Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2019, Vol. 53 Issue (6): 1205-1217    DOI: 10.3785/j.issn.1008-973X.2019.06.021
计算机与自动化技术     
基于图像混合特征的城市绿地遥感图像配准
高雪艳(),潘安宁,杨扬*()
云南师范大学 信息学院，西部资源环境地理信息技术教育部工程研究中心，云南 昆明 650500
Urban green space remote sensing image registration using image mixed features
Xue-yan GAO(),An-ning PAN,Yang YANG*()
School of Information Science and Technology, The Engineering Research Center of GIS Technology in Western China of Ministry of Education of China, Yunnan Normal University, Kunming 650500, China
 全文: PDF(1728 KB)   HTML
摘要：

为了解决同一场景城市绿地遥感图像因视角变化等原因不在同一坐标系，以致于不能对其进行变化检测的问题，提出一种基于图像混合特征的遥感图像配准方法. 1）提取SIFT特征点:从待配准图像和参考图像提取足够的SIFT特征点；2）基于混合特征的SIFT特征点配准：首先在特征点集Y和X之间进行对应关系评估，然后利用对应关系建立空间映射函数不断更新形变后源点集的位置；3）图像配准：基于源点集和形变后的源点集来构造一个映射函数，从而对图像进行配准. 在与当前流行的4种算法（SIFT、CPD、RSOC、GLMDTPS）的对比实验中，提出的算法均给出了精确的配准结果，在大部分实验中其性能超过了其他算法.
关键词： 遥感图像配准;  图像混合特征;  非刚性畸变;  多视角;  多时相    
Abstract:

A remote sensing image registration method based on image mixed features was proposed in order to solve the problem that the remote sensing images of urban green space in the same scene are not in the same coordinate system due to the change of viewpoint, and the change detection cannot be performed. Firstly, SIFT-based feature point extraction: exact sufficient SIFT feature points from the sensed image and the reference image. Secondly, SIFT feature point registration based on mixed features: the correspondence estimation between the feature point set Y and X, and then the correspondence was used to establish a spatial mapping function to continuously update the position of the transformed source point set. Thirdly, image registration: a mapping function was constructed based on the source point set and the transformed source point set to register the image. The experimental results show that, compared with four popular methods (SIFT, CPD, RSOC, GLMDTPS), the proposed method all gives accurate registration results, even presents better performance than the other methods in most cases.
Key words: remote sensing image registration    multiple image features    non-rigid distortion    multi view    multi temporal
收稿日期: 2018-04-24 出版日期: 2019-05-22
CLC:  TP 75  
通讯作者: 杨扬     E-mail: gxy0415@163.com;yyang_ynu@163.com
作者简介: 高雪艳（1992—），女，硕士生，从事遥感图像处理研究. orcid.org/0000-0003-0284-5229. E-mail： gxy0415@163.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
高雪艳
潘安宁
杨扬

引用本文:

高雪艳,潘安宁,杨扬. 基于图像混合特征的城市绿地遥感图像配准[J]. 浙江大学学报(工学版), 2019, 53(6): 1205-1217.

Xue-yan GAO,An-ning PAN,Yang YANG. Urban green space remote sensing image registration using image mixed features. Journal of ZheJiang University (Engineering Science), 2019, 53(6): 1205-1217.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2019.06.021    或    http://www.zjujournals.com/eng/CN/Y2019/V53/I6/1205

