kruse, A. B. Lefkoff, J. B. Boardman, 1993. The spectral image processing system (SIPS)-interactive visualization and analysis of imaging spe ctrometer data. Remote Sensing of Environment, 44: 145-163.
[5]J. R. Jensen, 1986. Introductory Digital Image Processing: A Remote Sensing Perspective. Publisher: Prentice Hall. Englewood Cliffs, New Jersey.
[6]J. C. Harsanyi, C. I. Chang, 1994. Hyper spectral image classificati on and dimensionality reduction: an orthogonal subspace projection approach. IEEE Transactions on Geosciences and Remote Sensing, (32): 779- 785.
[7]Su-xing Fu, 1998. Application and analysis of background parameter s in thematic mapping by remote sensing. Research on Geography, 2: 23-27.
[8]Enpu Wan, 1996. Yield Estimation and Remote Sensing Dynamic Monitori ng on Maize in China. Chinese Science and Technology Press. Beijing.
[9]Nai-bin Wang, 1996. Yield Estimation and Remote Sensing Dynamic Mon itoring on Wheat in China. Chinese Science and Technology Press. Beijing.
[10]Rui Zhao, 1996. Yield Estimation and Remote sensing Dynamic Monitor ing on Rice in China. Beijing: Chinese Science and Technology Press.
[11]Li-ya Xiong, 1996.Integrated System for Crop Remote Sensing Dynami c Monitoring and Yield Estimation in China. Chinese Science and Technology Press . Beijing.
[12]Su-xing Fu, Chong-hou Zhang, Xiou-yun Li, 1996. Regional paramet ers’ application research on classification mapping of image information. China Journal of Image and Graphics, 1(2): 146-148.
[13]Yu-liang Qiao, 2002. Study on classification methods for high, med ium and low yield farmlands in loess regions. Journal of Remote Sensin g, 6(1): 70-74.
[14]Yu-liang Qiao, 2000. Divisional compound hierarchical classificati on method for regionalization of high, medium and low yield croplands of china. Adv. Space Res, 29(1): 89-93.
[15]Yu-liang Qiao, 2000. Study on monitoring farmland by using remote sensing and GIS in shanxi china. Adv. Space Res, 26(7): 1059 -1064.
[16]Jiu-lin Sun. 1996. Overall Discussion on Dynamic Monitoring Crops and Yield Estimation in China by Using Remote Sensing. Beijing: Chinese Science and Technology Press.
[full text view]
