Classification of Alpine Wetlands Based on Feature Indices of Remote Sensing Image

Abstract:

Based on the brightness, greenness, humidity indices after Tasseled Cap transformation, NDWI and DEM. Extracting the alpine wetland information in source regions of three Rivers. Result shows that: the humidity can be used to distinguish wetland types from non-wetland classes, brightness component is effective in grassland extracting, while bare rock and gravel land, sand land etc. could be distinguished through its high value on lightness component. Elevation and slope component could be taken as the threshold variable in distinguishing the marsh and bare rock and gravel land. It shows that RS feature index based classification method used on Alpine wetland could improve the overall accuracy by 10.71% and Kappa index by 0.1250 after comparing with the maximum likelihood method. The result indicates that, the method based on indices got from image band transformation is an effective way of alpine wetlands information remote sensing extracting.

• Periodical: Key Engineering Materials (Volume 500)
• Pages: 579-585
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.500.579
• Online since: January 2012
• Authors: Wen Tao Zou, Huai Qing Zhang, Hong Bo Ju, Hua Liu
• Keywords: Accuracy Comparison, Alpine Wetland Information Exacting, Greenness Component after Tasseled Cap Transformation, Humidity Component after Tasseled Cap Transformation, NDWI

References

[1] Feng, S Q., Su, W J., Xiao, J. S , Water resources changing since 2000 in Three Rivers source region by Remote Sensing Investigation [J]. Qinghai Technology, 2008, 5: 20 ~ 26.

[2] Pan, H J., Wang, J., Wang, J.H., Dynamic Change of Frigid Wetlands in Source Region of the Yangtze and Yellow Rivers [J]. Wetland Science, 2007, 5 (4) : 298-304.

[3] Han, M., Cheng, L., Xing, J., Research on classification of land cover in Zhalong wetland area based on neural network [J]. Dalian University of Technology, 2004, 44 (4) : 582-588.

[4] Yao, Y.J., Zhang, Z.X., QIN, Q.M., Study on wetland information extraction of remote sensing images based on support vector machine[J]. Computer Applications, 2008, 25 (4) : 989-991.

[5] Ghioca-Robrecht, D. M, Johnston, C. A, & Tulbure, MG Assessing the use of multiseason QuickBird imagery for mapping invasive species in a Lake Erie coastal marsh. Wetlands. 2008, 28 (4), 1028-1039.

DOI: 10.1672/08-34.1

[6] Liu, J.B., DAI, C.D., Use of TM image in the detection and monitoring of large-scale reservoir. Environmental Remote Sensing, 1996, 11 (1): 53-58.

[7] Hanqiu Xu. Modification of Normalized Diference Water Index (NDWI) to Enhance 0pen Water Features in Remotely Sensed Imagery. International Journal of Remote Sensing, 2006, 27 (12); 3025-3033.

DOI: 10.1080/01431160600589179

[8] Lu, J.J., Li, Sh.H., Improvement of TM image water recognition technology [J]. Environmental Remote Sensing, 1992, 7 (1): l7-23.

[9] Friedl M, Brodley C, Strahler. Maximizing land cover classification accuracies produced by decision tree at continental to global scales. IEEE Transactions Geoscience and Remote Sensing, 1999, 37 (2) : 969-977.

DOI: 10.1109/36.752215

[10] Mei X.A., Peng, W.L., QIN, Q.M., Introduction to Remote Sensing [M]. Beijing: Higher Education Press, 2001: 155-156.

[11] Crist E P, Kauth R J. The Tasseled. Cap De-Mystified [J]. Photogram metric Engineering and Remote Sensing, 1986, 52 (1): 8l-85.

[12] McFeeters S K. The Use of normalized difference water index (NDWI) in the delineation of open water features [J]. International Jamal of Remote Sensing, 1996, 17 (7) : 1425-1432.

DOI: 10.1080/01431169608948714