摘要
多视密集匹配是倾斜摄影测量中的研究热点,提出一种基于改进的PatchMatch多视密集匹配算法。算法采用自适应归一化互相关作为匹配代价,由PatchMatch算法迭代运算优化得到影像深度图,再基于可见性融合深度图得到场景的三维点云。该方法在匹配所需影像的选择上,采用了同时考虑视图层和像素层的影像选择方法,在测度选择上,提出了具有边缘特性的相似性测度。最后,对影像进行密集匹配试验,结果表明,产生的点云质量得到一定的改善,验证了该方法的有效性。
Dense matching with Multi-view is a research hotspot in tilting photogrammetry. This paper proposes a multi-view matching algorithm based on improved PatchMatch. The algorithm uses the adaptive normalized cross correlation as the matching cost. The image depth map is obtained by the iterative operation of the PatchMatch algorithm, and then the 3 D point cloud of the scene is obtained based on the visible fusion depth map. This method adopts a method of image selection considering both the view layer and the pixel layer, and proposes a similarity measure with edge characteristic in the selection of the matching image. Finally, the dense matching experiment of the image shows that the quality of the generated cloud is improved and the effectiveness of the method is verified.
引文
[1] 杨国东,王民水.倾斜摄影测量技术应用及展望[J].测绘与空间地理信息,2016,39(1):13-15
[2] 何豫航,岳俊.基于CMVS/PMVS多视角密集匹配方法的研究与实现[J].测绘地理信息,2013,38(3):20-23
[3] Goesele M,Snavely N,Curless B,et al.Multi-view Stereo for Community Photo Collections[C].IEEE 11th International Conference on Computer Vision,Brazil,2007
[4] Furukawa Y,Ponce J.Accurate,Dense,and Robust Multi-view Stereopsis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(8):1 362-1 376
[5] Campbell N D F,Vogiatzis G,Hernández C H,et al.Using Multiple Hypotheses to Improve Depth-Maps for Multi-view Stereo[C].European Conference on Computer Vision,Marseille,France,2008
[6] 王竞雪,朱庆,王伟玺.多匹配基元集成的多视影像密集匹配方法[J].测绘学报,2013,42(5):691-698
[7] Seitz S M,Curless B,Diebel J,et al.A Comparison and Evaluation of Multi-view Stereo Reconstruction Algorithms[C].2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,New York,2006
[8] Bleyer M,Rhemann C,Rother C.PatchMatch Stereo-Stereo Matching with Slanted Support Windows[C].British Machine Vision Conference,UK,2011
[9] Furukawa Y.Multi-view Stereo:A Tutorial[J].Foundations and Trends in Computer Graphics and Vision,2015,9(1/2):1-148
[10] Goesele M,Snavely N,Curless B,et al.Multi-view Stereo for Community Photo Collections[C].2007 IEEE 11th International Conference on Computer Vision,Brazil,2007
[11] Shen S.Accurate Multiple View 3D Reconstruction Using Patch-Based Stereo for Large-Scale Scenes[J].IEEE Transactions on Image Processing,2013,22(5):1 901-1 914
[12] Strecha C,Hansen W V,Gool L V,et al.On Benchmarking Camera Calibration and Multi-view Stereo for High Resolution Imagery[C].2008 IEEE Conference on Computer Vision and Pattern Recognition,Anchorage,USA,2008