| 一种面向对象的CVA变化检测方法 |
| |
| 引用本文： | 石善球.一种面向对象的CVA变化检测方法[J].测绘与空间地理信息,2017,40(11). |
| |
| 作者姓名： | 石善球 |
| |
| 作者单位： | 江苏省基础地理信息中心,江苏南京,210013 |
| |
| 基金项目： | 江苏省测绘科研基金项目 |
| |
| 摘 要： | 以两期0.3 m分辨率图像作为变化检测对象,辅以矢量数据,以图斑为最小处理单元,采用面向对象的变化矢量分析(Change Vector Analysis,CVA)方法预测变化图斑。为提高预测精度,图像的特征采用多尺度下的光谱、纹理和局部不变特征的方法提取。实验结果表明,本文采用的方法,其预测准确率与同尺度下图像特征提取的方法相比有了一定程度的提高。
|
| 关 键 词： | 面向对象 变化矢量分析 图像特征 变化图斑 |
An Object-oriented Method of CVA Change Detection |
| |
| SHI Shan-qiu.An Object-oriented Method of CVA Change Detection[J].Geomatics & Spatial Information Technology,2017,40(11). |
| |
| Authors: | SHI Shan-qiu |
| |
| Abstract: | In this paper, a two-phase 0.3-m resolution image is used as the object of change detection , with vector data as the minimum processing unit .The change vector analysis ( CVA) method is used to predict the change pattern .In order to improve the prediction accuracy , feature extraction of the image , multi-scale spectral , texture and local invariant feature extraction .The experi-mental results show that the proposed method is more accurate than the image feature extraction method at the same scale . |
| |
| Keywords: | object –oriented change vector analysis image feature change pattern |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
