基于单视图三维重建的凹凸制造特征识别
|
摘要
为实现凹凸制造特征机器人的自动识别,文中提出了一种不依赖于CAD设计模型的自动特征识别新方法。该方法以零件的单幅图像为识别线索,首先采用改进的SFS算法对零件表面进行三维曲面重建;然后对重建模型表面的形状指数进行分析以计算特征分割线,利用特征线将曲面进行分割以获得相应的特征区域;最后基于特征识别规则实现对零件凹凸制造特征的有效识别。该方法能够在缺少CAD模型时有效地实现制造特征的自动识别,从而为来料加工以及二次装配过程中机器人的自动特征识别提供重要的方法。通过实例零件验证了该方法的有效性和准确性。
This paper proposed a new method of automatic feature recognition without relying on the CAD design model to achieve robot automatic recognition for concave-convex manufacturing features.The method takes the single image of the part as the identification clue.Firstly,the surface of the part is reconstructed by using the improved method of shape from shading.Then,the features segmentation lines which are used to segment the surface are calculated by analyzing the surface shape indexes of the reconstructed model.The surface is segmented by feature lines to obtain the corresponding classification region.Finally,based on the feature recognition rules,the feature of concave and convex manufacturing is identified effectively.This algorithm can effectively solve the problem of automatic identification of manufacturing features in the absence of CAD model,providing important method for the automatic feature recognition of the robot in the processing of incoming materials and two assembly.The validity and accuracy of the proposed method were verified by an example.
This paper proposed a new method of automatic feature recognition without relying on the CAD design model to achieve robot automatic recognition for concave-convex manufacturing features.The method takes the single image of the part as the identification clue.Firstly,the surface of the part is reconstructed by using the improved method of shape from shading.Then,the features segmentation lines which are used to segment the surface are calculated by analyzing the surface shape indexes of the reconstructed model.The surface is segmented by feature lines to obtain the corresponding classification region.Finally,based on the feature recognition rules,the feature of concave and convex manufacturing is identified effectively.This algorithm can effectively solve the problem of automatic identification of manufacturing features in the absence of CAD model,providing important method for the automatic feature recognition of the robot in the processing of incoming materials and two assembly.The validity and accuracy of the proposed method were verified by an example.
引文
[1] OUSSAMA J,ABDELILAH E,AHMED R.Manufacturing Computer Aided Process Planning for Rotational Parts.Part 1:Automatic Feature Recognition from STEP AP203 Ed2[J].International Journal of Engineering Research & Applications,2014,4(5):2248-9622.
[2] CHENG B,REN Z.Interacting Feature Recognition Based on AAG Expansion and Hint[J].Journal of Graphics,2017,38(4):469-475.
[3] LI Y,DING Y,MOU W.Feature recognition technology for aircraft structural parts based on a holistic attribute adjacency graph[J].Journal of Engineering Manufacture,2010,224(2):271-278.
[4] GUO Y,SOHEL F A,BENNAMOUN M,et al.Integrating shape and color cues for textured 3D object recognition[C]//2013 8th Conference on Industrial Electronics and Applications.IEEE,2013:1614-1619.
[5] DWIJAYANTI K,AOYAMA H.Basic study on process planning for Turning-Milling Center based on machining feature re-cognition[J].Journal of Advanced Mechanical Design Systems &Manufacturing,2014,8(4):95-108.
[6] LIU J F,LIU X J,CHENG Y L,et al.An algorithm of mapping the protrusion feature on the slanting face to its manufacturing feature volume in the process planning[J].International Journal of Advanced Manufacturing Technology,2015,79(1-4):361-376.
[7] KUSS A,DIETZ T,KSENSOW K,et al.Manufacturing Task Description for Robotic Welding and Automatic Feature Recognition on Product CAD Models [J].Procedia Cirp,2017,60:122-127.
