Hyperspectral remote sensing image classification with extremely randomized clustering forests

被引：0
|
作者：
Xu H.-W. [1 ]
Yang M.-H. [1 ]
Han R.-M. [2 ]
Wang Z.-X. [3 ,4 ]
机构：
[1] School of Geosciences and Info-Physics, Central South University
[2] School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, Henan Province
[3] School of Metallurgical Science and Engineering, Central South University
[4] South China Institute of Environmental Sciences, Ministry of Environmental Protection
来源：
Yingyong Kexue Xuebao/Journal of Applied Sciences | 2011年 / 29卷 / 06期
关键词：
Automatic image classification; Extremely randomized clustering forests (ERC-forests); Hyperspectral remote sensing; Land cover classification; Pattern classification;
D O I：
10.3969/j.issn.0255-8297.2011.06.008
中图分类号：
学科分类号：
摘要：
Hyperspectral images contain rich spectral information and have better performance in ground target recognition than panchromatic and multispectral images. An extremely randomized clustering forests (ERC-Forests) algorithm is introduced after analysis of the decision tree algorithm. Hyperion hyperspectral images and IRS-p6 image data of Qilian County, Qinghai Province, are used in the experiment. After dimension reduction with subspace methods and based on the spectral range, support vector machine (SVM), neural network (NN) and maximum likelihood (MLC) are used for classification. The results are compared with that of random decision trees algorithm, showing that the extremely randomized clustering forests algorithm is better, without dimension reduction. The method is widely applicable to hyperspectral remote sensing.
引用
下载
收藏
页码：598 / 604
页数：6
相关论文
共 13 条
  • [1] Wang K., Franklin S.E., Guo X., Cattet M., Remote sensing of ecology, biodiversity and conservation: A review from the perspective of remote sensing specialists, Sensor, 10, 11, pp. 9647-9667, (2010)
  • [2] Turner W., Spector S., Gardiner N., Fladeland M., Stetling E., Steininger M., Remote sensing for biodiversity science and conservation, Trends in Ecology and Evolution, 18, 6, pp. 306-314, (2003)
  • [3] (2003)
  • [4] Tu T.M., Chen C.H., A fast two-stage classification method for high-dimensional remote sensing data, IEEE Transactions on Geosciences and Remote Sensing, 36, 1, pp. 182-191, (1998)
  • [5] Jia X., Richards J.A., Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification, IEEE Transactions on Geosciences and Remote Sensing, 37, 1, pp. 538-542, (1999)
  • [6] Gu Y., Zhang Y., Unsupervised subspace linear spectral mixture analysis for hyperspectral image, Image Processing, 2003, Proceedings of International Conference on Image Processing, 1, pp. 801-804, (2003)
  • [7] Yang J., Yin Q., Zhou N., An improved method of hyperspectral remote sensing data adaptive band selection, Remote Sensing Technology and Application, 22, 4, pp. 513-519, (2007)
  • [8] Breiman L., Random forests, Machine Learning, 45, 1, pp. 5-32, (2001)
  • [9] Geurts P., Ernst D., Wehenkel L., Extremely randomized trees, Machine Learning, 63, pp. 3-42, (2006)
  • [10] Moosmann F., Nowak E., Jurie F., Randomized clustering forests for image classification, IEEE Transactions on Pattern Analysis and Machine Intelligence, 30, 9, pp. 1632-1646, (2008)
12