| Bayesian and Geostatistical Approaches to Combining Categorical Data Derived from Visual and Digital Processing of Remotely Sensed Images |
| |
| 作者姓名： | ZHANGJingxiong LIDeren |
| |
| 作者单位： | professor,SchoolofRemoteSensingandInformationEngineering,WuhanUniversity,129LuoyuRoad,Wuhan430079,China. |
| |
| 摘 要： | This paper seeks a synthesis of Bayesian and geostatistical approaches to combining categorical data in the context of remote sensing classification. By experiment with aerial photographs and Landsat TM data, accuracy of spectral, spatial, and combined classification results was evaluated. It was confirmed that the incorporation of spatial information in spectral classification increases accuracy significantly. Secondly, through test with a 5-class and a 3-class classification schemes, it was revealed that setting a proper semantic framework for classification is fundamental to any endeavors of categorical mapping and the most important factor affecting accuracy. Lastly, this paper promotes non-parametric methods for both definition of class membership profiling based on band-specific histograms of image intensities and derivation of spatial probability via indicator kriging, a non-parametric geostatistical technique.
|
| 关 键 词： | 贝叶斯地理统计 遥感图像 计算机仿真 数据处理 |
| 收稿时间： | 12 February 2005 |
Bayesian and geostatistical approaches to combining categorical data derived from visual and digital processing of remotely sensed images |
| |
| ZHANGJingxiong LIDeren.Bayesian and Geostatistical Approaches to Combining Categorical Data Derived from Visual and Digital Processing of Remotely Sensed Images[J].Geo-Spatial Information Science,2005,8(2):90-97. |
| |
| Authors: | Zhang Jingxiong Li Deren |
| |
| Institution: | (1) School of Remote Sensing and Information Engineering, Wuhan University, 129 Luoyu Road, 430079 Wuhan, China |
| |
| Abstract: | This paper seeks a synthesis of Bayesian and geostatistical approaches to combining categorical data in the context of remote sensing classification.By experiment with aerial photographs and Landsat TM data, accuracy of spectral, spatial, and combined classification results was evaluated.It was confirmed that the incorporation of spatial information in spectral classification increases accuracy significantly.Secondly, through test with a 5-class and a 3-class classification schemes, it was revealed that setting a proper semantic framework for classification is fundamental to any endeavors of categorical mapping and the most important factor affecting accuracy.Lastly, this paper promotes non-parametric methods for both definition of class membership profiling based on band-specific histograms of image intensities and derivation of spatial probability via indicator kriging, a non-parametric geostatistical technique. |
| |
| Keywords: | Bayesian remote sensing image visual and digital processing |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
|