[8] HUANG R,ZHANG S S,BAI X L.Manufacturability driven interacting machining feature recognition algorithms for 3D CAD models[J].Journal of Computer-Aided Design & Computer Graphics,2013,25(7):1089-1098.(in Chinese)黄瑞,张树生,白晓亮.可制造性驱动的三维CAD模型相交制造特征识别方法[J].计算机辅助设计与图形学学报,2013,25(7):1089-1098.
[9] LIU X M,ZHONG Y,HUANG J F,et al.Machining feature recognition method for complicated boxy parts based on manufacturing resources[J].Computer Integrated Manufacturing Systems,2015,21(12):3166-3173.(in Chinese)刘雪梅,周易,黄剑锋,等.基于制造资源的复杂箱体零件加工特征识别方法[J].计算机集成制造系统,2015,21(12):3166-3173.
[10] SRIDHARAN N,SHAH J J.Recognition of Multi-Axis Milling Features:Part II-Algorithms & Implementation [J].Journal of Computing and Information Science in Engineering,2005,5(1):25-34.
[11] ZHANG F J,MA J,GAO S M.Hybrid Recognition of Machining Feature [J].Journal of Computer-Aided Design & Computer Graphics,2002,14(3):228-232.(in Chinese)张凤军,马骥,高曙明.混合加工特征识别方法[J].计算机辅助设计与图形学学报,2002,14(3):228-232.
[12] LI L Z.Research on 3D Reconstruction Based Robotic Identification and Assembly Methods [D].Guangzhou:South China University of Technology,2016.(in Chinese)李良知.基于三维重建的机器人识别与装配方法硏究[D].广州:华南理工大学,2016.
[13] HORN B K P.Height and gradient from shading [J].Interna- tional Journal of Computer Vision,1990,5(1):37-75.
[14] WANG G,CHENG J.Three-dimensional reconstruction of hybrid surfaces using perspective shape from shading[J].Optik-International Journal for Light and Electron Optics,2016,127(19):7740-7751.
[15] BARRON J T,MALIK J.Shape,Illumination,and Reflectance from Shading[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,37(8):1670-1687.
[16] HERBORT S,W?HLER C.An introduction to image-based 3D surface reconstruction and a survey of photometric stereo me-thods[J].3d Research,2011,2(3):1-17.
[17] YING X,AYAN C,RONEN B,et al.From shading to local shape [J].TPAMI,2014,37(1):67-79.
[18] JAN K,ANDREA D,JOHAN W.Local Solid Shape [J].i-Perception,2015,6(5):1-15.
[19] BONDE U,BADRINARAYANAN V,CIPOLLA R.Multi Scale Shape Index for 3D Object Recognition [C]//International Conference on Scale Space and Variational Methods in Computer Vision.Springer Berlin Heidelberg,2013:306-318.
[20] ZHANG C J,ZHOU X H,LI C X.Multiple view conversion platform of CAD model for complex near-net-shape product [J].Computer Integrated Manufacturing Systems,2010,16(5):922-928.(in Chinese)张春捷,周雄辉,李从心.复杂近净成形产品CAD模型多视域转换平台[J].计算机集成制造系统,2010,16(5):922-928.
[21] STEIN S C,WORGOTTER F,SCHOELER M,et al.Convexity based object partitioning for robot applications [C]//Procee-dings of 2014 IEEE International Conference on Robotics and Automation (ICRA).Hong Kong:IEEE,2014.
[2] CHENG B,REN Z.Interacting Feature Recognition Based on AAG Expansion and Hint[J].Journal of Graphics,2017,38(4):469-475.
[3] LI Y,DING Y,MOU W.Feature recognition technology for aircraft structural parts based on a holistic attribute adjacency graph[J].Journal of Engineering Manufacture,2010,224(2):271-278.
[4] GUO Y,SOHEL F A,BENNAMOUN M,et al.Integrating shape and color cues for textured 3D object recognition[C]//2013 8th Conference on Industrial Electronics and Applications.IEEE,2013:1614-1619.
[5] DWIJAYANTI K,AOYAMA H.Basic study on process planning for Turning-Milling Center based on machining feature re-cognition[J].Journal of Advanced Mechanical Design Systems &Manufacturing,2014,8(4):95-108.
