满孝成,姚国标,张传辉,李兵,郑国强,王树臻

• 1:山东建筑大学测绘地理信息学院

摘要(Abstract)：

针对海岸带特殊纹理影像存在地物单一、纹理匮乏或重复等问题,该文提出一种融合多类特征的海岸带立体影像全自动配准方法。该算法分为3个阶段:①提取尺度不变特征变换(SIFT)关键点,采用欧氏距离比率获得初始匹配,并进一步采用归一互相关匹配(NCC)和随机抽样一致性算法剔除误匹配,继而估计影像间的单应矩阵;②利用改进的Forstner算子对左影像提取均匀分布的角点特征,并利用单应矩阵和NCC匹配进行同名点匹配;③基于上述多类特征的精匹配结果,计算影像间投影变换模型,实现影像的配准。最后,为验证该文算法的有效性,选取3组存在较大尺度、旋转及视角变化的海岸带特殊纹理影像进行综合对比试验,结果表明该文算法可实现全自动配准,并且在匹配点数量、配准精度以及匹配点空间分布等方面具有优势。

关键词(KeyWords)： 海岸带;特殊纹理;多类特征;单应矩阵;全自动配准

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41601489)

作者(Author): 满孝成,姚国标,张传辉,李兵,郑国强,王树臻

DOI: 10.16251/j.cnki.1009-2307.2020.08.020

参考文献(References)：

• [1] 苑晶晶,吕永龙,贺桂珍.海洋可持续发展目标与海洋和滨海生态系统管理[J].生态学报,2017,37(24):8139-8147.(YUAN Jingjing,LYU Yonglong,HE Guizhen.Sustainable development goals for oceans and marine and coastal ecosystem-based management[J].Acta Ecologica Sinica,2017,37(24):8139-8147.)
• [2] 王雅萍,陈宜金,谢东海,等.面向无人机水域影像的自动拼接方法[J].长江科学院院报,2014,31(5):92-96.(WANG Yaping,CHEN Yijin,XIE Donghai,et al.Automatic mosaic method for UAV water-area images[J].Journal of Yangtze River Scientific Research Institute,2014,31(5):92-96.)
• [3] 徐全飞.海洋遥感图像亚像素配准算法关键技术研究[D].北京:中国科学院大学,2017.(XU Quanfei.Research on key techniques of sub-pixel registration algorithm for marine remote sensing image[D].Beijing:University of Chinese Academy of Sciences,2017.)
• [4] 徐芳,邓非.数字摄影测量学基础[M].武汉:武汉大学出版社,2017:4-6.(XU Fang,DENG Fei.Fundamentals of digital photogrammetry[M].Wuhan:Wuhan University Press,2017:4-6.)
• [5] LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
• [6] 孙雪强,黄旻,张桂峰,等.基于改进SIFT的多光谱图像匹配算法[J].计算机科学,2019,46(4):280-284.(SUN Xueqiang,HUANG Min,ZHANG Guifeng,et al.Multispectral image matching algorithm based on improved SIFT[J].Computer Science,2019,46(4):280-284.)
• [7] 宋耀鑫,张丹丹,唐伶俐,等.基于ASIFT算法的低重叠度无人机影像拼接方法[J].遥感技术与应用,2015,30(4):725-730.(SONG Yaoxin,ZHANG Dandan,TANG Lingli,et al.An approach to stitch UAV image with low overlap based on ASIFT algorithm[J].Remote Sensing Technology and Application,2015,30(4):725-730.)
• [8] YU G S,MOREL J M.ASIFT:an algorithm for fully affine invariant comparison[J].Image Processing on Line,2011,1:11-38.
• [9] KE Y,SUKTHANKAR R.PCA-SIFT:a more distinctive representation for local image descriptors[J].Computer Vision and Pattern Recognition,2004(2):506-513.
• [10] 袁修孝,陈时雨,张勇.利用PCA-SIFT进行特殊纹理航摄影像匹配[J].武汉大学学报(信息科学版),2016,41(9):1137-1144.(YUAN Xiuxiao,CHEN Shiyu,ZHANG Yong.Special textural aerial image matching based on PCA-SIFT feature matching[J].Geomatics and Information Science of Wuhan University,2016,41(9):1137-1144.)
• [11] 马方龙.基于归一化积相关匹配的彩色图像灰度化研究[D].兰州:兰州大学,2018.(MA Fanglong.Research on color-to-gray conversion based on normalized cross correlation[D].Lanzhou:Lanzhou University,2018.)
