面向遥感影像匹配的特征点检测算子性能评估

叶沅鑫; 慎利

doi:10.3969/j.issn.0258-2724.2016.06.017

面向遥感影像匹配的特征点检测算子性能评估

doi: 10.3969/j.issn.0258-2724.2016.06.017

叶沅鑫^1,2,
慎利^1, ,

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）

详细信息

作者简介:
叶沅鑫(1985-),男,讲师,研究方向为遥感图像处理,E-mail:yeyuanxin110@163.com

通讯作者:
慎利(1986-),男,讲师,研究方向为机器学习与遥感影像处理,E-mail:rsshenli@outlook.com

计量
- 文章访问数: 572
- HTML全文浏览量: 92
- PDF下载量: 267
- 被引次数: 27
出版历程
- 收稿日期: 2015-09-16
- 刊出日期: 2016-12-25

Performance Evaluation of Interest Point Detectors for Remote Sensing Image Matching

YE Yuanxin^1,2,
SHEN Li^{1
, ,}

摘要

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.
- 遥感影像 /
- 影像匹配 /
- 特征点检测 /
- 重复率
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.
- remote sensing images /
- image matching /
- interest point detection /
- repeatability

HTML全文

参考文献(15)

叶沅鑫,单杰,彭剑威,等. 利用局部自相似进行多光谱遥感影像自动配准[J]. 测绘学报,2014,43(3):268-275. YE Yuanxin, SHAN Jie, PENG Jianwei, et al. Automated multispectral remote sensing image registration using local self-similarity[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(3):268-275.

张帅毅,李永树,蔡国林. 基于贝叶斯决策的航空影像自动配准[J]. 西南交通大学学报,2015,50(1):161-166. ZHANG Shuaiyi, LI Yongshu, CAI Guolin. Aerial image registration based on Bayesian decision theory[J]. Journal of Southwest Jiaotong University, 2015, 50(1):161-166.

YE Yuanxin, SHEN Li, WANG Jicheng, et al. Automatic matching of optical and SAR imagery through shape property[C]//2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).:IEEE, 2015:1072-1075.

叶沅鑫,单杰,熊金鑫,等. 一种结合SIFT和边缘信息的多源遥感影像匹配方法[J]. 武汉大学学报:信息科学版,2013,38(10):1148-1151. YE Yuanxin, SHAN Jie, XIONG Jinxin, et al. A matching method combining SIFT and edge information for multi-source remote sensing images[J]. Geomatics and Information Science of Wuhan University, 2013, 38(10):1148-1151.

ZITOV B, FLUSSER J. Image registration methods:a survey[J]. Image Vis. Comput., 2003, 21(11):977-1000.

YE Yuanxin, SHAN Jie. A local descriptor based registration method for multispectral remote sensing images with non-linear intensity differences[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 90:83-95.

SMITH S, BRADY J. SUSAN:a new approach to low level image processing[J]. International Journal of Computer Vision, 1997, 23(1):45-78.

LINDEBERG T. Feature detection with automatic scale selection[J]. International Journal of Computer Vision, 1998, 30(2):79-116.

MIKOLAJCZYK K, SCHMID C. Scale affine invariant interest point detectors[J]. International Journal of Computer Vision, 2004, 60(1):63-86.

MIKOLAJCZYK K, TUYTELAARS T, SCHMID C, et al. A comparison of affine region detectors[J]. International Journal of Computer Vision, 2005, 65(1):43-72.

LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.

MATAS J, CHUM O, URBAN M, et al. Robust wide-baseline stereo from maximally stable extremal regions[J]. Image and Vision Computing, 2004, 22(10):761-767.

TUYTELAARS T, MIKOLAJCZYK K. Local invariant feature detectors:a survey[J]. Foundations and Trends in Computer Graphics and Vision, 2008, 3(3):177-280.

SCHMID C, MOHR R, BAUCKHAGE C. Evaluation of interest point detectors[J]. International Journal of Computer Vision, 2000, 37(2):151-172.

AANS H, DAHL A L, STEENSTRUP PEDERSEN K. Interesting interest points[J]. International Journal of Computer Vision, 2011, 97(1):18-35.

施引文献

期刊类型引用(9)

1.	排日旦·阿布都热依木，吐尔地·托合提，艾斯卡尔·艾木都拉. 基于深度学习的实体关系抽取方法研究. 计算机工程与科学. 2023(05): 895-902 . 百度学术
2.	王晟全，陈济颖，王奕翔，李昂，李鑫. 无监督网络对抗生成模型的研究. 计算机技术与发展. 2020(04): 89-93 . 百度学术
3.	阳小华，张硕望，欧阳纯萍. 中文关系抽取技术研究. 南华大学学报(自然科学版). 2018(01): 66-72 . 百度学术
4.	王旭阳，姜喜秋. 特定领域概念属性关系抽取方法研究. 吉林大学学报(信息科学版). 2017(04): 430-437 . 百度学术
5.	刘婧，赵嵩正，张小娣. 基于核的关系抽取研究综述. 计算机应用研究. 2016(02): 321-329 . 百度学术
6.	徐庆，段利国，李爱萍，阴桂梅. 基于实体词语义相似度的中文实体关系抽取. 山东大学学报(工学版). 2015(06): 7-15 . 百度学术
7.	翟东海，崔静静，聂洪玉，杜佳. 基于语义相似度的话题关联检测方法. 西南交通大学学报. 2015(03): 517-522 . 本站查看
8.	王李冬，张引，吕明琪. 基于词组主题建模的文本语义压缩算法. 西南交通大学学报. 2015(04): 755-763 . 本站查看
9.	梁军，张飞云，陈龙，李世浩，顾胜强，张婉婉. 一种新型多核判别分析方法. 西南交通大学学报. 2015(06): 1122-1129 . 本站查看