[6] LIU J F,LIU X J,CHENG Y L,et al.An algorithm of mapping the protrusion feature on the slanting face to its manufacturing feature volume in the process planning[J].International Journal of Advanced Manufacturing Technology,2015,79(1-4):361-376.
[7] KUSS A,DIETZ T,KSENSOW K,et al.Manufacturing Task Description for Robotic Welding and Automatic Feature Recognition on Product CAD Models [J].Procedia Cirp,2017,60:122-127.
[8] HUANG R,ZHANG S S,BAI X L.Manufacturability driven interacting machining feature recognition algorithms for 3D CAD models[J].Journal of Computer-Aided Design & Computer Graphics,2013,25(7):1089-1098.(in Chinese)黄瑞,张树生,白晓亮.可制造性驱动的三维CAD模型相交制造特征识别方法[J].计算机辅助设计与图形学学报,2013,25(7):1089-1098.
[9] LIU X M,ZHONG Y,HUANG J F,et al.Machining feature recognition method for complicated boxy parts based on manufacturing resources[J].Computer Integrated Manufacturing Systems,2015,21(12):3166-3173.(in Chinese)刘雪梅,周易,黄剑锋,等.基于制造资源的复杂箱体零件加工特征识别方法[J].计算机集成制造系统,2015,21(12):3166-3173.
[10] SRIDHARAN N,SHAH J J.Recognition of Multi-Axis Milling Features:Part II-Algorithms & Implementation [J].Journal of Computing and Information Science in Engineering,2005,5(1):25-34.
[11] ZHANG F J,MA J,GAO S M.Hybrid Recognition of Machining Feature [J].Journal of Computer-Aided Design & Computer Graphics,2002,14(3):228-232.(in Chinese)张凤军,马骥,高曙明.混合加工特征识别方法[J].计算机辅助设计与图形学学报,2002,14(3):228-232.
[12] LI L Z.Research on 3D Reconstruction Based Robotic Identification and Assembly Methods [D].Guangzhou:South China University of Technology,2016.(in Chinese)李良知.基于三维重建的机器人识别与装配方法硏究[D].广州:华南理工大学,2016.
[13] HORN B K P.Height and gradient from shading [J].Interna- tional Journal of Computer Vision,1990,5(1):37-75.
[14] WANG G,CHENG J.Three-dimensional reconstruction of hybrid surfaces using perspective shape from shading[J].Optik-International Journal for Light and Electron Optics,2016,127(19):7740-7751.
[15] BARRON J T,MALIK J.Shape,Illumination,and Reflectance from Shading[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,37(8):1670-1687.
[16] HERBORT S,W?HLER C.An introduction to image-based 3D surface reconstruction and a survey of photometric stereo me-thods[J].3d Research,2011,2(3):1-17.
[17] YING X,AYAN C,RONEN B,et al.From shading to local shape [J].TPAMI,2014,37(1):67-79.
[18] JAN K,ANDREA D,JOHAN W.Local Solid Shape [J].i-Perception,2015,6(5):1-15.
[19] BONDE U,BADRINARAYANAN V,CIPOLLA R.Multi Scale Shape Index for 3D Object Recognition [C]//International Conference on Scale Space and Variational Methods in Computer Vision.Springer Berlin Heidelberg,2013:306-318.
[20] ZHANG C J,ZHOU X H,LI C X.Multiple view conversion platform of CAD model for complex near-net-shape product [J].Computer Integrated Manufacturing Systems,2010,16(5):922-928.(in Chinese)张春捷,周雄辉,李从心.复杂近净成形产品CAD模型多视域转换平台[J].计算机集成制造系统,2010,16(5):922-928.
[21] STEIN S C,WORGOTTER F,SCHOELER M,et al.Convexity based object partitioning for robot applications [C]//Procee-dings of 2014 IEEE International Conference on Robotics and Automation (ICRA).Hong Kong:IEEE,2014.