Please wait a minute...
img

官方微信

遥感技术与应用  2022, Vol. 37 Issue (5): 1259-1266    DOI: 10.11873/j.issn.1004-0323.2022.5.1259
遥感应用     
基于边缘特征的多源高分辨率影像配准
闫恒1(),杨树文1,2,3(),薛庆1,张乃心1,付昱凯1
1.兰州交通大学 测绘与地理信息学院,甘肃 兰州 730070
2.地理国情监测技术应用国家地方联合工程研究中心,甘肃 兰州 730070
3.甘肃省地理国情监测工程实验室,甘肃 兰州 730070
Multisource High-resolution Image Registration based on Edge Feature
Heng Yan1(),Shuwen Yang1,2,3(),Qing Xue1,Naixin Zhang1,Yukai Fu1
1.Faculty of Geomatics,Lanzhou Jiaotong University,Lanzhou 730070,China
2.National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring,Lanzhou 730070,China
3.Gansu Provincial Engineering laboratory for National Geographic State Monitoring,Lanzhou 730070,China
 全文: PDF(6284 KB)   HTML
摘要:

针对多源高分辨率影像之间较大的非线性辐射差异和局部几何变形造成较差配准精度的问题,提出一种基于边缘特征的多源高分辨率影像配准方法。该方法首先通过各向异性扩散滤波构造输入影像的非线性尺度空间,在此基础上计算每一尺度的扩展相位一致性最大矩以获取丰富的边缘特征,并利用基于分块策略的FAST检测器提取稳定的特征点;其次利用多尺度多方向Log-Gabor滤波生成主方向索引图(Main Orientated Index Map,MOIM),并结合高斯加权构建一种稳健的特征描述子;最后采用巴氏距离和快速采样一致(Fast Sample Consensus,FSC)方法获取同名点。选择多组多源高分辨率影像进行实验,结果表明:该方法能够有效克服多源高分辨率影像间非线性辐射差异和局部几何变形,配准效果好于其他相关方法,并且平均配准精度优于1个像素。

关键词: 高分辨率影像配准边缘特征非线性辐射    
Abstract:

To address the problem of poor registration accuracy caused by large nonlinear radiometric differences and local geometric distortions between multisource high-resolution images, this paper proposes a multisource high-resolution image registration method based on edge features. Our method first constructs the nonlinear scale space for the input images by anisotropic diffusion filters, on the basis of which the extended phase congruency maximum moments are calculated for each scale to obtain rich edge features, and extracts stable feature points using a FAST detector based on a blocking strategy. Secondly, a Main Orientated Index Map (MOIM) was generated using multiscale Multi-Orientation Log-Gabor filters and combined with Gaussian weighting to construct a robust feature descriptor. Finally, the corresponding points are obtained using the Bhattacharyya distance and Fast Sample Consensus (FSC) method. Multiple sets of multisource high-resolution images are selected for experiments, and the results show that proposed method can effectively overcome nonlinear radiometric differences and local geometric distortions between multisource high-resolution images, with better registration results than other related methods, and an average registration accuracy of better than 1 pixel.

Key words: High-resolution    Image registration    Edge feature    Nonlinear radiation
收稿日期: 2021-06-01 出版日期: 2022-12-13
ZTFLH:  P237  
基金资助: 国家重点研发计划(地球观测与导航)“星空地遥感立体监测技术”(2017YFB0504201);国家自然科学基金项目“基于高分辨率卫星影像的彩钢板建筑与城市空间结构演变关系研究”(41761082);兰州交通大学优秀平台支持(201806)
通讯作者: 杨树文     E-mail: 2582885074@qq.com;ysw040966@163.com
作者简介: 闫 恒(1996-),男,内蒙古包头人,硕士研究生,主要从事遥感影像处理研究。E?mail:2582885074@qq.com
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  
闫恒
杨树文
薛庆
张乃心
付昱凯

引用本文:

闫恒,杨树文,薛庆,张乃心,付昱凯. 基于边缘特征的多源高分辨率影像配准[J]. 遥感技术与应用, 2022, 37(5): 1259-1266.

