前期土地覆被数据辅助下的分类样本自动选取
收稿日期: 2012-01-16
修回日期: 2012-07-20
网络出版日期: 2012-08-22
基金资助
国家自然科学基金项目(40971224);国家"863"计划项目(2011AA20101)。
Automatic Selection of Classified Samples with the Help of Previous Land Cover Data
Received date: 2012-01-16
Revised date: 2012-07-20
Online published: 2012-08-22
Supported by
null
将地学知识与影像标定相结合,一直是目视解译或计算机自动分类制图的主要手段。传统的目视解译方法能够充分利用地学知识,但需要大量的人力、物力,效率较低;计算机分类中尚未出现比较成熟的高效运用地学知识的分类方法。已有研究表明,分类样本可以作为地学知识的载体,将地学知识融入分类过程中;此外,无监督聚类可以显著提高样本选取的效率,有助于提供足够的样本,为将地学知识高效地融入计算机分类提供了一定的基础。本文提出一种以前期土地利用数据辅助与影像聚类相结合的样本自动选取方法。利用自动选取的样本,通过最大似然分类器对TM影像进行分类,并与手动选取样本分类的方法进行了对比分析。研究结果表明,在分类效果上,本文提出的前期土地覆被辅助下的分类样本自动选取方法,优于手动选取样本的方法,提高了分类效率。在水体、林地、园地、城镇建设用地等7种类型上的分类整体精度达到84.18%,kappa系数为0.8066;手动选取样本进行分类的整体精度为77.04%,kappa系数为0.7196。
刘锟, 杨晓梅*, 张涛 . 前期土地覆被数据辅助下的分类样本自动选取[J]. 地球信息科学学报, 2012 , 14(4) : 507 -513 . DOI: 10.3724/SP.J.1047.2012.00507
The combination of geographical knowledge and image calibration has long been the principal means of both the traditional visual interpretation and computer automatic classification in remote sensing mapping. Traditional visual interpretation could use the geographic knowledge well because of the artificial participation. However, it goes with the shortcomings that visual interpretation needs a lot of labor and is less efficient. In addition, the computer classification has not applied geographic knowledge in a proper way. Studies have shown that samples as the carrier of geographic knowledge can integrate geographic knowledge into the classification process to some extent. Meanwhile, unsupervised clustering can significantly improve the efficiency of sample selection and solve the problem of scarcity of samples in order to meet the requirement of distribution and purity. These studies provide a basic foundation for integration of geographic knowledge with computer classification. This paper presents an automatic sample selecting method which integrates image clustering with the aid of previous land cover data. The samples were selected automatically based on the TM images by the method mentioned above and used to classify the image later by the maximum likelihood classifier. We also classified the image using the manual samples by the maximum likelihood classifier in order to compare the classified results produced by these two kinds of samples. The test results indicated that the proposed method achieved an overall accuracy of 84.18% and a kappa coefficient of 0.8066 in seven categories, including water body, forest land, orchard and urban construction land. The method proposed in this paper is more efficient than the way of samples selected manually and provides better classification results.
Key words： classification; samples; select automatically; LUCC
[1] 术洪磊,毛赞猷. GIS辅助下的基于知识的遥感影像分类方法研究——以土地覆盖/土地利用类型为例[J].测绘学报,1997(4):328-326.
[2] 张峰,王桥,王文杰,等. 美国高分辨率土地覆盖信息提取技术研究进展[J].遥感技术与应用,2008(6):593-600.
[3] 孙秀邦,范伟,严平,等. 遥感影像土地覆被分类研究进展[J].中国农学通报,2007(9):607-610.
[4] 韩文萍,王金亮,可华明,等. 基于GIS的遥感影像土地利用/土地覆盖信息提取研究——以滇西北香格里拉县为例[J].云南地理环境研究,2007(2):98-102.
[5] 吴健平,杨星卫. 遥感数据监督分类中训练样本的纯化[J].国土资源遥感,1996(1): 36-41.
[6] 龚文瑜. GIS辅助遥感影像分类概述[J].地理空间信息,2006(2):15-17.
[7] 肖鹏峰,刘顺喜,冯学智,等. 中分辨率遥感图像土地利用与覆被分类的方法及精度评价[J].国土资源遥感,2004(4):41-45,79.
[8] Borgi A, Akdag H. Knowledge based supervised fuzzy-classification: An application to image processing[J]. Annals of Mathematics and Artificial Intelligence,2001,32(1):67-86.
[9] 游代安,蒋定华,余旭初. GIS辅助下的Bayes法遥感影像分类[J].测绘学院学报,2001(2):113-117.
[10] Shahshahani B M, Landgrebe D A. The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon[J]. IEEE Transactions on Geoscience and Remote Sensing,1994,32(5):1087-1095.
[11] 熊彪, 江万寿, 李乐林. 基于高斯混合模型的遥感影像半监督分类[J].武汉大学学报(信息科学版),2011(01):108-112.
[12] Bian X, Zhang T, Fang Z, et al. Cluster-based training data preselection and classification for remote sensing images. 2010 IEEE 10th International Conference on Signal Processing (ICSP). Beijing,2010,October.
[13] Vogelmann J, Sohl T, Campbell P and Shaw D. Regional land cover characterization using Landsat Thematic Mapper data and ancillary data sources[J]. Environmental Monitoring and Assessment,1998,51(1):415-428.
[14] Bartholomé E, Belward A. GLC2000: A new approach to global land cover mapping from Earth observation data[J]. International Journal of Remote Sensing,2005,26(9):1959-1977.
[15] 徐文婷,吴炳方,颜长珍,等. 用 SPOT-VGT 数据制作中国2000年度土地覆盖数据[J].遥感学报,2005,9(2):204-215.
[16] 刘勇洪,牛铮,徐永明. 基于 MODIS 数据设计的中国土地覆盖分类系统与应用研究[J].农业工程学报,2006,22(5):99-104.
[17] 张景华,封志明,姜鲁光. 土地利用/土地覆被分类系统研究进展[J].资源科学,2011(06):1195-1203.
[18] 刘纪远. 中国资源环境遥感宏观调查与动态研究[M].北京:中国科学技术出版社,1996.
[19] 陈百明,周小萍. "土地利用现状分类"国家标准的解读[J].自然资源学报,2008,22(6):994-1003.
[20] Edwards Jr. T C, Moisen G G, Cutler D R. Assessing map accuracy in a remotely sensed, ecoregion-scale cover map[J]. Remote Sensing of Environment,1998,63(1):73-83.
[21] 严红萍,俞兵. 主成分分析在遥感图像处理中的应用[J].资源环境与工程,2006,20(2):168-170.
[22] 高义,苏奋振,孙晓宇,等. 近20a广东省海岛海岸带土地利用变化及驱动力分析[J].海洋学报,2011,33(4):95-103.
/
| 〈 |
|
〉 |