## Message Board

Respected readers, authors and reviewers, you can add comments to this page on any questions about the contribution, review,        editing and publication of this journal. We will give you an answer as soon as possible. Thank you for your support!

Volume 47 Issue 8
Aug.  2022
Turn off MathJax
Article Contents

YAO Yongxiang, DUAN Ping, LI Jia, WANG Yunchuan. A UAV Image Matching Algorithm Considering log-Polar Description and Position Scale Distance Feature[J]. Geomatics and Information Science of Wuhan University, 2022, 47(8): 1271-1278. doi: 10.13203/j.whugis20200362
 Citation: YAO Yongxiang, DUAN Ping, LI Jia, WANG Yunchuan. A UAV Image Matching Algorithm Considering log-Polar Description and Position Scale Distance Feature[J]. Geomatics and Information Science of Wuhan University, 2022, 47(8): 1271-1278.

# A UAV Image Matching Algorithm Considering log-Polar Description and Position Scale Distance Feature

##### doi: 10.13203/j.whugis20200362
Funds:

The National Natural Science Foundation of China 41961061

Yunnan Fundamental Research Projects 202001AT070057

Science Foundation of Yunnan Provincial Department of Education Project 2018JS148

• Author Bio:

YAO Yongxiang, PhD candidate, specializes in aerial photogrammetry, and geometry registration of image. E-mail: yaoyongxiang@whu.edu.cn

