改进SIFT算法结合两级特征匹配的无人机图像匹配算法

doi:10.11896/j.issn.1002-137X.2019.06.048

计算机科学 ›› 2019, Vol. 46 ›› Issue (6): 316-321.doi: 10.11896/j.issn.1002-137X.2019.06.048

改进SIFT算法结合两级特征匹配的无人机图像匹配算法

邵进达¹, 杨帅¹, 程琳²

(南京工业大学测绘科学与技术学院南京210000)¹
(东南大学交通学院南京210096)²

收稿日期:2018-05-21 发布日期:2019-06-24
通讯作者: 邵进达(1963－),男,硕士,副教授,主要研究方向为GIS应用,E-mail:605728465@qq.com
作者简介:杨帅(1991－),男,硕士生,主要研究方向为摄影测量、影像匹配算法;程琳(1963－),男,博士,教授,博士生导师,主要研究方向为交通规划、优化理论与方法。
基金资助:
国家自然科学基金项目(51378119)资助。

UAV Image Matching Algorithm Based on Improved SIFT Algorithm and Two-stage Feature Matching

SHAO Jin-da¹, YANG Shuai¹, CHENG Lin²

(College of Geomatics Science and Technology,Nanjing Tech University,Nanjing 210000,China)¹
(School of Transportation,Southeast University,Nanjing 210096,China)²

Received:2018-05-21 Published:2019-06-24

摘要/Abstract

摘要： 针对无人机航拍图像匹配过程中所需时间长、成本高、计算量大的问题,提出一种几何代数法(Geometry Algebra,GA)和尺度不变特征变换(Scale Invariant Feature Transform,SIFT)结合的无人机图像匹配算法,以实现图像的快速特征提取和特征匹配。首先利用GA算法和SIFT算法进行特征点的检测及描述;接下来进行两级特征匹配,即先使用快速最近邻搜索包(Fast Library for Approximate Nearest Neighbors,FLANN)算法对特征点进行粗匹配,再根据改进的随机抽样一致算法(Random Sample Consensus,RANSAC)来优化匹配结果。实验结果表明,与传统的图像匹配方法相比,提出的算法可以准确地定位更多的特征点,极大地提高了图像对准过程的速度,并且可以为大型无人机图像匹配节省大量时间。

关键词: FLANN粗匹配, SIFT算法, 改进RANSAC算法, 几何代数法, 无人机图像匹配

Abstract: Aiming at the problems in the matching process of UAV aerial images,such as long time,high cost and large amount of computation,this paper proposed an UAV image matching algorithm based on scale invariant feature transform scale invariant feature transform(SIFT) algorithm and geometrical algebraic method geometry algebra(GA) to achieve fast image feature extraction and feature matching.Firstly,the feature points are detected and described by using GA method and SIFT algorithms.Then,two-level feature matching is performed,fast library for approximate nearest neighbors (FLANN) algorithm is used to pre-matching the feature points and matching results is optimized according to the improved random sample consensus(RANSAC) algorithm.Experimental results show that compared with traditio-nal image matching algorithm,the proposed algorithm can locate more feature points accurately and improve the speed of image alignment process greatly,and it can save a lot of time for image matching of large drones.

Key words: FLANN rough matching, Geometry algebra, Improved RANSAC algorithm, SIFT algorithm, UAV image matching

中图分类号:

TP391

邵进达, 杨帅, 程琳. 改进SIFT算法结合两级特征匹配的无人机图像匹配算法[J]. 计算机科学, 2019, 46(6): 316-321. https://doi.org/10.11896/j.issn.1002-137X.2019.06.048

SHAO Jin-da, YANG Shuai, CHENG Lin. UAV Image Matching Algorithm Based on Improved SIFT Algorithm and Two-stage Feature Matching[J]. Computer Science, 2019, 46(6): 316-321. https://doi.org/10.11896/j.issn.1002-137X.2019.06.048