Heng Yan,Shuwen Yang,Qing Xue,Naixin Zhang,Yukai Fu. Multisource High-resolution Image Registration based on Edge Feature. Remote Sensing Technology and Application, 2022, 37(5): 1259-1266.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2022.5.1259        http://www.rsta.ac.cn/CN/Y2022/V37/I5/1259

图1  Log-Gabor小波基本形状
图2  特征提取结果
图3  描述子构建过程
图4  实验影像对
图5  三种方法的匹配结果对比
图6  本文方法配准结果的棋盘格镶嵌及局部放大图
评价标准第一组第二组第三组第四组
PSO-SIFTLGHD本文方法PSO-SIFTLGHD本文方法PSO-SIFTLGHD本文方法PSO-SIFTLGHD本文方法
NCM1211453761272033861410216672142533
DQ0.652 90.933 30.468 80.836 40.629 30.603 22.179 41.101 60.622 70.957 30.713 60.723 5
RMSE1.226 20.905 80.884 70.910 50.706 20.689 32.622 91.885 51.326 01.332 91.262 40.646 5
T (s)34.8100.738.185.870.552.728.384.614.018.912.513.4
表1  3种方法的配准结果
组别

尺寸

(参考影像/待配准影像)

评价标准
RMSET (s)
1局部4 136×3 587 4 308×3 7370.948 3197.3
整景24 444×24 563 18 147×18 1471.346 41983.2
2局部2 838×2 704 2 000×2 0001.249 9272.5
整景4 352×4 608 6 835×6 9921.562 8730.6
表2  整景多源遥感影像的配准结果
图7  整景影像配准结果的棋盘格镶嵌及局部放大图
1 Zitova B, Flusser J. Image registration methods: A survey[J]. Image and Vision Computing,2003,21(11):977-1000. DOI: 10.1016/S0262-8856(03)00137-9 .
doi: 10.1016/S0262-8856(03)00137-9
2 Xiang Y, Jiao N, Wang F, et al. A robust two-stage registration algorithm for large optical and SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing,2021,60:1-15. DOI: 10.1109/TGRS.2021.3133863 .
doi: 10.1109/TGRS.2021.3133863
3 Li Z, Yue J, Fang L. Adaptive regional multiple features for large-scale high-resolution remote sensing image registration[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-13. DOI: 10.1109/TGRS.2022.3141101 .
doi: 10.1109/TGRS.2022.3141101
4 Ye Y, Zhu B, Tang T, et al. A robust multimodal remote sensing image registration method and system using steerable filters with first-and second-order gradients[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2022,188:331-350. DOI: 10.1016/j.isprsjprs.2022.04.011 .
doi: 10.1016/j.isprsjprs.2022.04.011
5 Yao Y, Zhang Y, Wan Y, et al. Multi-modal remote sensing image matching considering co-occurrence filter[J]. IEEE Transactions on Image Processing,2022,31:2584-2597. DOI: 10.1109/TIP.2022.3157450 .
doi: 10.1109/TIP.2022.3157450
6 Suri S, Reinartz P. Mutual-information-based registration of TerraSAR-X and Ikonos imagery in urban areas[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 48(2):939-949. DOI: 10.1109/TGRS.2009.2034842 .
doi: 10.1109/TGRS.2009.2034842
7 Zhuang Y, Gao K, Miu X, et al. Infrared and visual image registration based on mutual information with a combined particle swarm optimization–Powell search algorithm[J]. Optik, 2016, 127(1):188-191. DOI: 10.1016/j.ijleo.2015.09.199 .
