我们的网站为什么显示成这样?

可能因为您的浏览器不支持样式,您可以更新您的浏览器到最新版本,以获取对此功能的支持,访问下面的网站,获取关于浏览器的信息:

|Table of Contents|

基于RF模型的高分辨率遥感影像分类评价(PDF)

《南京林业大学学报(自然科学版)》[ISSN:1000-2006/CN:32-1161/S]

Issue:
2015年01期
Page:
99-103
Column:
研究论文
publishdate:
2015-01-30

Article Info:/Info

Title:
Classification evaluation on high resolution remote sensing image based on RF
Article ID:
1000-2006(2015)01-0099-05
Author(s):
LIU Haijuan1 ZHANG Ting1 SHI Hao2 XU Yannan1* WU Wenlong1 Yu Peiling1
1.College of Forestry, Nanjing Forestry University, Nanjing 210037, China;
2.Environmental Monitoring Center of Jiangsu Province, Nanjing 210036, China
Keywords:
random forest remote sensing classification object-oriented characteristic variables
Classification number :
TP75
DOI:
10.3969/j.issn.1000-2006.2015.01.018
Document Code:
A
Abstract:
With the support of multi-scale segmentation of object-oriented classification method, features and characteristics variables were established and extracted by taking the QuickBird high-resolution remote sensing image as the main data source. High resolution remote sensing image classification model was built based on RF(Random Forest), the importance and sensitivity of characteristic variables to the model were analyzed. The research results showed that the optimal segmentation parameter in the study area was determined: segmentation scale parameter is 70, shape factor is 0.2, color factor is 0.8,and 32 characteristics such as spectrum, texture and shape variable information of eight landscape types were extracted; the overall accuracy of RF classification model which was built by choosing 5 000 trees and one node variable is 0.94, the Kappa coefficient was 0.93, OOB(Out of the Bag)data generalization error is 6.01%; through the analysis of the importance of variables, the importance value of spectral characteristics was obviously higher than that of shape features and texture features; based on mean decrease accuracy the overall accuracy is 0.94, the Kappa coefficient was 0.93 when 16 variables were used to built RF model; but they achieved the peak when 19 variables were used to built the model based on mean decrease Gini coefficient, the sensitivity analysis of the model which based on mean decrease accuracy was optimum than which based on mean decrease Gini coefficient. The feasibility of random forest model classification method should be further explored to provide scientific and rational reference for the high resolution remote sensing image classification.

References

[1] 马廷.高分辨率卫星影像及其信息处理的技术模型[J].遥感信息,2001,66(3):6-10.Ma T. High resolution satellite imagery and its technology model of information processing [J]. Remote Sensing Information, 2001, 66(3):6-10.
[2] Foody G M. Approaches for the production and evaluation of fuzzy land cover classifications from remotely-sensed data [J]. International Journal of Remote Sensing, 1996, 17(7): 1317-1340.
[3] Tso B, Mather P M. Classification methods for remotely sensed data[M]. London, New York: Taylor & Francis, 2001: 332.
[4] Pal M, Mather P M. An assessment of the effectiveness of decision tree methods for land cover classification[J]. Remote Sensing of Environment, 2003, 86(4):554-565.
[5] Gallego F J. Remote sensing and land cover area estimation [J]. International Journal of Remote Sensing, 2004, 25(15): 3019-3047.
[6] Rogan J, Franklin J, Stow D, et al. Mapping land-cover modifications over large areas: A comparison of machine learning algorithms [J]. Remote Sensing of Environment, 2008, 112(5):2272-2283.
[7] Dixon B, Candade N. Multispectral landuse classification using neural networks and support vector machines: one or the other, or both?[J]. International Journal of Remote Sensing, 2008, 29(4):1185-1206.
[8] Giacinto G, Roli F. An approach to the automatic design of multiple classifier systems[J]. Pattern Recognition Letters, 2001, 22(1): 25-33.
[9] Breiman L. Random forests [J]. Machine Learning, 2001, 45(1):5-32.
[10] Rodríguez-Galiano V F, Abarca-Hernández F, Ghimire B, et al. Incorporating spatial variability measures in land-cover classification using random forest [J]. Procedia Environmental Sciences, 2011, 3: 44-49.
[11] Gislason P O, Benediktsson J A, Sveinsson J R. Random forests for land cover classification [J]. Pattern Recognition Letters, 2006, 27(4): 294-300.
[12] Verikas A, Gelzinis A, Bacauskiene M. Mining data with random forests: A survey and results of new tests [J]. Pattern Recognition, 2011, 44(2): 330-349.
[13] Larivière B, Van den Poel D. Predicting customer retention and profitability by using random forests and regression forests techniques [J]. Expert Systems with Applications, 2005, 29(2): 472-484.
[14] Smith A, Sterba-Boatwright B, Mott J. Novel application of a statistical technique, Random Forests, in a bacterial source tracking study [J]. Water Research, 2010, 44(14): 4067-4076.
[15] Lee S L A, Kouzani A Z, Hu E J. Random forest based lung nodule classification aided by clustering[J]. Computerized Medical imaging and Graphics, 2010, 34(7): 535-542.
[16] 乌日汗,宋丽萍,温小荣,等.深圳特区城市绿地景观格局现状分析[J].南京林业大学学报:自然科学版, 2008,32(3): 79-82.Wu R H, Song L P, Wen X R, et al. Analysis of the current states on landscape pattern of urban green space in Shenzhen city[J]. Journal of Nanjing Forestry University: Natural Sciences Edition, 2008, 32(3):79-82.
[17] 张存.基于Quick Bird影像的面向对象信息提取方法比较实验研究[D].哈尔滨:东北大学,2009.Zhang C. Comparative experimentation study on information extraction of object-oriented based on quick bird image [D]. Harbin: Northeastern University, 2009.
[18] Haralick R M, Shanmugam K, Dinstein I H. Textural features for image classification [J]. IEEE Transactions on Systems, Man and Cybernetics, 1973(6): 610-621.
[19] Rodriguez-Galiano V F, Ghimire B, Rogan J, et al. An assessment of the effectiveness of a random forest classifier for land-cover classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 67: 93-104.
[20] 李欣海.随机森林模型在分类与回归分析中的应用[J].应用昆虫学报,2013,50(4):1190-1197.Li X H.Using “random forest” for classification and regression [J]. Applied Entomology, 2013, 50(4):1190-1197.

Last Update: 2015-01-31