| 基于图像显著性区域的遥感图像机场检测 |
| |
| 引用本文： | 王鑫,王斌,张立明.基于图像显著性区域的遥感图像机场检测[J].计算机辅助设计与图形学学报,2012,24(3):336-344. |
| |
| 作者姓名： | 王鑫 王斌 张立明 |
| |
| 作者单位： | 1. 复旦大学电子工程系 上海 200433
2. 复旦大学电子工程系 上海 200433;复旦大学波散射和遥感信息教育部重点实验室 上海 200433 |
| |
| 摘 要： | 针对已有方法对图像逐像素进行分析的不足,将人眼的注意力选择计算模型引入到遥感图像的机场目标检测中,提出一种基于图像显著性区域的遥感图像中机场目标检测与识别的方法,以提高自动目标检测的效率.首先利用霍夫变换对遥感图像中是否存在机场目标进行初步筛选,然后利用改进后的基于图像的视觉显著性模型提取显著性区域,根据区域上的尺度不变特征变换特征并结合多层分类回归树完成机场目标的识别.实验结果表明,该方法比现有的其他机场检测方法具有速度快、识别率高、虚警率低的特点,同时对噪声有较强的鲁棒性.
|
| 关 键 词： | 视觉注意 显著性区域 机场检测 尺度不变特征变换 多层分类回归树 霍夫变换 |
Airport Detection Based on Salient Areas in Remote Sensing Images |
| |
| Wang Xin
,
Wang Bin
,
Zhang Liming.Airport Detection Based on Salient Areas in Remote Sensing Images[J].Journal of Computer-Aided Design & Computer Graphics,2012,24(3):336-344. |
| |
| Authors: | Wang Xin Wang Bin Zhang Liming |
| |
| Affiliation: | 1) 1)(Department of Electronic Engineering,Fudan University,Shanghai 200433) 2)(The Key Laboratory of Wave Scattering and Remote Sensing In formation(Ministry of Education),Fudan University,Shanghai 200433) |
| |
| Abstract: | In this paper we propose a new airport detection and recognition method for remote sensing images based on salient areas with the introduction of visual attention models to improve the efficiency of automatic target detection.Firstly,Hough transform is used to judge the existence of an airport,and then the improved graph-based visual saliency(GBVS) model is used to extract regions of candidates(ROCs).According to the features with scale-invariant feature transform(SIFT),which are extracted from ROCs and classified by hierarchical discriminant regression(HDR) tree,the airport areas are recognized.Experimental results show that our method is faster with higher recognition rate and lower false alarm rate than other current methods,and is robust against white noise. |
| |
| Keywords: | visual attention salient areas airport detection scale-invariant feature transform hierarchical discriminant regression tree Hough transform |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