• Corresponding author: DUAN Ping, PhD, associate professor. E-mail: dpgiser@163.com
• Received Date: 2021-07-19
• Publish Date: 2022-08-05
•   Objectives  Few corresponding points can easily affect the calculation of image pose information, increase the difficulty of constructing a regional network in an aerial triangulation solution, so that lead to problems such as image stitching misalignment, incorrect bundle adjustment results or even failure. In order to better complete the matching of unmanned aerial vehicle (UAV) images, this paper proposes a robust UAV image matching algorithm considering log-polar description and position scale distance.  Methods  Firstly, a Gaussian multi-scale image collection is established and feature points are extracted. Secondly, the descriptors are constructed using log-polar coordinates, and a descriptor suitable for UAV image characteristics is established. Then, the feature matching is performed by the distance function of position and scale constraints. Finally, the mode seeking and fast sample consensus method are used to eliminate the outliner and complete the extraction of correspondence.  Results  The image obtained by four-rotor UAV is used as the data source, and a comparison experiment of image matching with scale invariant feature transform (SIFT) algorithm and synthetic aperture radar-scale invariant feature transform (SAR-SIFT) algorithm is carried out. The experimental results show that a 210-dimensional log-polar coordinate descriptor is constructed through the gradient location and orientation histogram. The descriptor can better describe the feature points in 10 directions through the circular neighborhood, making the matching results more robust. The position scale Euclidean distance matching function established by integrating factors such as position and scale can better calculate the UAV image matching relationship, and match more correct corresponding points. In terms of the number of correct corresponding points extracted under the same parameter settings, the proposed algorithm is significantly more than the other two algorithms, and in terms of the root mean square error of the matching results, the algorithm in this article is also significantly better than the two compared algorithms.  Conclusions  The proposed algorithm can better extract the corresponding points of UAV images.
•  [1] Senthilnath J, Omkar S N, Mani V, et al. Multiobjective Discrete Particle Swarm Optimization for Multisensor Image Alignment[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(5): 1095-1099 [2] Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630 [3] 李欣，杨宇辉，杨博，等. 利用方向相位特征进行多源遥感影像匹配[J]. 武汉大学学报·信息科学版, 2020, 45(4): 488-494 Li Xin, Yang Yuhui, Yang Bo, et al. A Multi-source Remote Sensing Image Matching Method Using Directional Phase Feature[J]. Geomatics and Information Science of Wuhan University, 2020, 45(4): 488-494 [4] 张卡，盛业华，管忠诚，等. 基于NSCT的立体影像匹配相似性测度计算[J]. 武汉大学学报·信息科学版, 2015, 40(4): 457-461 Zhang Ka, Sheng Yehua, Guan Zhongcheng, et al. NSCT Based Computation of Similarity Measure for Stereo Image Matching[J]. Geomatics and Information Science of Wuhan University, 2015, 40(4): 457-461 [5] Chen H M, Arora M K, Varshney P K. Mutual Information-Based Image Registration for Remote Sensing Data[J]. International Journal of Remote Sensing, 2003, 24(18): 3701-3706 [6] Gong M G, Zhao S M, Jiao L C, et al. A Novel Coarse-to-Fine Scheme for Automatic Image Registration Based on SIFT and Mutual Information[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(7): 4328-4338 [7] Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110 [8] Bay H, Ess A, Tuytelaars T, et al. Speeded-up Robust Features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359 [9] 李佳，段平，姚永祥，等. 加速分割特征优化的图像配准方法[J]. 激光与光电子学进展, 2019, 56(1): 138-144 https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ201901017.htm Li Jia, Duan Ping, Yao Yongxiang, et al. Image Registration Method Based on Accelerated Segmentation Feature Optimization[J]. Laser & Optoelectronics Progress, 2019, 56(1): 138-144 https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ201901017.htm [10] 张卡，盛业华，付素霞，等. 基于物方定位一致性约束的光学航空影像多视铅垂线轨迹匹配[J]. 光学精密工程, 2018, 26(7): 1784-1793 https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201807025.htm Zhang Ka, Sheng Yehua, Fu Suxia, et al. Multi-view VLL Matching Algorithm for Optical Aerial Images Based on Constraint of Object Space Positioning Consistency[J]. Optics and Precision Engineering, 2018, 26(7): 1784-1793 https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM201807025.htm [11] 耿娟，何成龙，刘宪鑫. 基于CSIFT特性的无人机影像匹配[J]. 国土资源遥感, 2016, 28(1): 93-100 https://www.cnki.com.cn/Article/CJFDTOTAL-GTYG201601015.htm Geng Juan, He Chenglong, Liu Xianxin. UAV Image Matching Based on CSIFT Feature[J]. Remote Sensing for Land & Resources, 2016, 28(1): 93-100 https://www.cnki.com.cn/Article/CJFDTOTAL-GTYG201601015.htm [12] 鲁萍萍，梅雪. 基于降维与聚类的无人机航拍图拼接配准算法[J]. 计算机应用与软件, 2018, 35(6): 220-225 Lu Pingping, Mei Xue. Aerial Image Stitching Registration Algorithm for UAV Based on Dimensionality Reduction and Clustering[J]. Computer Applications and Software, 2018, 35(6): 220-225 [13] 张永军，熊小东，王梦秋，等. 机载激光雷达点云与定位定姿系统数据辅助的航空影像自动匹配方法[J]. 测绘学报, 2014, 43(4): 380-388 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201404010.htm Zhang Yongjun, Xiong Xiaodong, Wang Mengqiu, et al. A New Aerial Image Matching Method Using Airborne LiDAR Point Cloud and POS Data[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(4): 380-388 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201404010.htm [14] Wan Y, Zhang Y J, Liu X Y. An A-Contrario Method of Mismatch Detection for Two-View Pushbroom Satellite Images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 153: 123-136 [15] 詹总谦，李一挥，王陈东，等. 顾及局部相对几何变形改正的影像匹配和空三逐步精化方法[J]. 武汉大学学报·信息科学版, 2018, 43(11): 1620-1627 http://ch.whu.edu.cn/cn/search Zhan Zongqian, Li Yihui, Wang Chendong, et al. A Stepwise Refinement Method for Image Matching and Aerotriangulation Using Correction of Local Relative Geometric Distortion[J]. Geomatics and Information Science of Wuhan University, 2018, 43(11): 1620-1627 http://ch.whu.edu.cn/cn/search [16] Kupfer B, Netanyahu N S, Shimshoni I. An Efficient SIFT-Based Mode-Seeking Algorithm for Sub-Pixel Registration of Remotely Sensed Images[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(2): 379-383 [17] Wu Y, Ma W P, Gong M G, et al. A Novel Point-Matching Algorithm Based on Fast Sample Consensus for Image Registration[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(1): 43-47 [18] Ma W P, Wen Z L, Wu Y, et al. Remote Sensing Image Registration with Modified SIFT and Enhanced Feature Matching[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(1): 3-7 [19] Chum O, Matas J, Kittler J. Pattern Recognition[M]//Berlin, Heidelberg: Springer, 2003 [20] Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630
###### 通讯作者: 陈斌, bchen63@163.com
• 1.

沈阳化工大学材料科学与工程学院 沈阳 110142

Figures(4)  / Tables(3)

## A UAV Image Matching Algorithm Considering log-Polar Description and Position Scale Distance Feature

##### doi: 10.13203/j.whugis20200362
###### 1. Faculty of Geography, Yunnan Normal University, Kunming 650500, China2. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
Funds:

The National Natural Science Foundation of China 41961061

Yunnan Fundamental Research Projects 202001AT070057

Science Foundation of Yunnan Provincial Department of Education Project 2018JS148

• Author Bio:

• ###### Corresponding author:DUAN Ping, PhD, associate professor. E-mail: dpgiser@163.com

