张瑞,颜青松,曲英杰,邓非,蔡亚锋

• 1:武汉大学
• 2:武汉天际航信息科技股份有限公司

摘要(Abstract)：

针对城市场景中大量存在的边线结构特征,该文提出了一种融合SFM先验信息的城市三维线段重建算法。该文算法首先在影像金字塔中构建精简的二维线段集;然后将相机位姿及稀疏点等数据作为先验信息,引入极线约束、方向约束和深度约束构建匹配线对;最后根据匹配线对重建出三维线段集。实验结果表明,该文提出的三维线段重建算法,在保持场景完整性的同时,能够有效地减少线段误匹配和重建结果冗余,缩短重建时间,提高三维线段重建结果精度。

关键词(KeyWords)： 三维线段重建;LSD;SFM;线段匹配

Abstract:

Keywords:

基金项目(Foundation): 四川省科技计划资助项目(2019YFG0460)

作者(Author): 张瑞,颜青松,曲英杰,邓非,蔡亚锋

DOI: 10.16251/j.cnki.1009-2307.2021.08.009

参考文献(References)：

• [1]邓非，颜青松，肖腾．多视密集匹配并行传播GPU-PatchMatch算法[J]．测绘学报，2020,49(2):181-190.(DENG Fei,YAN Qingsong,XIAO Teng.A GPU-PatchMatch multi-view dense matching algorithm based on parallel propagation[J].Acta Geodaetica et Cartographica Sinica,2020,49(2):181-190．）
• [2]ILLINGWORTH J,KITTLER J.A survey of the hough transform[J].Computer Vision,Graphics,and Image Processing,1988,44(1):87-116．
• [3]CANNY J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6):679-698．
• [4]GROMPONE VON GIOI R,JAKUBOWICZ J,MOREL JM,et al.LSD:a fast line segment detector with a false detection control[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(4):722-732．
• [5]AKINLAR C,TOPAL C.EDLines:a real-time line segment detector with a false detection control[J].Pattern Recognition Letters,2011,32(13):1633-1642．
• [6]WANG Z H,WU F C,HU Z Y.MSLD:a robust descriptor for line matching[J].Pattern Recognition,2009,42(5):941-953．
• [7]ZHANG L L,KOCH R.Line matching using appearance similarities and geometric constraints[C]∥Pattern Recognition.Berlin:Springer,2012:236-245．
• [8]LI K,YAO J,LU X H.Robust line matching based on Ray-Point-Ray structure descriptor[C]∥Computer Vision:ACCV 2014 Workshops.Cham:Springer International Publishing,2015:554-569．
• [9]LI K,YAO J,LU X H,et al.Hierarchical line matching based on line-junction-line structure descriptor and local homography estimation[J].Neurocomputing,2016,184:207-220．
• [10]FAN B,WU F C,HU Z Y.Robust line matching through line-point invariants[J].Pattern Recognition,2012,45(2):794-805．
• [11]JIA Q,GAO X K,FAN X,et al.Novel coplanar linepoints invariants for robust line matching across views[C]∥Computer Vision:ECCV 2016.Cham:Springer International Publishing,2016:599-611．
• [12]欧阳欢，范大昭，纪松，等．结合离散化描述与同名点约束的线特征匹配[J]．测绘学报，2018,47(10):1363-1371.(OUYANG Huan,FAN Dazhao,JI Song,et al.Line matching based on discrete description and conjugate point constraint[J].Acta Geodaetica et Cartographica Sinica,2018,47(10):1363-1371．）
• [13]WANG L,NEUMANN U,YOU S Y.Wide-baseline image matching using line signatures[C]∥2009IEEE12th International Conference on Computer Vision.Piscataway:IEEE,2009:1311-1318．
• [14]BARTOLI A,STURM P.Structure-from-motion using lines:representation,triangulation,and bundle adjustment[J].Computer Vision and Image Understanding,2005,100(3):416-441．
• [15]JAIN A,KURZ C,THORMHLEN T,et al.Exploiting global connectivity constraints for reconstruction of 3Dline segments from images[C]∥2010IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2010:1586-1593．
• [16]ZHANG L L,KOCH R.Structure and motion from line correspondences:representation,projection,initialization and sparse bundle adjustment[J].Journal of Visual Communication and Image Representation,2014,25(5):904-915．
• [17]HOFER M,MAURER M,BISCHOF H.Efficient 3Dscene abstraction using line segments[J].Computer Vision and Image Understanding,2017,157:167-178．
• [18]WU C C.Towards linear-time incremental structure from motion[C]∥2013International Conference on 3DVision:3DV 2013.Piscataway:IEEE,2013:127-134．
• [19]SCHNBERGER J L,ZHENG E L,FRAHM J M,et al.Pixelwise view selection for unstructured multiview stereo[C]∥Computer Vision:ECCV 2016.Cham:Springer International Publishing,2016:501-518．
• [20]ROMANONI A,MATTEUCCI M.Mesh-based camera pairs selection and occlusion-aware masking for mesh refinement[J].Pattern Recognition Letters,2019,125:364-372．
• [21]HOFER M,DONOSER M,BISCHOF H.Semi-global3Dline modeling for incremental structure-from-motion[C]∥Proceedings of the British Machine Vision Conference 2014.[S.l.]:[s.n.],2014．
• [22]FELZENSZWALB P F,HUTTENLOCHER D P.Efficient graph-based image segmentation[J].International Journal of Computer Vision,2004,59(2):167-181．
• [23]STRECHA C,VON HANSEN W,VAN GOOL L,et al.On benchmarking camera calibration and multiview stereo for high resolution imagery[C]∥2008IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2008:1-8．
• [24]邓非，陈欣，颜青松，等．带线约束的摄影测量网格变分精化算法[J]．测绘学报，2020,49(4):469-479.(DENGFei,CHEN Xin,YAN Qingsong,et al.Variational refinement of mesh with line constraint for photogrammetry[J].Acta Geodaetica et Cartographica Sinica,2020,49(4):469-479.)