基于SURF的图像配准改进算法

doi:10.6046/gtzyyg.2017.01.17

摘要
参考文献
相关文章
Metrics

全文: PDF(4260 KB)

HTML
输出: BibTeX | EndNote (RIS)

摘要

针对传统的加速鲁棒性特征（speeded-up robust features，SURF）算法在图像配准中的应用现状，结合图像分块策略和相对距离理论，提出一种基于SURF的图像配准改进算法。通过图像分块策略改善提取特征点分布的均匀性；在SURF算法初匹配基础上，引用相对距离理论剔除异常匹配点，从而提高特征点匹配的精度和可靠性。选取覆盖重庆市沙坪坝实验区的QuickBird卫星数据，以特征点正确匹配率和均方根误差RMSE为量化指标，对所提出的SURF改进算法的图像配准效果进行验证。实验结果表明，改进后的SURF算法的特征点正确匹配率达到88%以上，高于传统SURF算法的76%。通过相对距离剔除误匹配点后，最终配准结果的RMSE达到2.69个像元，符合图像配准的基本需求（RMSE在2个像元左右），具有一定的应用推广价值。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	胡华龙
	薛武
	秦志远

关键词 ：高分辨率全色影像(高分影像), 居民地提取, 小波变换(WT), 分形网络进化算法(FNEA), 基元级纹理特征, 基元合并

Abstract：

In view of the study status of traditional speeded-up robust features (SURF)algorithm, an improved image registration algorithm based on SURF was proposed in combination with the image blocking strategies and the relative distance theory. The proposed algorithm can improve image uniformity of the feature distribution by image blocking strategy and increase the matching accuracy of the feature point through relative distance theory. With the quantitative indicators of correct feature point matching rate and RMSE, the authors selected the QuickBird satellite data of Shapingba District in Chongqing as the test area to verify the image registration results by using the improved algorithm based on SURF. The results show that the correct feature point matching rate of improved SURF algorithm reached 88%, higher than that of the traditional SURF algorithm (the rate is 76%). Excluding the mismatching points by relative distance, the RMSE of the final registration results reached 2.69 pixels. It meets the basic need of high-precision image registration(the RMSE is 2 pixels around), achieves the automation of remote sensing image registration and thus has some promotional value.

Key words： high resolution panchromatic images residential area extraction wavelet transform (WT) fractal net evolution approach (FNEA) primitive-based texture feature primitive merging

收稿日期: 2015-06-25 出版日期: 2017-01-23

TP751.1

基金资助:

重庆市国土资源与房屋管理局2010年科技计划项目“面向土地利用分类体系的高分辨率遥感影像变化检测应用技术研究”（编号：[2011]51-01号）和国家测绘地理信息局2014年基础测绘科技项目“面向地理国情监测的信息化测绘生产技术升级改造”（编号：[2012]56号）共同资助。

通讯作者: 郝建明(1990-),男,硕士研究生,主要研究方向为3S信息处理与集成应用。Email:jaminhoh@hotmail.com。

作者简介: 潘建平(1976-),男,教授,博士,主要从事摄影测量与遥感等方面的研究。Email:6370554@qq.com。

引用本文:

潘建平, 郝建明, 赵继萍. 基于SURF的图像配准改进算法[J]. 国土资源遥感, 2017, 29(1): 110-115.
PAN Jianping, HAO Jianming, ZHAO Jiping. Improved algorithm based on SURF for image registration. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(1): 110-115.

链接本文:

https://www.gtzyyg.com/CN/10.6046/gtzyyg.2017.01.17 或 https://www.gtzyyg.com/CN/Y2017/V29/I1/110

[1] Harris C,Stephens M.A combined corner and edge detector[C]//Proceedings of the 4th Alvey Conference.Manchester,UK:[s.n.],1988:147-152.
[2] You J,Bhattacharya P.A wavelet-based coarse-to-fine image matching scheme in a parallel virtual machine environment[J].IEEE Transactions on Image Processing,2009,9(9):1547-1559.
[3] Lowe D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[4] 刘小军,杨杰,孙坚伟,等.基于SIFT的图像配准方法[J].红外与激光工程,2008,37(1):156-160. Liu X J,Yang J,Sun J W,et al.Image registration approach based on SIFT[J].Infrared and Laser Engineering,2008,37(1):156-160.
[5] 张锐娟,张建奇,杨翠,等.基于SURF的图像配准方法研究[J].红外与激光工程,2009,38(1):160-165. Zhang R J,Zhang J Q,Yang C,et al.Image registration approach based on SURF[J].Infrared and Laser Engineering,2009,38(1):160-165.
[6] 高素青,谭勋军,黄承夏.一种基于SURF的图像配准改进算法[J].解放军理工大学学报:自然科学版,2013,14(4):372-376. Gao S Q,Tan X J,Huang C X.Improved algorithm of image registration based on SURF[J].Journal of PLA University of Science and Technology:Natural Science Edition,2013,14(4):372-376.
[7] 刘朝霞,安居白,邵峰,等.航空遥感图像配准技术[M].北京:科学出版社,2014:1-54. Liu Z X,An J B,Shao F,et al.Aerial Remote Sensing Image Registration Technology[M].Beijing:Science Press,2014:1-54.
[8] 杨占龙.基于特征点的图像配准与拼接技术研究[D].西安:西安电子科技大学,2008. Yang Z L.Research on Image Registration and Mosaic Based on Feature Point[D].Xi'an:Xidian University,2008.
[9] 陈超,秦其明,江涛,等.一种改进的遥感图像配准方法[J].北京大学学报:自然科学版,2010,46(4):629-635. Chen C,Qin Q M,Jiang T,et al.An improved method for remote sensing image registration[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2010,46(4):629-635.
[10] 范大昭,任玉川,贾博,等.一种基于点特征的高精度图像配准方法[J].地理信息世界,2007(5):66-70. Fan D Z,Ren Y C,Jia B,et al.A high precision image registration method based on point features[J].Geomatics World,2007(5):66-70.
[11] 龚咏喜,刘瑜,谢玉波,等.基于分块-空间聚类的图像配准算法[J].计算机工程与应用,2007,43(29):53-55. Gong Y X,Liu Y,Xie Y B,et al.Image registration algorithm based on blocking-spatial clustering[J].Computer Engineering and Applications,2007,43(29):53-55.
[12] 孙彬,边辉,王培忠.基于势函数点分布调整的SIFT图像配准算法[J].国土资源遥感,2015,27(3):36-41.doi:10.6046/gtzyyg.2015.03.07. Sun B,Bian H,Wang P Z.Image registration algorithm based on SIFT and potential function adjusting location of points[J].Remote Sensing for Land and Resources,2015,27(3):36-41.doi:10.6046/gtzyyg.2015.03.07.
[13] 李慧,蔺启忠,刘庆杰.基于FAST和SURF的遥感图像自动配准方法[J].国土资源遥感,2012,24(2):28-33.doi:10.6046/gtzyyg.2012.02.06. Li H,Lin Q Z,Liu Q J.An automatic registration method of remote sensing imagery based on FAST corner and SURF descriptor[J].Remote Sensing for Land and Resources,2012,24(2):28-33.doi:10.6046/gtzyyg.2012.02.06.

[1]	胡华龙, 薛武, 秦志远. 基于小波纹理和基元合并的高分影像居民地提取[J]. 国土资源遥感, 2017, 29(1): 21-28.
[2]	李文静, 温文鹏, 王清和. 基于Contourlet变换的遥感图像融合方法研究[J]. 国土资源遥感, 2015, 27(2): 44-50.

Viewed

Full text

Abstract

Cited

Shared

Discussed