| 高分辨率SAR图像中建筑物特征融合检测算法 |
| |
| 引用本文： | 苏娟,张强,陈炜,王继平.高分辨率SAR图像中建筑物特征融合检测算法[J].测绘学报,2014,43(9):939-944. |
| |
| 作者姓名： | 苏娟 张强 陈炜 王继平 |
| |
| 作者单位： | 1. 第二炮兵工程大学;
2. 第二炮兵装备研究院 |
| |
| 摘 要： | 针对高分辨率SAR图像中的建筑物检测问题，提出了一种基于视觉注意和特征融合的检测算法。首先，根据SAR图像中建筑物目标与背景存在较大差异的特点，采用视觉注意机制进行建筑物的感兴趣区分割；然后，提取位于感兴趣区域内的高亮线条和阴影区域；最后，采用D-S证据理论对注意焦点、高亮线条和阴影区域进行特征融合，实现建筑物目标的检测。实验结果表明，本文算法对矩形建筑物具有较高的检测精度。
|
| 关 键 词： | SAR图像处理 建筑物检测 视觉注意机制 D-S证据理论 特征融合 |
| 收稿时间： | 2014-02-14 |
| 修稿时间： | 2014-05-15 |
A Building Detection Algorithm Based on Feature Fusion in High Resolution SAR Images |
| |
| SU Juan,ZHANG Qiang,CHEN Wei,WANG Jiping.A Building Detection Algorithm Based on Feature Fusion in High Resolution SAR Images[J].Acta Geodaetica et Cartographica Sinica,2014,43(9):939-944. |
| |
| Authors: | SU Juan ZHANG Qiang CHEN Wei WANG Jiping |
| |
| Institution: | 1. The Second Artillery Engineering University;
2. The Second Artillery Equipment Institute |
| |
| Abstract: | A building detection algorithm based on visual attention and feature fusion is proposed for high spatial resolution SAR images. Firstly, visual attention model is constructed on the basis of great difference between buildings and backgrounds, and used to segment the ROIs of buildings. Secondly, bright lines and shadow regions are extracted in the segmented ROIs. Finally, D-S evidence theory is used to fusion the focus of attention, bright line and shadow region, and then the buildings are detected. Experimental results demonstrate that, the proposed algorithm has high detection accuracy for rectangular buildings in SAR images. |
| |
| Keywords: | SAR image processing building detection visual attention model D-S evidence theory feature fus i on |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《测绘学报》浏览原始摘要信息 |
| 点击此处可从《测绘学报》下载免费的PDF全文 |
