Factors Affecting Decision Tree Classification Method over TM Image

ZHANG Lian-hua; PANG Yong; YUE Cai-rong; LI Zeng-yuan; FAN Ying-long; TAN Bing-xiang; CHE Xue-jian

Taking one scene TM image of Xishuangbanna of Yunnan as an example, the main factors affecting the classification and regression tree method were analyzed. The results show that in the parameters under identical circumstances, the training data has higher classification accuracy if the field investigation data covering all the classification data were used rather than the system layout data. It also shows that selecting various bands of parameters can also improve the precision of classification effectively.

1. Research Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, China

2. College of Forest, Southwest Forestry University, Kunming 650224, Yunnan, China

Received Date: 2013-03-20

Abstract: Taking one scene TM image of Xishuangbanna of Yunnan as an example, the main factors affecting the classification and regression tree method were analyzed. The results show that in the parameters under identical circumstances, the training data has higher classification accuracy if the field investigation data covering all the classification data were used rather than the system layout data. It also shows that selecting various bands of parameters can also improve the precision of classification effectively.

HTML

Reference (16)

[1]	李彤, 吴骅.采用决策树分类技术对北京市土地覆盖现状进行研究[J].遥感技术与应用, 2004, 19(6):485-487
[2]	陈云, 戴锦芳, 李俊杰.基于影像多种特征的CART决策树分类方法及其应用[J].地理与地理信息科学, 2008, 24(2):33-36
[3]	罗来平, 宫辉力, 赵文吉, 等.遥感图像决策树分类器研究与实现[J].遥感信息, 2006(3):13-15
[4]	Huang X, Jensen J R.A Machine-learning Approach to Automated Knowledge-based Building for Remote Sensing Image Analysis with GIS Data[J].Photogrammetric Engineering and Remote Sensing, 1997, 63(10):1185-1194
[5]	Wickham J D, Stehman S V, Smith J H, et al.Thematic Accuracy of the 1992 National Land-Cover Data for the Western United States[J]. Remote Sensing of Environment, 2004, 91:452-468
[6]	Lawrence R L, Wright A.Rule-Based Classification Systems Using Classification and Regression Tree (CART) Analysis[J].Photogrammetric Engineering and Remote Sensing, 2001, 67(10):1137-1142
[7]	齐乐, 岳彩荣.基于CART决策树方法的遥感影像分类[J].林业调查规划, 2011, 36(2):62-66
[8]	赵英时.遥感应用分析原理与方法[M].北京:科学出版社, 2003
[9]	韩涛.用TM资料对祁连山部分地区进行针叶林、灌木林分类研究[J].遥感技术与应用, 2002, 17(6):317-321
[10]	权维俊, 郭文利, 叶采华, 等.基于TM卫星影像获取北京市水体密度指数与植被覆盖指数的方法[J].南京气象学院学报, 2007, 30(5):610-616
[11]	韩丛丛, 逄杰武, 吴泉源, 等.TM影像中居民地提取的决策树方法研究——以烟台市为例[J].遥感信息, 2007(6):73-75
[12]	邸向红, 王周龙, 张明明, 等.基于决策树的蓬莱市土地覆盖信息提取[J].山东国土资源, 2009, 25(11):52-55
[13]	吴见, 彭道黎.基于TM影像的多伦县土地利用信息提取[J].东北林业大学学报, 2004, 38(10):88-94
[14]	Baraldi A, Puzzolo V, Blonda P, et al.Automatic Spectral Rule-based Preliminary Mapping of Calibrated Landsat TM and ETM+ Images[J].IEEE Transactions on Geoscience and Remote Sensing, 2006, 49(9):2563-2586
[15]	李石华, 王金亮, 陈姚, 等.多光谱遥感数据最佳波段选择方法试验研究[J].云南地理环境研究, 2005, 17(6):29-33
[16]	杨阿强.CBERS数据用于老挝土地覆被分类的方法论研究[D]. 北京:中国科学院地理科学与资源研究所, 2009

Factors Affecting Decision Tree Classification Method over TM Image

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views