参考文献

[1]CHEN Z X,REN J Q,TANG H J,et al.Progress and perspectives on agricultural remote sensing research and applications[J].Journal of Remote Sensing,2016,20(5):748-767.(in Chinese)
陈仲新,任建强,唐华俊,等.农业遥感研究应用进展与展望[J].遥感学报,2016,20(5):748-767.
[2]JIA P Y,PENG X D,ZHOU W G.Research on Autonomous Landing of Quad-rotor UAV[J].Computer Science,2017,44(S2):520-523.(in Chinese)
贾配洋,彭晓东,周武根.四旋翼无人机自主移动降落方法研究[J].计算机科学,2017,44(S2):520-523.
[3]TAN T Z,XIANG Y P.Large-scale image processing implementation under Hadoop platform[J].Computer Engineering and Design,2017,38(4):976-980.(in Chinese)
谭台哲,向云鹏.Hadoop平台下海量图像处理实现[J].计算机工程与设计,2017,38(4):976-980.
[4]BRAGA J R G,VELHO H F C,CONTE G,et al.An image matching system for autonomous UAV navigation based on neural network[C]∥International Conference on Control,Automation,Robotics and Vision.IEEE,2017:1-6.
[5]XU J J.Fast image registration method based on Harris and SIFT algorithm[J].Chinese Journal of Optics,2015,8(4):574-581.(in Chinese)
许佳佳.结合Harris与SIFT算子的图像快速配准算法[J].中国光学,2015,8(4):574-581.
[6]YUE X,SHANG Z H,QIANG Z P,et al.Astronomical Image Registration Combining Information Entropy and SIFT Algorithm[J].Computer Science,2015,42(6):57-60.(in Chinese)
岳昕,尚振宏,强振平,等.基于信息熵与SIFT算法的天文图像配准[J].计算机科学,2015,42(6):57-60.
[7]SU P F,HUANG S Q,WANG Y T,et al.An Image Registration Method Based on SIFT and Moment Features [J].Electronics Optics & Control,2016,23(8):89-91.(in Chinese)
苏培峰,黄世奇,王艺婷,等.用图像矩特征描述的SIFT特征SAR图像配准[J].电光与控制,2016,23(8):89-91.
[8]ZHAO J F,DAI Y Z,FAN Y R.Improvement the Fast Splicing of Unmanned Aerial Vehic Image[J].Geomatics & Spatial Information Technology,2016,39(9):182-185.(in Chinese)
赵俊峰,代亚贞,范玉茹.无人机影像快速拼接改进[J].测绘与空间地理信息,2016,39(9):182-185.
[9]CHEN Y X,SUN Q S,XU H Y,et al.Matching Method of Remote Sensing Images Based on SURF Algorithm and RANSAC Algorithm[J].Journal of Frontiers of Computer Science & Technology,2012,6(9):822-828.(in Chinese)
陈艺虾,孙权森,徐焕宇,等.SURF算法和RANSAC算法相结合的遥感图像匹配方法[J].计算机科学与探索,2012,6(9):822-828.
[10]LI H Y,ZHANG R Z.An Improved Image Stitching Algorithm Based on SURF Feature Matching[J].Journal of Taiyuan University of Technology,2016,47(1):91-95.(in Chinese)
李海洋,张睿哲.一种改进的基于SURF特征匹配的图像拼接算法[J].太原理工大学学报,2016,47(1):91-95.
[11]MARTINI H,SPIROVA M,STRAMBACH K.Geometric alge-bra of strictly convex Minkowski planes[J].Aequationes Mathe-maticae,2014,88(1-2):49-66.
[12]MOREL J M,YU G.ASIFT:A New Framework for Fully Affine Invariant Image Comparison[J].Siam Journal on Imaging Sciences,2009,2(2):438-469.
[13]YU Y,HUANG K,CHEN W,et al.A Novel Algorithm for View and Illumination Invariant Image Matching[J].IEEE Transactions on Image Processing,2012,21(1):229-240.
[14]CHEN M,SHAO Z,LI D,et al.Invariant matching method for different viewpoint angle images[J].Applied Optics,2013,52(1):96-104.
[15]MOHANTY P K,PARHI D R.A new hybrid optimization algorithm for multiple mobile robots navigation based on the CS-ANFIS approach[J].Memetic Computing,2015,7(4):255-273.
[16]LIU X,TIAN Z,CHAI C,et al.Multiscale registration of remote sensing image using robust SIFT features in Steerable-Domain[J].Egyptian Journal of Remote Sensing & Space Science,2011,14(2):63-72.
[17]GARG B,SHARMA G K.A Quality-aware Energy-scalable Gaussian Smoothing Filter for Image Processing Applications[J].Microprocessors & Microsystems,2016,45:1-9.
[18]CHEN X.An Algorithm Development Environment for Problem-Solving[C]∥International Conference on Computational Problem-Solving.IEEE,2010:85-90.
[19]LI S,YU J X,HAO X H,et al.Probabilistic Threshold Group k-nearest Neighbor Queries Method Based on Uncertain Voronoi Diagram [J].Journal of Chinese Computer Systems,2017,38(1):44-48.(in Chinese)
李松,于嘉希,郝晓红,等.不确定Voronoi图的概率阈值组k最近邻查询方法[J].小型微型计算机系统,2017,38(1):44-48.
[20]WU X,ZHAO Q,BU W.A SIFT-based contactless palmprint verification approach using iterative RANSAC and local palmprint descriptors[J].Pattern Recognition,2014,47(10):3314-3326.
[21]MOREL J M,YU G.ASIFT:A New Framework for Fully Affine Invariant Image Comparison[J].Siam Journal on Imaging Sciences,2009,2(2):438-469.
[22]WANG Z C,LU Y,XUE L X.Vehicle Video Tracking Based on Adaptive Dichotomy Bounded Partial Correlation Image Match Algorithm.Journal of Chongqing University of Technology(Natural Science),2017,31(6):147-153.(in Chinese)
王佐成,卢宇,薛丽霞.基于部分有界互相关图像匹配算法的车辆视频跟踪.重庆理工大学学报(自然科学版),2017,31(6):147-153.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

