| 基于多元局部二值模式的遥感图像纹理提取与分类 |
| |
| 引用本文： | 宋翠玉,李培军,杨锋杰.基于多元局部二值模式的遥感图像纹理提取与分类[J].遥感技术与应用,2011,26(3):322-327. |
| |
| 作者姓名： | 宋翠玉 李培军 杨锋杰 |
| |
| 作者单位： | (1.山东科技大学山东省沉积成矿作用与沉积矿产重点实验室,山东 青岛266510；;
2.北京大学遥感与地理信息系统研究所,北京100871) |
| |
| 摘 要： | 纹理信息已经广泛应用于遥感图像分类以提高地物识别的精度。为了描述多光谱遥感图像多个波段之间的空间信息变化规律，将新型纹理提取算法局部二值模式（Local Binary Pattern，LBP）扩展到多维空间以计算多元纹理。单波段纹理信息、多元纹理信息分别与光谱信息结合后用于遥感图像分类，并根据分类精度评价其有效性。实验表明，加入单波段或多元纹理信息的分类精度均比光谱分类有明显提高；基于多元LBP纹理的分类不仅避免了传统单波段纹理参与分类前进行波段选择的繁琐，其精度还能与基于单波段纹理分类精度最高者相当或者更高。
|
| 关 键 词： | 局部二值模式 多元纹理 纹理提取 支持向量机(SVM) 精度评价 |
Remote Sensing Image Classification based on Texture Features by Multivariate Local Binary Pattern |
| |
| SONG Cui-yu,LI Pei-jun,YANG Feng-jie.Remote Sensing Image Classification based on Texture Features by Multivariate Local Binary Pattern[J].Remote Sensing Technology and Application,2011,26(3):322-327. |
| |
| Authors: | SONG Cui-yu LI Pei-jun YANG Feng-jie |
| |
| Affiliation: | (1.Shandong University of Science and Technology,Shandong Provincial Key Laboratory of;
Depositional Mineralization & Sedimentary Minerals,Qingdao 266510,China; ;
2.Remote Sensing and GIS Institute,Peking University,Beijing 100871,China) |
| |
| Abstract: | Texture has been widely used in remote sensing image classification to improvethe classification result.In this paper,the recently developed texture measure Local Binary Pattern(LBP) was extended to a multivariate version to characterize the multivariate spatial correlation among multiple bands of multispectral image.The derived single-band and multivariate texture features were then individually combined with the spectral data in image classification to evaluate the performance of the texture measure.Exper... |
| |
| Keywords: | Local Binary Pattern Multivariate texture Texture extraction Support Vector Machine(SVM) Assessment of accuracy |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《遥感技术与应用》浏览原始摘要信息 |
|
点击此处可从《遥感技术与应用》下载全文 |
