引用本文:侯 飞,胡召玲,成 晨. 全极化SAR图像的煤矿区土地覆盖信息分层提取方法研究[J]. 中国生态农业学报(中英文), 2013, 21(9): 1142-1148
HOU Fei,HU Zhao-Ling,CHENG Chen. Hierarchical extraction of land cover information from fully polarimetric SAR image of coal mining areas[J]. Chinese Journal of Eco-Agriculture, 2013, 21(9): 1142-1148
DOI:10.3724/SP.J.1011.2013.01142
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  下载PDF阅读器   关闭   
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 1571次   下载 1630 本文二维码信息
码上扫一扫!
分享到: 微信 更多
全极化SAR图像的煤矿区土地覆盖信息分层提取方法研究
侯 飞1, 胡召玲2, 成 晨2
1.江苏师范大学测绘学院 徐州 221116;2.江苏师范大学城市与环境学院 徐州 221116
摘要:  为弥补光学遥感在煤矿区资源与生态环境监测中应用的不足, 研究应用全极化SAR图像有效提取煤矿区土地覆盖信息的方法具有重要意义。针对全极化SAR图像极化信息丰富、斑点噪声多、局部异质性大等特点, 提出采用面向对象的影像分类方法对其进行分层土地覆盖信息提取。以徐州市西南部的煤矿区为研究区, 选取Radarsat-2的全极化SAR图像, 分析了研究区内全极化SAR图像中典型地物的灰度特征, 提出面向对象分类方法所涉及的最优分割尺度选择法, 给出全极化SAR图像分割对象后向散射特征的计算方法。对研究区的SAR图像进行试验, 首先对SAR图像进行多尺度分割, 选择各土地覆盖类型的最优分割尺度, 然后在该尺度下计算出土地覆盖类型的后向散射特征指数, 最后采用模糊逻辑分类法分层提取出研究区内的土地覆盖信息。结果表明: 在适于各土地覆盖类型提取的最优分割尺度下, 充分利用分割对象的灰度、形状、纹理以及类间相关特征, 并综合应用隶属函数法和最邻近分类法, 能有效地提取煤矿区的农田、道路、塌陷地、建筑物、山林这5类土地覆盖信息。与最大似然分类法相比, 该方法能够较好地消除"椒盐现象", 各种土地覆盖类型的提取精度都有所提高, 其总体分类精度可提高38.3%。
关键词:  全极化SAR图像 面向对象 多尺度分割 分类精度 土地覆盖 煤矿区
中图分类号:
基金项目:国家自然科学基金项目(41101428)和现代工程测量国家测绘局重点实验室开放课题(TJES1204)资助
Hierarchical extraction of land cover information from fully polarimetric SAR image of coal mining areas
HOU Fei1, HU Zhao-Ling2, CHENG Chen2
1.School of Geodesy and Geomatics, Jiangsu Normal University, Xuzhou 221116, China;2.School of Urban and Environmental Sciences, Jiangsu Normal University, Xuzhou 221116, China
Abstract:  An effective approach of extracting land cover information from fully polarimetric SAR images has been compensating for the lack of optical remote sensing data. This approach has also promoted the application of SAR technology in resources and ecological monitoring in coal mining areas. With abundant polarimetric information, speckle and large local heterogeneity of fully polarimetric SAR images, this study proposed an object-oriented image classification approach for hierarchical extraction of land cover information. The study area was a coal mining region in the southwest of Xuzhou City and the SAR image acquired by Radarsat-2 for a fully polarimetric image. The gray features of typical surface objects of SAR images for the study area were analyzed. The optimal segmentation scale for object-oriented image classification was proposed. The computation approach of backscatter features of segmentation objects was also presented. Also ground-truth data were collected on the land cover to verify the SAR image for the study area. In the first step, the SAR image was segmented into several scales and the optimal segmentation scale of each land cover type selected. In the second step, the backscatter feature indexes of each land cover type were calculated under the optimal segmentation scale. Then in the last step, the land cover information in the study area was hierarchically extracted using the fuzzy logic classification method. The results showed that the proposed approach accurately extracted the five types of land cover information under the optimal segmentation scales of land cover type, including farmland, road, subsidence land, building and mountain woodland. In terms of gray, shape, texture and class-related features of the segmentation objects, the membership function and nearest neighbor classification approaches weakened the "pepper phenomenon". Compared with the maximum likelihood classification method, the classification accuracy of each land cover type improved while the average classification accuracy improved by 38.3%. In particular, the classification accuracy of farmland was as high as 90.2%, an improvement of 42.0% due to use of texture features in the classification.
Keyword:  Fully polarimetric SAR image, Object-oriented method, Multiple-scale segmentation, Classification accuracy, Land cover, Coal mining area
您是第 6000725 位访问者  冀ICP备05003362号-2
版权所有 ©《中国生态农业学报(中英文)》编辑部
地址:河北省石家庄市裕华区槐中路286号 050022 电话:0311-85818007 E-mail:editor@sjziam.ac.cn
技术支持:北京勤云科技发展有限公司