面向全景拼接的图像配准技术研究及应用

J4 ›› 2016, Vol. 38 ›› Issue (02): 317-324.

面向全景拼接的图像配准技术研究及应用

兰红,洪玉欢,高晓林

(江西理工大学信息工程学院,江西赣州 341000)

收稿日期:2015-01-07 修回日期:2015-04-09 出版日期:2016-02-25 发布日期:2016-02-25
基金资助:
江西省教育厅科技项目(GJJ14430);江西省教育厅重点项目（赣教技字［12770］号）

Research and application of image registration
technology in panoramic stitching

LAN Hong,HONG Yuhuan,GAO Xiaolin

(School of Information Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China)

Received:2015-01-07 Revised:2015-04-09 Online:2016-02-25 Published:2016-02-25

摘要/Abstract

摘要：

针对SIFT算法在生成特征向量和进行特征匹配过程中存在的计算量较大、容易产生误匹配等不足,提出一种优化的SIFT配准算法。优化算法首先引入拉普拉斯算子对图像边缘进行锐化处理,结合图像单元信息投影熵原理提取分块图像特征；再依据投影熵矢量欧氏距离最小揣度进行特征匹配；最后利用改进的随机抽样一致性算法删除误匹配。改进算法应用于全景图像拼接中。实验表明,与原始SIFT配准算法相比,优化算法能够有效提高算法效率，减少错误匹配,取得了较好的匹配效果。

关键词: 全景拼接, 图像配准, SIFT算法, 单元信息投影熵

Abstract:

Aiming at solving the insufficiencies of the SIFT registration algorithm such as large calculation, error matching when generating feature vectors and doing feature matching, we propose an optimized SIFT registration algorithm. The optimized registration algorithm firstly sharpens the edge of images by bringing in the Laplacian operator and extracts the characteristics of block images via the projection entropy of image unit information. Then feature points are matched according to the minimum Euclidean distance of entropy vector projection. Finally, the improved random sample consensus algorithm is adopted to eliminate error matching. We apply the optimized algorithm in panoramic mosaic and experimental results show that, the optimized registration algorithm exceeds the SIFT registration algorithm, which not only effectively improves the efficiency, but also reduces error matching, achieving good matching effect.

Key words: panoramic mosaic;image registration;SIFT algorithm;projection entropy of unit information

兰红,洪玉欢,高晓林. 面向全景拼接的图像配准技术研究及应用[J]. J4, 2016, 38(02): 317-324.

LAN Hong,HONG Yuhuan,GAO Xiaolin. Research and application of image registration
technology in panoramic stitching [J]. J4, 2016, 38(02): 317-324.