图 1  遥感图像配准算法流程图
图 2  M型特征点集中的某个中心点与最近5个相邻点构成的局部片段
图 3  不同速度场约束下得到的对应关系图解
图 4  单一特征和混合特征的配准性能比较
图 5  使用不同混合特征（所提算法和GLMDTPS）的配准性能展示
图 6  不同数量冗余点干扰下L2E和MLE的鲁棒性对比
图 7  参数β和ε的实验结果展示
数据集 数据类型 实验组数 尺寸 特征点数
I 卫星遥感图像 60 620×480~1 300×890 65~605
Ⅱ 小型无人机遥感图像 60 620×480~1 300×890 90~556
表 1  遥感图像配准实验数据集
方法 RMSE MAE 方法 RMSE MAE
SIFT ? ? GLMDTPS 3.367 6 7.351 2
CPD 3.090 4 7.573 3 本研究 1.892 5 3.548 7
RSOC 2.663 1 6.197 1 ? ? ?
表 2  卫星遥感图像配准实验结果（测试数据为数据 I）
图 8  数据集I的3组具有代表性的卫星遥感图像配准结果示例
方法 RMSE MAE 方法 RMSE MAE
SIFT ? ? GLMDTPS 5.200 0 9.516 4
CPD 7.299 6 10.203 5 本研究 1.743 8 2.031 3
RSOC 4.524 7 7.228 3 ? ? ?
表 3  小型无人机（SUAV）低空遥感图像配准实验结果（测试数据为数据II）
图 9  数据集II的3组具有代表性的小型无人机低空遥感图像配准结果示例
评估方法 RMSE MAE
a 2.477 6 2.914 4
b 1.516 2 1.986 9
c 1.820 5 1.157 6
d 2.330 1 2.757 1
e 0.982 8 2.240 7
均值 1.507 4 1.611 3
表 4  卫星遥感图像配准实验结果
图 10  具有代表性的5组卫星遥感图像对配准示例（I：待配准图像, II：参考图像, III：转换图像，IV：交叉显示转换图像和参考图像的5×5棋盘格）
评估方法 RMSE MAE
a 0.990 3 1.240 7
b 1.954 8 2.166 3
c 1.181 2 1.347 92
d 1.688 9 1.968 49
e 1.425 9 1.636 76
均值 1.448 2 1.672 0
表 5  无人机遥感图像的配准实验结果
图 11  具有代表性的5组无人机遥感图像对配准示例（I：待配准图像, II：参考图像, III：转换图像，IV：交叉显示转换图像和参考图像的5×5棋盘格）
1 WEI Y, CAI J Evaluation and sustainable development on ecological service value for urban green space system in Hangzhou City[J]. Journal of Zhejiang A & F University, 2017, 34 (04): 695- 703
2 ZHANG Y, LI X New thought on urban green space system planning based on the perspective of supply side[J]. Journal of Chinese Urban Forestry, 2017, 15 (1): 1- 4
3 陈永生, 黄庆丰, 章裕超, 等 基于GIS的合肥市中心城区绿地可达性分析评价[J]. 中国农业大学学报, 2015, 20 (2): 229- 236
CHEN Yong-sheng, HUANG Qing-feng, ZHANG Yu-chao, et al GIS-based analysis and evaluation for the accessibility of urban green in the central city of Hefei[J]. Journal of China Agricultural University, 2015, 20 (2): 229- 236
4 王野 基于资源三号卫星影像的城市绿地信息提取方法探讨[J]. 测绘工程, 2014, 23 (7): 65- 67
WANG Y Research on urban green surveying based on ZY-3 satellite[J]. Engineering of Surveying and Mapping, 2014, 23 (7): 65- 67
doi: 10.3969/j.issn.1006-7949.2014.07.016
5 陈红顺, 贺辉, 肖红玉 基于高空间分辨率遥感影像的城市绿地提取方法研究[J]. 环境科学与管理, 2016, 41 (10): 25- 27
CHEN Hong-shun, HE Hui, XIAO Hong-yu Extraction of urban green space from high spatial resolution remote sensing images[J]. Environmental Science and Management, 2016, 41 (10): 25- 27
doi: 10.3969/j.issn.1673-1212.2016.10.007
6 杨柳, 陈延辉, 岳德鹏, 等 无人机遥感影像的城市绿地信息提取[J]. 测绘科学, 2017, 42 (2): 59- 64
YANG Liu, CHEN Yan-hui, YUE De-peng, et al Information extraction of urban green space based on UAV remote sensing image[J]. Science of Surveying and Mapping, 2017, 42 (2): 59- 64
7 王斐, 刘艳红, 冯代丽, 等 城市绿地信息提取的研究进展[J]. 中国农学通报, 2017, 33 (10): 67- 71
WANG Fei, LIU Yan-hong, FENG Dai-li, et al Research progress of information extraction of urban green space[J]. Chinese Agricultural Science Bulletin, 2017, 33 (10): 67- 71
doi: 10.11924/j.issn.1000-6850.casb16050185
8 YANG K, PAN A, YANG Y, et al Remote sensing image registration using multiple image features[J]. Remote Sensing, 2017, 9 (6): 581
doi: 10.3390/rs9060581
9 SMITH S M, BRADY J M SUSAN: a new approach to low level image processing[J]. International Journal of Computer Vision, 1997, 23 (1): 45- 78