改进SIFT算法结合两级特征匹配的无人机图像匹配算法

UAV Image Matching Algorithm Based on Improved SIFT Algorithm and Two-stage Feature Matching

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

Metrics

本文评价

推荐阅读 0

[1]	高玉潼, 雷为民, 原玥. 复杂环境下基于聚类分析的人脸目标识别 Face Recognition Based on Cluster Analysis in Complex Environment 计算机科学, 2020, 47(7): 111-117. https://doi.org/10.11896/jsjkx.190500004
[2]	李昆仑,孙硕. 基于改进SIFT算法的图像复制粘贴篡改检测 Image Copy-Paste Tampering Detection Based on Improved SIFT Algorithm 计算机科学, 2016, 43(Z6): 179-183. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.042
[3]	任伟建,王子维,康朝海. 基于改进SIFT算法的无人机遥感图像匹配 Remote Sensing Image of UAV Registration Based on Improved SIFT Algorithm 计算机科学, 2015, 42(Z11): 179-182.
[4]	岳昕,尚振宏,强振平,刘辉,付晓东,张志华. 基于信息熵与SIFT算法的天文图像配准 Astronomical Image Registration Combining Information Entropy and SIFT Algorithm 计算机科学, 2015, 42(6): 57-60. https://doi.org/10.11896/j.issn.1002-137X.2015.06.013
[5]	王万同，韩志刚，刘鹏飞. 基于SIFT点特征和Canny边缘特征匹配的多源遥感影像配准研究 Multi-sensor Image Registration Algorithm Based on SIFT Points and Canny Edge Features Matching 计算机科学, 2011, 38(7): 287-289.