陈智君,李浩,周弈,温四林

• 1:河海大学

摘要(Abstract)：

针对传统的半全局匹配算法在处理视差变化大、遮挡严重的城市航空影像时,存在匹配精度下降、匹配效率低下的问题,提出了一种基于区域生长的半全局密集匹配方法。采用区域生长算法获取影像的初始视差,并从初始匹配点中挑选可靠的点作为视差控制点;利用区域生长获取的视差图,限制各个方向动态规划的过程以加速最优路径的搜索;通过视差控制点对动态规划的路径进行修正,避免错误匹配代价的传播。基于城区无人机影像的实验结果表明,所提算法不仅可以提高匹配结果正确率,还能使耗费的内存和时间都不到原算法的50%。

关键词(KeyWords)： 半全局匹配;互信息;区域生长;动态规划

Abstract:

Keywords:

基金项目(Foundation): 江苏省自然科学基金项目(BK2012812)

作者(Author): 陈智君,李浩,周弈,温四林

DOI: 10.16251/j.cnki.1009-2307.2017.05.003

参考文献(References)：

• [1]HIRSCHMULLER H.Stereo processing by semiglobal matching and mutual information[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2008,30(2):328-341.
• [2]BOYKOV Y,VEKSLER O,ZABIH R.Fast approximate energy minimization via graph cuts[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2001,1(11):1222-1239.
• [3]SUN J,ZHENG N N,SHUM H Y.Stereo matching using belief propagation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2003,25(7):787-800.
• [4]郭永彩,魏朋玉,高潮.采用多级动态规划实现立体匹配[J].光学精密工程,2009,17(7):1745-1751.(GUO Yongcai,WEI Pengyu,GAO Chao.Stereo correspondence using multi-stage dynamic programming[J].Optics and Precision Engineering,2009,17(7):1745-1751.)
• [5]高波,马利庄.加入结构约束的半全局立体匹配方法[J].计算机应用与软件,2009,26(2):244-247.(GAO Bo,MA Lizhuang.Semi-globle stereo matching combined with structure constraint[J].Computer Applications and Software,2009,26(2):244-247.)
• [6]HERMANN S,KLETTE R.Iterative semi-global matching for robust driver assistance systems[M].Computer Vision-ACCV 2012.Belin:Springer Berlin Heidelberg,2013:465-478.
• [7]HU H,RZHANOV Y,HATCHER P J,et al.Binary adaptive semi-global matching based on image edges[C]//Seventh International Conference on Digital Image Processing.International Society for Optics and Photonics,2015.
• [8]吕佩育.基于影像分割的无人机影像密集匹配算法研究与实现[D].西安:西安科技大学,2013.(LV Peiyu.Research on segment-based dense matching algorithm and its realization in UAV images[D].Xi'an:Xi'an University of Science and Technology,2013.)
• [9]吴军,姚泽鑫,程门门.融合SIFT与SGM的倾斜航空影像密集匹配[J].遥感学报,2015,19(3):431-442.(WU Jun,YAO Zexin,CHENG Menmen.Airborne oblique stereo image dense matching by integrating SIFT and SGM algorithm[J].Journal of Remote Sensing,2015,19(3):431-442.)
• [10]唐丽,吴成柯,刘侍刚,等.基于区域增长的立体像对稠密匹配算法[J].计算机学报,2004,27(7):936-943.(TANG Li,WU Chengke,LIU Shigang,et al.Image dense stereo matching by technique of region growing[J].Chinese Journal of Computers,2004,27(7):936-943.)
• [11]林国余,张为公.基于控制点的分层双向动态规划立体匹配算法[J].信息与控制,2006,35(3):411-416.(LIN Guoyu,ZHANG Weigong.A control-point-based stereo matching algorithm for layered and bidirectional dynamic programming[J].Information and Control,2006,35(3):411-416.)
• [12]BOBICK A F,INTILLE S S.Large occlusion stereo[J].International Journal of Computer Vision,1999,33(3):181-200.
• [13]张彦峰.利用多条件约束的航空影像逐像素密集匹配算法研究[D].北京:中国测绘科学研究院,2014.(ZHANG Yanfeng.Pixel-wise dense matching of aerial images with multi-conditional constraints[D].Beijing:Chinese Academy of Surveying and Mapping,2014.)
• [14]KIM J,KOLMOGOROV V,ZABIH R.Visual correspondence using energy minimization and mutual information[C]//Computer Vision,IEEE International Conference on,[S.l.]:IEEE Computer Society,2003:1033-1040.
• [15]张浩峰,赵春霞.基于地面控制点的迭代动态规划立体匹配算法[J].仪器仪表学报,2008,29(8):1665-1669.(ZHANG Haofeng,ZHAO Chunxia.Ground control point based stereo matching via iterative dynamic programming[J].Chinese Journal of Scientific Instrument,2008,29(8):1665-1669.)