doi: 10.1023/A:1007963824710
10 HARRIS C, Stephens M. A combined corner and edge detector [C] // Proceedings of the 4th Alvey Vision Conference. Alvey: IEEE, 1988: 147-151.
11 MOREVEC H P. Towards automatic visual obstacle avoidance [C] // International Joint Conference on Artificial Intelligence. Cambridge : IEEE. 1977: 584.
12 LOWE D G. Object recognition from local scale-invariant features [C] // The Proceedings of the Seventh IEEE International Conference on Computer Vision. Kerkyra: IEEE, 1999: 1150-1157.
13 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
14 MYRONENKO A, SONG X Point set registration: coherent point drift[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32 (12): 2262- 2275
doi: 10.1109/TPAMI.2010.46
15 GREENGARD L, STRAIN J The fast gauss transform[J]. Siam Journal on Scientific and Statistical Computing, 1991, 12 (1): 79- 94
16 MARKOVSKY I. Structured low-rank approximation and its applications [J]. Automatica, 2008, 44(4): 891-909.
17 梁栋, 颜普, 朱明, 等 一种基于NSCT和SIFT的遥感图像配准算法[J]. 仪器仪表学报, 2011, 32 (5): 1083- 1088
LIANG Dong, YAN Pu, ZHU Ming, et al Remote sensing image registration algorithm based on SIFT and NSCT[J]. Chinese Journal of Scientific Instrument, 2011, 32 (5): 1083- 1088
18 JIAN B, VEMURI B C Robust point pet registration using gaussian mixture models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33 (8): 1633- 1645
doi: 10.1109/TPAMI.2010.223
19 LIU Z, AN J, JING Y A simple and robust feature point matching algorithm based on restricted spatial order constraints for aerial image registration[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50 (2): 514- 527
20 ZHAO L Y, BU-YUN L, LI X R, et al Multi-source remote sensing image registration based on scale-invariant feature transform and optimization of regional mutual information[J]. Acta Physica Sinica, 2015, 64 (12): 0- 0
21 YANG Y, ONG S H, FOONG K W C A robust global and local mixture distance based non-rigid point set registration[J]. Pattern Recognition, 2015, 48 (1): 156- 173
doi: 10.1016/j.patcog.2014.06.017
22 张闻宇, 李智, 王勇军 基于CenSurE-star特征的无人机景象匹配算法[J]. 仪器仪表学报, 2017, 38 (2): 462- 470
ZHANG Wen-yu, LI Zhi, WANG Yong-jun UAV scene matching algorithm based on CenSurE-star feature[J]. Chinese Journal of Scientific Instrument, 2017, 38 (2): 462- 470
23 CHUI H, RANGARAJAN A A new point matching algorithm for non-rigid registration[J]. Computer Vision and Image Understanding in Nonrigid Image Registration, 2003, 89 (2): 114- 141
24 SCOTT D W Parametric statistical modeling by minimum integrated square error[J]. Technometrics, 2001, 43 (3): 274- 285
doi: 10.1198/004017001316975880
25 YUILLE A L, GRZYWACZ N M A mathematical analysis of the motion coherence theory[J]. International Journal of Computer Vision, 1989, 3 (2): 155- 17
doi: 10.1007/BF00126430
26 ARONSZAJN A Theory of reproducing kernels[J]. Transactions of the American Mathematical Society, 1950, 68 (3): 337- 404
doi: 10.1090/S0002-9947-1950-0051437-7
[1] 桑高丽,王国滨,朱蓉,宋佳佳. 基于级联形状回归的多视角人脸特征点定位[J]. 浙江大学学报(工学版), 2019, 53(7): 1374-1379.
[2] 何智翔, 丁晓青, 方驰, 文迪. 基于LBP和CCS-AdaBoost的多视角人脸检测[J]. J4, 2013, 47(4): 622-629.