• [12] 张源峰.基于图像特征与灰度值的快速匹配算法研究[D].兰州:兰州理工大学,2018.(ZHANG Yuanfeng.Research on fast matching algorithm based on image features and gray values[D].Lanzhou:Lanzhou University of Technology,2018.)
• [13] 贺一楠,耿娟,秦军,等.结合Forstner与NCC约束的UAV图像配准研究[J].国土资源遥感,2015,27(1):48-54.(HE Yinan,GENG Juan,QIN Jun,et al.Integration of Forstner and NCC constraint for UAV image registration[J].Remote Sensing for Land & Resources,2015,27(1):48-54.)
• [14] 何志伟,王晓红,邓仕雄,等.一种喀斯特地貌无人机遥感影像的快速匹配方法[J/OL].测绘科学,2019[2019-05-06].http://kns.cnki.net/kcms/detail/11.4415.P.20190226.0946.014.html.(HE Zhiwei,WANG Xiaohong,DENG Shixiong,et al.A fast matching method for remote sensing images of UAVs in Karst landform[J/OL].Science of Surveying and Mapping,2019[2019-05-06].http://kns.cnki.net/kcms/detail/11.4415.P.20190226.0946.014.html.)
• [15] 华赛男.无人机数字影像匹配算法研究[D].长沙:长沙理工大学,2018.(HUA Sainan.Research on UAV digital image matching algorithm[D].Changsha:Changsha University of Science & Technology,2018.)
• [16] 息朝健,郭三学.基于简化Forstner算子改进的SIFT无人机图像识别算法[J].计算机应用与软件,2012,29(5):254-255,300.(XI Chaojian,GUO Sanxue.Improved SIFT identification algorithm for UAV image based on simplified Forstner operator[J].Computer Applications and Software,2012,29(5):254-255,300.)
• [17] 张凯南,杨志强,张学伟,等.基于低空摄影测量影像的特征点提取算子比较研究[J].地理与地理信息科学,2017,33(3):30-35.(ZHANG Kainan,YANG Zhiqiang,ZHANG Xuewei,et al.Study on feature point extraction operators based on low alititude photogrammetry image[J].Geography and Geo-Information Science,2017,33(3):30-35.)
• [18] 姚国标,邓喀中,张力,等.融合互补仿射不变特征的倾斜立体影像高精度自动配准方法[J].测绘学报,2013,42(6):869-876,883.(YAO Guobiao,DENG Kazhong,ZHANG Li,et al.An automated registration method with high accuracy for oblique stereo images based on complementary affine invariant features[J].Acta Geodaetica et Cartographica Sinica,2013,42(6):869-876,883.)
• [19] 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,2017,26(11):55-59,64.(SUN Hao,GAO Junqiang,XU Susu.UAV image matching based on SURF algorithm and improved RANSAC algorithm[J].Engineering of Surveying and Mapping,2017,26(11):55-59,64.)
• [20] 王竞雪,张晶.局部仿射变换的自适应窗口立体影像匹配算法[J/OL].测绘科学,2019[2019-05-06].http://kns.cnki.net/kcms/detail/11.4415.P.20190505.1720.048.html.(WANG Jingxue,ZHANG Jing.Adaptive window stereo matching algorithm combining local affine transformation[J].Science of Surveying and Mapping,2019[2019-05-06].http://kns.cnki.net/kcms/detail/11.4415.P.20190505.1720.048.html.)
• [21] 岳春宇,江万寿.几何约束和改进SIFT的SAR影像和光学影像自动配准方法[J].测绘学报,2012,41(4):570-576.(YUE Chunyu,JIANG Wanshou.An automatic registration algorithm for SAR and optical images based on geometry constraint and improved SIFT[J].Acta Geodaetica et Cartographica Sinica,2012,41(4):570-576.)