doi: 10.1016/j.ijleo.2015.09.199
8 Yan Li, Wang Ziqi, Ye Zhiyun. Multimodal image registration algorithm considering grayscale and gradient information[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(1):71-81.
8 闫利, 王紫琦, 叶志云. 顾及灰度和梯度信息的多模态影像配准算法[J].测绘学报, 2018, 47(1):71-81.
9 Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004,60(2):91-110. DOI:10.1023/B:VISI.0000029664.99615.94 .
doi: 10.1023/B:VISI.0000029664.99615.94
10 Sedaghat A, Mokhtarzade M, Ebadi H. Uniform robust scale-invariant feature matching for optical remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011,49(11):4516-4527. DOI:10.1109/TGRS.2011.2144607 .
doi: 10.1109/TGRS.2011.2144607
11 Xiang Y, Wang F, You H. OS-SIFT: A robust SIFT-like algorithm for high-resolution optical-to-SAR image registration in suburban areas[J]. IEEE Transactions on Geoscience and Remote Sensing,2018,56(6):3078-3090. DOI:10.1109/TGRS.2018.2790483 .
doi: 10.1109/TGRS.2018.2790483
12 Ye Yuanxin, Hao Siyuan, Cao Yungang. Automatic registration of optical and SAR image using geometric structural properties[J]. Journal of Infrared and Millimeter Waves, 2017, 36(6):720-726.
12 叶沅鑫, 郝思媛, 曹云刚. 基于几何结构属性的光学和SAR影像自动配准[J]. 红外与毫米波学报, 2017, 36(6):720-726.
13 Li Dongchen, Xiang Wenhao, Dang Qiannan, et al. SAR and optical images registration using uniform distribution and structure description based ASIFT[J].Acta Geodaetica et Cartogra-phica Sinica,2020,49(12):1583-1590.
13 李东宸,向文豪,党倩楠, 等. 均匀分布与结构描述ASIFT相结合的SAR与可见光图像配准算法[J]. 测绘学报,2020,49(12):1583-1590.
14 Wang L, Sun M, Liu J, et al. A robust algorithm based on phase congruency for optical and SAR image registration in suburban areas[J]. Remote Sensing,2020,12(20):3339. DOI: 10.3390/rs12203339 .
doi: 10.3390/rs12203339
15 Morrone M C, Owens R A. Feature detection from local energy[J]. Pattern Recognition Letters, 1987, 6(5):303-313. DOI: 0.1016/0167-8655(87)90013-4 .
doi: 0.1016/0167-8655(87)90013-4
16 Kovesi P. Image features from phase congruency[J]. Videre: Journal of Computer Vision Research,1999,1(3):1-26.
17 Horn B, Klaus B, Horn P.Robot vision[M]. New York:McGraw-Hill Higher Education,1986.
18 Perona P, Malik J. Scale-space and edge detection using anisotropic diffusion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7):629-639. DOI: 10.1109/34.56205 .
doi: 10.1109/34.56205
19 Fu Z, Qin Q, Luo B, et al. HOMPC: A local feature descriptor based on the combination of magnitude and phase congruency information for multi-sensor remote sensing images[J]. Remote Sensing,2018,10(8):1234. DOI:10.3390/rs10081234 .