Abstract:   Objectives  Few corresponding points can easily affect the calculation of image pose information, increase the difficulty of constructing a regional network in an aerial triangulation solution, so that lead to problems such as image stitching misalignment, incorrect bundle adjustment results or even failure. In order to better complete the matching of unmanned aerial vehicle (UAV) images, this paper proposes a robust UAV image matching algorithm considering log-polar description and position scale distance.  Methods  Firstly, a Gaussian multi-scale image collection is established and feature points are extracted. Secondly, the descriptors are constructed using log-polar coordinates, and a descriptor suitable for UAV image characteristics is established. Then, the feature matching is performed by the distance function of position and scale constraints. Finally, the mode seeking and fast sample consensus method are used to eliminate the outliner and complete the extraction of correspondence.  Results  The image obtained by four-rotor UAV is used as the data source, and a comparison experiment of image matching with scale invariant feature transform (SIFT) algorithm and synthetic aperture radar-scale invariant feature transform (SAR-SIFT) algorithm is carried out. The experimental results show that a 210-dimensional log-polar coordinate descriptor is constructed through the gradient location and orientation histogram. The descriptor can better describe the feature points in 10 directions through the circular neighborhood, making the matching results more robust. The position scale Euclidean distance matching function established by integrating factors such as position and scale can better calculate the UAV image matching relationship, and match more correct corresponding points. In terms of the number of correct corresponding points extracted under the same parameter settings, the proposed algorithm is significantly more than the other two algorithms, and in terms of the root mean square error of the matching results, the algorithm in this article is also significantly better than the two compared algorithms.  Conclusions  The proposed algorithm can better extract the corresponding points of UAV images.

YAO Yongxiang, DUAN Ping, LI Jia, WANG Yunchuan. A UAV Image Matching Algorithm Considering log-Polar Description and Position Scale Distance Feature[J]. Geomatics and Information Science of Wuhan University, 2022, 47(8): 1271-1278. doi: 10.13203/j.whugis20200362
 Citation: YAO Yongxiang, DUAN Ping, LI Jia, WANG Yunchuan. A UAV Image Matching Algorithm Considering log-Polar Description and Position Scale Distance Feature[J]. Geomatics and Information Science of Wuhan University, 2022, 47(8): 1271-1278.
• 影像匹配是对两幅或多幅具有一定重叠区域的影像寻找同一特征点的过程[1]。无人机（unmanned aerial vehicle, UAV）影像图幅小、影像姿态不稳健，导致影像匹配过程存在无序匹配的情况，且匹配的同名点对数量较少，而影像匹配结果质量会对后续图像处理产生较大的影响。

针对影像匹配，国内外专家学者展开了大量探索，主要集中在影像区域与影像特征两个方面[2-3]。基于影像区域匹配的方法通过像素强度之间的相似性来判断影像之间的对齐关系，例如相似性度量[4]、互信息[5]、像素强度和梯度强度[6]等，当图像的显著特征较少时，区域匹配方法可以得到较好的性能，但存在计算复杂度高、图像失真和强度变化等问题，可能是由图像噪声、图像亮度和不同传感器成像差异等引起。因此该方法对图像的尺寸、图像旋转以及遮挡等都较为敏感，其应用受到了限制。基于影像特征的方法，例如尺度不变特征变换（scale invariant feature transform, SIFT）[7]、加速稳健特征（speeded up robust features, SURF）[8]、快速特征点提取和描述（oriented fast and rotated brief, ORB）[9]、多视铅垂线轨迹匹配[10]等，从尺度稳健性、搜索方式、粗点剔除等角度对影像匹配进行了研究，丰富了影像匹配的方法，较好地降低了遥感影像的匹配难度。但上述算法主要研究影像的同名点提取的精度和效率，较少关注同名点的数量。

匹配精度和效率对空中三角测量的结果影响较大，但UAV影像的同名点数量将直接影响空中三角测量、图像拼接及镶嵌融合等处理的结果，尤其当同名点数量较少时会导致空中三角测量错位甚至失败。对此，文献[11]利用几何代数优化SIFT算法；文献[12]利用降维与聚类改进SURF算法；还可以利用描述子检测、降维及增强鲁棒性等方法来优化UAV影像匹配效率。上述方法所提取的同名点对数量有所提升，但依然不够充足，且一定程度上增加了算法复杂度。为此，有学者利用薄板样条函数结合SIFT算法、点云辅助匹配[13]、仿射尺度不变特征匹配方法[14-15], 提出了模式搜索匹配[16]、快速样本共识匹配[17]、遥感影像增强特征匹配[18]等方法，这些方法可以提取足够多的同名点，但受局部区域差异、影像重叠率低或影像仿射变换小及影像光照差异等不同方面的制约。综上所述，目前在UAV影像匹配研究中，对UAV影像提取的特征点描述方面仍存有欠缺，当描述符不能鲁棒地实现特征描述时，会增加同名点的提取难度，且对UAV影像提取的特征点周边区域的位置与尺度等信息利用不充分，影响同名点提取。因此，本文提出了一种改进的UAV影像匹配算法，首先通过构建适合UAV影像的对数极坐标描述子来描述特征信息；然后充分考虑影像特征的位置和尺度建立更加稳健的距离匹配函数，增加同名点的数量。

Reference (20)

/