基于高分辨率遥感影像分类的地图更新方法

基金项目: 国家自然科学基金资助项目(60175022)

详细信息

Application of Maps Revision Based on Classification of High Resolution Satellite Images

¹School of Remote Sensing and Information Engineering, Wuhan University, 129 Luoyu Road, Wuhan 430079, China

Funds: 国家自然科学基金资助项目(60175022)

摘要: 提出了一种在对遥感影像分类的基础上进行地图更新的方法,讨论了利用高分辨率遥感影像,通过不同空间分辨率和光谱分辨率的影像进行融合,利用合适的高通滤波对影像进行边缘检测,构建一个三层的 MLP分类器对影像进行分类,提取城市建筑物与道路信息,并在此分类基础上通过对现有地图的叠加来实现地图的更新。实验结果表明,基于影像融合,利用较少数量的训练样本也能生成具有较高精度的分类图,利用分类结果图进行地图更新能取得令人满意的效果。
- 影像融合 /
- 影像分类 /
- 地图更新
Abstract: On the basis of remote sensing image classification, this paper introduces a method for updating urban maps through high resolution remote sensing image. The RGB-HIS transformation technique is considered to merge spectral and spatial information, an appropriate filter for the edge extraction has been used. An MLP classifier is trained to produce a labeled image, focusing on urban buildings and roads, with great accuracy in test even if a limited training set is used. The result reveals a good feasibility of the classified image for monitoring the presence of changes in urban areas.
- image fusion /
- image classification /
- map revision