doi: 10.3390/rs10081234
20 Li J, Hu Q, Ai M. RIFT: Multi-modal image matching based on radiation-variation insensitive feature transform[J]. IEEE Transactions on Image Processing,2019,29:3296-3310. DOI: 10.1109/TIP.2019.2959244 .
doi: 10.1109/TIP.2019.2959244
21 Wu Y, Ma W, Gong M, et al. A novel point-matching algorithm based on fast sample consensus for image registration[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 12(1):43-47. DOI: 10.1109/LGRS.2014.2325970 .
doi: 10.1109/LGRS.2014.2325970
22 Ma W, Wen Z, Wu Y, et al. Remote sensing image registration with modified SIFT and enhanced feature matching[J]. IEEE Geoscience and Remote Sensing Letters,2016,14(1):3-7. DOI: 10.1109/LGRS.2016.2600858 .
doi: 10.1109/LGRS.2016.2600858
23 Xiang Y, Tao R, Wang F, et al. Automatic registration of optical and SAR images via improved phase congruency model[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,13:5847-5861. DOI: 10.1109/JSTARS.2020.3026162 .
doi: 10.1109/JSTARS.2020.3026162
24 Ye Y, Bruzzone L, Shan J, et al. Fast and robust matching for multimodal remote sensing image registration[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(11):9059-9070. DOI: 10.1109/TGRS.2019.2924684 .
doi: 10.1109/TGRS.2019.2924684
[1] 薛庆,杨树文,闫恒,张萌生,张卓. 基于SIFT与互信息筛选优化的遥感影像配准[J]. 遥感技术与应用, 2022, 37(5): 1209-1216.
[2] 王晶,高帅,郭亮,汪云. 基于多尺度特征融合的U-Net网络高分影像不透水面提取研究[J]. 遥感技术与应用, 2022, 37(4): 811-819.
[3] 史佳睿,申茜,彭红春,李利伟,姚月,汪明秀,王茹. 基于三种高分辨率影像样本迁移学习的城市水体提取研究[J]. 遥感技术与应用, 2022, 37(3): 731-738.
[4] 董秀春,刘忠友,蒋怡,郭涛,李宗南. 基于WorldView-2影像和语义分割模型的小麦分类提取[J]. 遥感技术与应用, 2022, 37(3): 564-570.
[5] 李业钦,王常颖,隋毅,初佳兰,李劲华. 基于自动阈值分类的高分辨率影像海陆分界线自动提取[J]. 遥感技术与应用, 2021, 36(6): 1379-1387.
[6] 郑磊,何直蒙,丁海勇. 基于ENVINet5的高分辨率遥感影像稀疏塑料大棚提取研究[J]. 遥感技术与应用, 2021, 36(4): 908-915.
[7] 高子为,孙伟伟,程朋根,杨刚,孟祥超. 融合高分辨率遥感影像和POI数据的多特征潜在语义信息用于识别城市功能区[J]. 遥感技术与应用, 2021, 36(3): 618-626.
[8] 陈敏,潘佳威,李江杰,徐璐,刘加敏,韩健,陈奕云. 结合VGGNet与Mask R-CNN的高分辨率遥感影像建设用地检测[J]. 遥感技术与应用, 2021, 36(2): 256-264.
[9] 王卓,闫浩文,禄小敏,冯天文,李亚珍. 一种改进U-Net的高分辨率遥感影像道路提取方法[J]. 遥感技术与应用, 2020, 35(4): 741-748.
[10] 连喜红,祁元,王宏伟,张金龙,杨瑞. 基于面向对象的青海湖环湖区居民地信息自动化提取[J]. 遥感技术与应用, 2020, 35(4): 775-785.
[11] 何浩,刘修国,沈永林. 基于视差的高分辨率遥感影像建筑物变化检测[J]. 遥感技术与应用, 2019, 34(6): 1315-1323.
[12] 王宇,杨艺,王宝山,王田,卜旭辉,王传云. 深度残差神经网络高分辨率遥感图像建筑物分割[J]. 遥感技术与应用, 2019, 34(4): 736-747.
[13] 龙恩, 汪源, 孟钢, 王伟阳, 陈旭, 连翠萍. 基于同名特征的建筑物高度高分影像提取方法[J]. 遥感技术与应用, 2019, 34(1): 107-114.
[14] 曹云刚,王志盼,杨磊. 高分辨率遥感影像道路提取方法研究进展[J]. 遥感技术与应用, 2017, 32(1): 20-26.
[15] 陈行,卓莉,陶海燕. 基于MMBI的高分辨率影像建筑物提取研究[J]. 遥感技术与应用, 2016, 31(5): 930-938.