参考文献［16］

［1］	Chen Xianyi. Image registration technique and MATLAB programming［M］.Beijing:Electronic Industry Press,2009：1317.(in Chinese)
［2］	Chen Jinwei. Research on registration and stitching of remote sensing image of agile satellite［D］.Hangzhou:Zhejiang University,2014.(in Chinese)
［3］	Kupfer B, Netanyahu N S, Shimshoni I. An efficient SIFTbased modeseeking algorithm for subpixel registration of remotely sensed images［J］.Geoscience and Remote Sensing Letters,2014,12(2):379383.
［4］	Chen Mengting,Yan Dongmei,Wang Gang.Algorithm of highresolution remote sensing image matching based onHarris corner and SIFT descriptor［J］.Chinese Journal of Image and Graphics,2012,17(11):14531459.(in Chinese)
［5］	Zheng Yue,Cheng Hong,Sun Wenbang.Finding an optimal seamline through theshortest distance in the neighborhood［J］.Chinese Journal of Image and Graphics,2014,19(2):227233.(in Chinese)
［6］	Li Haichao, Hao Shengyong, Zhu Qi. Fast seamless mosaic algorithm for multiple remote sensing images［J］.Infrared and Laser Engineering,2011,40(7):13811386.(in Chinese)
［7］	Ji Ying,Lu Yueming.Method based on SIFT for recognition of flip images［J］.Application Research of Computers,2013,30(3):924925.(in Chinese)
［8］	Yu Lili,Dai Qing.Improved SIFT feature matching algorithm［J］.Computer Engineering,2011,37(2):210212.(in Chinese)
［9］	Wang Wantong,Han Zhigang,Liu Pengfei.Multisensor image registration algorithm based on SIFT points and Canny edge features matching［J］.Computer Science,2011,38(7):287289.(in Chinese)
［10］	Lowe D G.Distinctive image features from scale invariant key points［J］.International Journal of Computer Vision,2004,60(2):91110.
［11］	Liu Yunbo.Research on the key technology of image stitching［D］.Chengdu:University of Electronic Science and Technology,2013.(in Chinese)
［12］	Wang Suyun,Wang Xiaoming,Zhao Xueqing.Image denoising algorithms based on Laplacian operator and image inpainting［J］.Journal of Computer Applications,2012,32(10):27932797.(in Chinese)
［13］	Su Xiuqin,Liang Jinfeng.An improved target matching algorithm based on the unit of information entropy［J］.Acta Photonica Sinica,2009,38(11):30403043.(in Chinese)
［14］	Fischler M A,Bolles R C.Random sample consensus:A paradigm for model fitting with applications to image analysis and automated acrtography［J］.Communications of the ACM,1981,24(6):381395.
［15］	Lu Shan,Lei Yingjie,Kong Weiwei,et al.Fundamental matrix estimation based on probability analysis and sampling consensus［J］.Control and Decision,2012,27(3):425430.(in Chinese)
［16］	Zhang Dexiang,Zhang Jingjing,Wu Xiaopei,et al.Fusion of polarization image based on directionlets transform［J］.Journal of Electronics and Information,2011,33(12):27952800.(in Chinese)
	附中文参考文献：
［1］	陈显毅.图像配准技术及其MATLAB编程实现［M］.北京:电子工业出版社,2009.
［2］	陈锦伟.敏捷卫星遥感图像配准和拼接技术研究［D］.杭州：浙江大学,2014.
［4］	陈梦婷,闫冬梅,王刚.基于Harris角点和SIFT描述符的高分辨率遥感影像匹配算法［J］.中国图象图形学报,2012,17(11):14531459.
［5］	郑悦,程红,孙文邦.邻域最短距离法寻找最佳拼接缝［J］.中国图象图形学报,2014,19(2):227233.
［6］	李海超,郝胜勇,朱琦.多片遥感图像的快速无缝拼接方法［J］.红外与激光工程,2011,40(7):13811386.
［7］	及莹,陆月明.一种基于SIFT算法的图像镜像变换识别方法［J］.计算机应用研究,2013,30(3):924925.
［8］	于丽莉,戴青.一种改进的SIFT特征匹配算法［J］.计算机工程,2011,37(2):210212.
［9］	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［J］.计算机科学,2011,38(7):287289.
［11］	柳运波.全景图像拼接关键技术研究［D］.成都:电子科技大学,2013.
［12］	王素云,王小明,赵雪青.基于拉普拉斯算子和图像修补的图像去噪算法［J］.计算机应用,2012,32(10):27932797.
［13］	苏秀琴,梁金峰.一种基于单元信息熵的目标匹配改进算法［J］.光子学报,2009,38(11):30403043.
［15］	鲁珊,雷英杰,孔韦韦,等.基于概率抽样一致性的基础矩阵估计算法［J］.控制与决策,2012,27(3):425430.
［16］	张德祥,张晶晶,吴小培,等.基于Directionlets变换的偏振图像融合［J］.电子与信息学报,2011,33(12):27952800.

[1]	熊炜1,2，王传胜1，管来福1，童磊1，刘敏1，曾春艳1. 基于特征跟踪和网格路径运动的视频稳像算法[J]. 计算机工程与科学, 2020, 42(05): 843-850.
[2]	盛明伟，唐松奇，万磊，秦洪德，李俊. 基于改进CNN-RANSAC的水下图像特征配准方法[J]. 计算机工程与科学, 2020, 42(05): 859-868.
[3]	朱天宇，全惠敏，刘国才. 联合弯曲能量和标志点对应约束的非刚性医学图像配准[J]. 计算机工程与科学, 2019, 41(05): 851-857.
[4]	苏培峰1，黄世奇2，王艺婷1，刘代志1. 具有SIFT描述的多尺度角点图像配准[J]. 计算机工程与科学, 2017, 39(09): 1700-1705.
[5]	常方媛1，冯志勇1，徐超2. 基于SLIC区域分割的三维地形重建算法[J]. J4, 2015, 37(09): 1718-1723.
[6]	孟建良，王雅继. 最佳点平滑法寻找最佳拼接缝[J]. J4, 2015, 37(07): 1387-1392.
[7]	王天召，徐克虎，陈金玉. 基于K-means聚类和RANSAC的图像配准算法研究[J]. J4, 2014, 36(09): 1765-1769.
[8]	冯雪芳，吴锡生. 基于归一化边缘互信息与自适应加速粒子群的图像配准方法[J]. J4, 2013, 35(1): 119-123.
[9]	刘君1,2，武和雷3. 基于形状和灰度信息的断层图像二次配准算法[J]. J4, 2012, 34(12): 110-114.
[10]	周德龙,刘〓迎,吴巾一. 基于二维Gabor小波变换的角点匹配算法[J]. J4, 2011, 33(12): 61-65.
[11]	马政德杜云飞周海芳刘衡竹. 遥感图像配准中相似性测度的比较和分析[J]. J4, 2008, 30(2): 45-48.
[12]	郑明玲. 遥感多图像配准中自动提取特征点的并行算法[J]. J4, 2004, 26(10): 45-48.