基于标志点匹配算法的研究
|
摘要
复杂曲面的建模是计算机视觉和计算机图形学领域的重要研究内容,在工业制造、目标检测和过程质量控制中具有重要的应用价值。提出一种基于标志点约束的自动匹配建模方法,该方法利用粘贴在目标物体表面的标志点进行匹配,把局部采集的深度像数据匹配到同一坐标系下,实现复杂曲面的自动建模。该方法能有效地实现自由曲面的深度像匹配,并且过程中不需要人工操作就能实现复杂曲面的自动建模,操作简便,在实际工程中具有重要的应用价值。实验结果验证了算法的鲁棒性和有效性。
The modeling of complex surfaces is an important research content in the field of computer vision and computer graphics. It has important application value in industrial manufacturing, target detection and process quality control. An automatic matching modeling method based on marker point constraint is proposed. This method uses the marker points pasted on the surface of the target object to match, and the locally acquired depth image data is matched to the same coordinate system to realize the automatic modeling of complex surfaces. The method can effectively realize the depth image matching of the free-form surface, and the automatic modeling of the complex surface can be realized without manual operation in the process, and the operation is simple, and has important application value in practical engineering. The experimental results verify the robustness and effectiveness of the algorithm.
The modeling of complex surfaces is an important research content in the field of computer vision and computer graphics. It has important application value in industrial manufacturing, target detection and process quality control. An automatic matching modeling method based on marker point constraint is proposed. This method uses the marker points pasted on the surface of the target object to match, and the locally acquired depth image data is matched to the same coordinate system to realize the automatic modeling of complex surfaces. The method can effectively realize the depth image matching of the free-form surface, and the automatic modeling of the complex surface can be realized without manual operation in the process, and the operation is simple, and has important application value in practical engineering. The experimental results verify the robustness and effectiveness of the algorithm.
引文
[1]Jeon J H,Jung Y G,Kim H J,Lee S Y.Texture map generation for 3D reconstructed scenes[J].The Visual Computer,2016,32(6):955-65.
[2]何懂.相位辅助三维成像相关技术研究[D].深圳:深圳大学;2014.He D.Reseach on relevant technologies of Phaseaided three dimentional imaging[D].Shenzhen:Shenzhen university;2014.(in Chinese)
[3]Goldlcke B,Aubry M,Kolev K,Cremers D.A SuperResolution Framework for High-Accuracy Multiview Reconstruction[J].Int J Comput Vision 2014,106(2):172-91.
[4]Liu X M,Peng X,Yin Y K,Liu X L,Wu W.Generation of photorealistic 3D image using optical digitizer[J].Applied Optics,2012,51(9):1304-11.
[5]Ou P,Li B W,Wang Y J,Zhang S.Flexible real-time natural2D color and 3D shape measurement[J].Optics Express,2013,21(14):16736-41.
[6]殷永凯.相位辅助光学三维测量系统的标定[D].深圳:深圳大学;2012.Yin Y K.The calibration of Phase-aided optical threedimensional system[D].Shenzhen:Shenzhen University;2012(in Chinese)
[7]Li A M,Peng X,Yin Y K,Liu X L.Optical 3D digitizer for photorealistic imaging of movable cultural heritage[J].acta photonica sinica,2013,42(12):1421-9.
[8]Vrubel A,Bellon O R P,Silva L.A 3D reconstruction pipeline for digital preservation[C].Computer Vision and Pattern Recognition,2009 CVPR 2009 IEEE Conference on,2009:2687-94.
[9]Liu X L,Peng X,He D,et al.Automatic 3D Imaging and Modelling System with Color Information for Cultural Heritage Digitization[C].Fringe 2013:Springer Berlin Heidelberg,2014:821-6.
[10]Karaszewski M,Sitnik R,Bunsck E.On-line,collisionfree positioning of a scanner during fully automated threedimensional measurement of cultural heritage objects[J].Robotics and Autonomous Systems,2012,60(9):1205-19.
[11]翁金平,程悠胜,崔海华,杨柳,范敬利.面向三维测量的空间标志点高稳定实时匹配方法[J].激光与光电子学进展,2016,(02):021201-8.Weng J P,Cheng X S,Cui H H,Yang L,Fan J G.robust matching algorithm for real-time 3D measurement based on spatial marked points[J].Laser&Optoelectronics progress,2016,(02):021201-8.(in Chinese)
[12]张红颖,于之靖.一种基于标志点匹配的散斑图形变形初值估计法[J].光学学报,2017,37(03):0303001.Zhang H Y,YU Z J.An initial displacement estimation method for speckle image based on marker matching[J].Acta optica sinica,2017,37(03):0303001.(in Chinese)
[13]刘凤英,王冬,陈天恩,于留传.三维相机检校场标志点图像坐标提取方法[J].测绘工程,2015,24(7):48-52.Liu F Y,Wang D,Chen T E,Yu L z.A method of image coordinates extraction for mark points in 3D camera calibration network[J].Engineering of surveying and mapping,2015,24(7):48-52.(in Chinese)
[14]杨帆,权巍,白宝兴,薛耀红.基于标志点的三维点云自动拼接技术[J].计算机工程与设计,2014,35(9):3321-5.Yang F,Quan W,Bai B X,Xue Y h.automatically stitching 3D point-cloud based on marked point[J].computer engineering and design,2014,35(9):3321-5.(in Chinese)
[15]袁建英,王琼,李柏林.利用标志点多视图约束实现结构光扫描高精度粗拼接[J].计算机辅助设计与图形学学报,2015,27(4):674-83.Yuan J Y,Wang Q,Li B.Using multi-view network constraints among reference marker points to realize coarse registration in structured light system with high accuracy[J].Journal of computer-aided design&computer graphics,2015,27(4):674-83.(in Chinese)
[16]Zhang Z Y.A Flexible New Technique for Camera Calibration[J].IEEE Trans Pattern Anal Mach Intel,l 2000,22(11):1330-4.
