| 面向遥感影像匹配的特征点检测算子性能评估 |
| |
| 引用本文： | 叶沅鑫,慎利.面向遥感影像匹配的特征点检测算子性能评估[J].西南交通大学学报,2016,29(6):1170-1176. |
| |
| 作者姓名： | 叶沅鑫 慎利 |
| |
| 基金项目： | 国家973计划资助项目（2012CB719901）国家自然科学基金资助项目（41401369，41401374） |
| |
| 摘 要： | 在基于特征点的匹配方法中，特征点检测是非常关键的步骤，直接影响到匹配的效果.为了确立遥感影像匹配过程中特征点算子的选择依据，本文从光谱、时相和尺度（分辨率）3个方面，选择不同类型的遥感影像作为实验数据，以特征点重复率作为评估标准，对当前主流的Harris-Laplace、Hessian-Laplace、DoG和MSER 4种特征点检测算子进行性能评估，并分析了每一种算子的优缺点和适用范围.实验结果表明:在光谱和时相方面，Hessian-Laplace的平均重复率达到40%，性能最好，其次为Harris-Laplace和DoG，而MSER的性能相对较弱；而对于尺度方面，MSER表现出最好的性能，平均重复率达到35%，其次为Hessian-Laplace，而Harris-Laplace和DoG的性能较弱.
|
| 关 键 词： | 遥感影像 影像匹配 特征点检测 重复率 |
| 收稿时间： | 2015-09-16 |
Performance Evaluation of Interest Point Detectors for Remote Sensing Image Matching |
| |
| YE Yuanxin,SHEN Li.Performance Evaluation of Interest Point Detectors for Remote Sensing Image Matching[J].Journal of Southwest Jiaotong University,2016,29(6):1170-1176. |
| |
| Authors: | YE Yuanxin SHEN Li |
| |
| Abstract: | Interest point detection is a crucial step for the image matching because it directly influences the matching results. In order to establish the criterion of selecting the interest point detectors for remote sensing image matching, different remote sensing images in terms of spetrum, time and scale were selected to evaluate the four famous interest point detectors including Harris-Laplace, Hessian-Laplace, Difference of Gaussian (DoG) and Maximally Stable Extremal Regions (MSER), and the repeatability was used as the evaluation criterion. The merits, the demerits and application of these detectors were also discussed. The experimental results show that for spectrum and time variation, the repeatability of Hessian-Laplace detector achieves 40% whichperforms best, followed by Harris-Laplace and DoG, whereas MSER performs worst. For image scale changes, MSER outperforms other detectors and its repeatability is 35%, followed by Hession-Laplace, whereas Harris-Laplace and DoG perform worse than other detectors. |
| |
| Keywords: | |
|
| 点击此处可从《西南交通大学学报》浏览原始摘要信息 |
|
点击此处可从《西南交通大学学报》下载全文 |
|
