FREAK和改进的RANSAC算法在影像匹配中的应用
|
摘要
针对倾斜摄影中包含多个视角的影像而使匹配速度较慢的问题,提出了一种Speeded up robust features(SURF)、Fast Retina Keypoint(FREAK)和改进的Random Sample Consensus(RANSAC)算法相结合的影像匹配算法。首先利用SURF算法提取出稳健的特征点,然后利用FREAK描述符对特征点进行描述,在影像匹配阶段首先进行预匹配,然后用改进的RANSAC算法剔除错误匹配点对。经实验比较分析后得出:该算法在效率和匹配精度上都有较好的鲁棒性。
In view of the problem that the matching speed is slow where images with multiple view angles in the oblique photography,an improved photography matching algorithm based on SURF,FREAK and improved RANSAC was proposed in oblique photography.Firstly,using the SURF algorithm to extract the robust feature points.Then using the FREAK descriptors to describe the features.In the photography matching phase,after the pre-matching performed and then the error matching points are eliminated by the improved RANSAC algorithm.Through comparison and analysis,we found that,the algorithm has great robustness in both efficiency and matching accuracy.
In view of the problem that the matching speed is slow where images with multiple view angles in the oblique photography,an improved photography matching algorithm based on SURF,FREAK and improved RANSAC was proposed in oblique photography.Firstly,using the SURF algorithm to extract the robust feature points.Then using the FREAK descriptors to describe the features.In the photography matching phase,after the pre-matching performed and then the error matching points are eliminated by the improved RANSAC algorithm.Through comparison and analysis,we found that,the algorithm has great robustness in both efficiency and matching accuracy.
引文
[1]吉大纯,李学军,侯金宝.影像匹配中的若干基本问题研究[J].计算机技术与发展,2010,20(5):246-249.
[2]孙运豪,高洪,胡朵朵,等.无人机倾斜摄影在文物修复中的应用[J].北京测绘,2017(5):92-95,108.
[3]闫利,叶志云.几何约束条件下的SIFT倾斜影像匹配[J].测绘通报,2016(1):37-40.
[4]索春宝,杨东清,刘云鹏.多种角度比较SIFT,SURF,BRISK,ORB,FREAK算法[J].北京测绘,2014(4):23-26.
[5]LOWE D G.Object Recognition from Local Scale-invariant Features[C]//Computer Vision,1999.The Proceedings of The Seventh IEEE International Conference on.IEEE,1999,(2):1150-1157.
[6]BAY H,TUYTELAARS T,VAN Gool L.Surf:Speeded Up Robust Features[C].Computer VisionECCV 2006 International Conference on.IEEE,2006:404-417.
[7]LEUTENEGGER S,CHLI M,SIEGWART R Y.BRISK:Binary Robust Invariant Scalable Keypoints[C]//Computer Vision(ICCV),2011IEEE International Conference on.IEEE,2011:2548-2555.
[8]RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:An Efficient Alternative To SIFT or SURF[C]//Computer Vision(ICCV),2011IEEE international conference on.IEEE,2011:2564-2571.
[9]陈岷,徐伟芳.基于图像匹配的高精度室内定位技术研究[J].北京测绘,2017,(5):104-108.
[10]ALAHI A,ORTIZ R,Vandergheynst P.Freak:Fast Retina Keypoint[C]//Computer Vision and Pattern Recognition(CVPR),2012IEEE Conference On.IEEE,2012:510-517.
[11]FISCHLER M A,BOLLES R C.Random Sample Consensus:A Paradigm For Model Fitting With Applications To Image Analysis and Automated Cartography[J].Communications of the ACM,1981,24(6):381-395.
[12]王灿进,孙涛,陈娟.基于FREAK特征的快速景象匹配[J].电子测量与仪器学报,2015,29(2):204-212.
[13]顾亚军,胡伏原.一种基于分数阶微分的FREAK改进算法[J].苏州科技学院学报:自然科学版,2016,33(4):62-67.
[14]谢红,王石川,解武.基于改进的FREAK算法的图像特征点匹配[J].2016,43(4):35-40.
[15]房贻广,刘武,高梦珠,等.基于FREAK描述子的精确图像配准改进算法[J].计算机应用,2016,36(12):3402-3405.