[2]何懂.相位辅助三维成像相关技术研究[D].深圳:深圳大学;2014.He D.Reseach on relevant technologies of Phaseaided three dimentional imaging[D].Shenzhen:Shenzhen university;2014.(in Chinese)
[3]Goldlcke B,Aubry M,Kolev K,Cremers D.A SuperResolution Framework for High-Accuracy Multiview Reconstruction[J].Int J Comput Vision 2014,106(2):172-91.
[4]Liu X M,Peng X,Yin Y K,Liu X L,Wu W.Generation of photorealistic 3D image using optical digitizer[J].Applied Optics,2012,51(9):1304-11.
[5]Ou P,Li B W,Wang Y J,Zhang S.Flexible real-time natural2D color and 3D shape measurement[J].Optics Express,2013,21(14):16736-41.
[6]殷永凯.相位辅助光学三维测量系统的标定[D].深圳:深圳大学;2012.Yin Y K.The calibration of Phase-aided optical threedimensional system[D].Shenzhen:Shenzhen University;2012(in Chinese)
[7]Li A M,Peng X,Yin Y K,Liu X L.Optical 3D digitizer for photorealistic imaging of movable cultural heritage[J].acta photonica sinica,2013,42(12):1421-9.
[8]Vrubel A,Bellon O R P,Silva L.A 3D reconstruction pipeline for digital preservation[C].Computer Vision and Pattern Recognition,2009 CVPR 2009 IEEE Conference on,2009:2687-94.
[9]Liu X L,Peng X,He D,et al.Automatic 3D Imaging and Modelling System with Color Information for Cultural Heritage Digitization[C].Fringe 2013:Springer Berlin Heidelberg,2014:821-6.
[10]Karaszewski M,Sitnik R,Bunsck E.On-line,collisionfree positioning of a scanner during fully automated threedimensional measurement of cultural heritage objects[J].Robotics and Autonomous Systems,2012,60(9):1205-19.
[11]翁金平,程悠胜,崔海华,杨柳,范敬利.面向三维测量的空间标志点高稳定实时匹配方法[J].激光与光电子学进展,2016,(02):021201-8.Weng J P,Cheng X S,Cui H H,Yang L,Fan J G.robust matching algorithm for real-time 3D measurement based on spatial marked points[J].Laser&Optoelectronics progress,2016,(02):021201-8.(in Chinese)
[12]张红颖,于之靖.一种基于标志点匹配的散斑图形变形初值估计法[J].光学学报,2017,37(03):0303001.Zhang H Y,YU Z J.An initial displacement estimation method for speckle image based on marker matching[J].Acta optica sinica,2017,37(03):0303001.(in Chinese)
[13]刘凤英,王冬,陈天恩,于留传.三维相机检校场标志点图像坐标提取方法[J].测绘工程,2015,24(7):48-52.Liu F Y,Wang D,Chen T E,Yu L z.A method of image coordinates extraction for mark points in 3D camera calibration network[J].Engineering of surveying and mapping,2015,24(7):48-52.(in Chinese)
[14]杨帆,权巍,白宝兴,薛耀红.基于标志点的三维点云自动拼接技术[J].计算机工程与设计,2014,35(9):3321-5.Yang F,Quan W,Bai B X,Xue Y h.automatically stitching 3D point-cloud based on marked point[J].computer engineering and design,2014,35(9):3321-5.(in Chinese)
[15]袁建英,王琼,李柏林.利用标志点多视图约束实现结构光扫描高精度粗拼接[J].计算机辅助设计与图形学学报,2015,27(4):674-83.Yuan J Y,Wang Q,Li B.Using multi-view network constraints among reference marker points to realize coarse registration in structured light system with high accuracy[J].Journal of computer-aided design&computer graphics,2015,27(4):674-83.(in Chinese)
[16]Zhang Z Y.A Flexible New Technique for Camera Calibration[J].IEEE Trans Pattern Anal Mach Intel,l 2000,22(11):1330-4.