[16]顾漪,王保平.基于旋转SURF算子的图像配准新方法[J].计算机测量与控制,2017,25(7):197-201.
[17]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.
[18]孙灏,高俊强,许苏苏.基于SURF算法和改进RANSAC算法的无人机影像匹配[J].测绘工程,2017(11):012.
[19]佘建国,徐仁桐,陈宁.基于ORB和改进RANSAC算法的图像拼接技术[J].江苏科技大学学报(自然科学版),2015,29(2):164-169.
[20]戴雪梅,郎朗,陈孟元.基于改进ORB的图像特征点匹配研究[J].电子测量与仪器学报,2016,30(2):233-240.
[21]机器视觉课题组.中国科学院自动化研究所模式识别国家重点实验室[EB/OL].(2011-02-04)[2017-10-15].http://vision.ia.ac.cn/zh/d ata/index.html.
[2]孙运豪,高洪,胡朵朵,等.无人机倾斜摄影在文物修复中的应用[J].北京测绘,2017(5):92-95,108.
[3]闫利,叶志云.几何约束条件下的SIFT倾斜影像匹配[J].测绘通报,2016(1):37-40.
[4]索春宝,杨东清,刘云鹏.多种角度比较SIFT,SURF,BRISK,ORB,FREAK算法[J].北京测绘,2014(4):23-26.
[5]LOWE D G.Object Recognition from Local Scale-invariant Features[C]//Computer Vision,1999.The Proceedings of The Seventh IEEE International Conference on.IEEE,1999,(2):1150-1157.
[6]BAY H,TUYTELAARS T,VAN Gool L.Surf:Speeded Up Robust Features[C].Computer VisionECCV 2006 International Conference on.IEEE,2006:404-417.
[7]LEUTENEGGER S,CHLI M,SIEGWART R Y.BRISK:Binary Robust Invariant Scalable Keypoints[C]//Computer Vision(ICCV),2011IEEE International Conference on.IEEE,2011:2548-2555.
[8]RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:An Efficient Alternative To SIFT or SURF[C]//Computer Vision(ICCV),2011IEEE international conference on.IEEE,2011:2564-2571.
[9]陈岷,徐伟芳.基于图像匹配的高精度室内定位技术研究[J].北京测绘,2017,(5):104-108.
[10]ALAHI A,ORTIZ R,Vandergheynst P.Freak:Fast Retina Keypoint[C]//Computer Vision and Pattern Recognition(CVPR),2012IEEE Conference On.IEEE,2012:510-517.
[11]FISCHLER M A,BOLLES R C.Random Sample Consensus:A Paradigm For Model Fitting With Applications To Image Analysis and Automated Cartography[J].Communications of the ACM,1981,24(6):381-395.
[12]王灿进,孙涛,陈娟.基于FREAK特征的快速景象匹配[J].电子测量与仪器学报,2015,29(2):204-212.
[13]顾亚军,胡伏原.一种基于分数阶微分的FREAK改进算法[J].苏州科技学院学报:自然科学版,2016,33(4):62-67.
[14]谢红,王石川,解武.基于改进的FREAK算法的图像特征点匹配[J].2016,43(4):35-40.
[15]房贻广,刘武,高梦珠,等.基于FREAK描述子的精确图像配准改进算法[J].计算机应用,2016,36(12):3402-3405.
[16]顾漪,王保平.基于旋转SURF算子的图像配准新方法[J].计算机测量与控制,2017,25(7):197-201.
[17]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.
[18]孙灏,高俊强,许苏苏.基于SURF算法和改进RANSAC算法的无人机影像匹配[J].测绘工程,2017(11):012.
[19]佘建国,徐仁桐,陈宁.基于ORB和改进RANSAC算法的图像拼接技术[J].江苏科技大学学报(自然科学版),2015,29(2):164-169.
[20]戴雪梅,郎朗,陈孟元.基于改进ORB的图像特征点匹配研究[J].电子测量与仪器学报,2016,30(2):233-240.
[21]机器视觉课题组.中国科学院自动化研究所模式识别国家重点实验室[EB/OL].(2011-02-04)[2017-10-15].http://vision.ia.ac.cn/zh/d ata/index.html.