基于局部轮廓形状特征的复杂管路结构识别方法
|
摘要
针对管路结构难识别的问题,提出一种基于局部轮廓形状特征的复杂管路结构识别方法,该方法获取管路各结构的轮廓形状,利用形状描述子将各轮廓转换为信号数据,在采集大量信号数据样本的基础上,训练反向传播神经网络,以识别管路结构。训练试验结果表明,所提方法实现了管路结构的自动识别与分割,其准确率达到97%。在实际应用中,采用多相机同时识别,并投票决策的方式提高了识别准确率,实现了分支管路的自动重建与测量。
To solve the problem of automatic tube structure recognition,a recognition method for complex tube structures based on local shape feature was proposed.The recognition method first obtained the different tube structures'shape.Then the obtained shape was converted to a signal by shape descriptor.Batches of signal samples was collected and applied to train a BP neural network to classify the different tube structures.The training experiments showed that the recognition method had accuracy in 97%.In a certain application,multi-cameras were applied to recognize the tube structures and a voting method was also applied to increase the accuracy,which could be applied to reconstruct and measure multi-branch tubes automatically.
To solve the problem of automatic tube structure recognition,a recognition method for complex tube structures based on local shape feature was proposed.The recognition method first obtained the different tube structures'shape.Then the obtained shape was converted to a signal by shape descriptor.Batches of signal samples was collected and applied to train a BP neural network to classify the different tube structures.The training experiments showed that the recognition method had accuracy in 97%.In a certain application,multi-cameras were applied to recognize the tube structures and a voting method was also applied to increase the accuracy,which could be applied to reconstruct and measure multi-branch tubes automatically.
引文
[1]LIU Q,WANG C.Pipe-assembly approach for aero-engines by modified particle swarm optimization[J].Assembly Automation,2010,30(4):365-77.
[2]HE Y,HENG L,ZHANG Z,et al.Advances and trends on tube bending forming technologies[J].Chinese Journal of Aeronautics,2012,25(1):1-12.
[3]JIN P,LIU J,LIU S,et al.A new multi-vision-based reconstruction algorithm for tube inspection[J].The International Journal of Advanced Manufacturing Technology,2017,93(5/6/7/8):2021-2035.
[4]LUHMANN T.Close range photogrammetry for industrial applications[J].ISPRS Journal of Photogrammetry and Remote Sensing,2010,65(6):558-569.
[5]TANGELDER J W H,ERMES P,VOSSELMAN G,et al.CAD-based photogrammetry for reverse engineering of industrial installations[J].Computer-Aided Civil and Infrastructure Engineering,2003,18(4):264-274.
[6]ERMES P.Constraints in CAD models for reverse engineering using photogrammetry[J].International Archives of Photogrammetry and Remote Sensing,2000,33:215-221.
[7]VOSSELMANG,TANGELDERJ W H.3Dreconstruction of industrial installations by constrained fitting of CAD models to images[M]//Mustererkennung 2000.Berlin,Germany:Springer-Verlag,2000:285-292.
[8]JONES M A,CHAPMAN D P,HAMID A A,et al.Close range photogrammetry using geometric primitives for efficient CAD modelling of industrial plant[J].International Archives of Photogrammetry and Remote Sensing,1996,31:284-289.
[9]NAVAB N.Canonical representation and three view geometry of cylinders[J].International Archives Of Photogrammetry Remote Sensing And Spatial Information Sciences,2002,34:218-224.
[10]NAVABN,APPEL M.Canonical representation and multiview geometry of cylinders[J].International Journal of Computer Vision,2006,70(2):133-149.
[11]WU Jigang,BIN Hongzan.Dimensional inspecting system of thin sheet parts based on machine vision[J].Optics and Precision Engineering,2007,15(1):123-130(in Chinese).[伍济钢,宾鸿赞.机器视觉的薄片零件尺寸检测系统[J].光学精密工程,2007,15(1):124-130.]
[12]BAO Lijun,PU Zhaobang,TANG Wenyan.Aviation springwire socket measurement system based on computer vision[J].Semiconductor Optoelectronics,2006,27(3):333-336(in Chinese).[包立君,浦昭邦,唐文彦.航空接插件线簧孔视觉检测系统的研制[J].半导体光电,2006,27(3):333-336.]
[13]LEI L.A machine vision system for inspecting bearing-diameter[C]//Proceedings of the 5th World Congress on Intelligent Control and Automation.Washington,D.C.,USA:IEEE,2004:3904-3906.
[14]YANG Hui,YANG Huicheng.Parts shape recognition based on improved harris corner detection algorithm[J].Journal of Chongqing Institute of Technology:Natural Sciences,2013,27(12):64-67(in Chinese).[杨惠,杨会成.改进Harris角点检测算法的零件形状识别[J].重庆理工大学学报:自然科学版,2013,27(12):64-67.]
[15]WAN Xin,WAN Wen.Thread parameter detection based on machine vision[J].Journal of Nanchang Hangkong University:Natural Sciences,2016,30(3):97-102(in Chinese).[万鑫,万文.基于机器视觉的螺纹参数检测系统设计[J].南昌航空大学学报:自然科学版,2016,30(3):97-102.]
[16]ZHANG Xiaojie,DUAN Jun.Application of improved hough transforming in parts center positioning[J].Machinery&E-lectronics,2016,34(10):62-64(in Chinese).[张小洁,段峻.改进的Hough变换在零件圆心定位中的应用[J].机械与电子,2016,34(10):62-64.]
[17]RABBANI T,VAN DEN HEUVEL F A.Efficient hough transform for automatic detection of cylinders in point clouds[EB/OL].[2018-10-26].https://www.isprs.org/proceedings/xxxvi/3-w19/papers/060.pdf.
[18]MARSHALL D,LUKACS G,MARTIN R.Robust segmentation of primitives from range data in the presence of geometric degeneracy[J].IEEE Transactions on pattern analysis and machine intelligence,2001,23(3):304-314.
[19]SARTI A,TUBARO S.Detection and characterisation of planar fractures using a 3D Hough transform[J].Signal Processing,2002,82(9):1269-1282.
[20]LIU Y J,ZHANG J B,HOU J C,et al.Cylinder detection in large-scale point cloud of pipeline plant[J].IEEE Transactions on Visualization and Computer Graphics,2013,19(10):1700-1707.
[21]TRAN T T,CAO V T,LAURENDEAU D.Extraction of cylinders and estimation of their parameters from point clouds[J].Computers&Graphics,2015,46(C):345-357.
[22]BAUER U,POLTHIER K.Parametric reconstruction of bent tube surfaces[C]//Proceedings of the International Conference on Cyberworlds.Washingtong,D.C.,USA:IEEE,2007:465-474.
[23]BAUER U,POLTHIER K.Generating parametric models of tubes from laser scans[J].Computer-Aided Design,2009,41(10):719-729.
[24]ZHANG Tian,LIU Shaoli,TANG Chengtong,et al.Measurement and 3Dreconstruction method for pipeline's joints based on shape feature[J].Computer Integrated Manufacturing Systems,2015,21(1):123-134(in Chinese).[张天,刘少丽,唐承统,等.基于形状特征的管路接头测量和三维重建方法[J].计算机集成制造系统,2015,21(1):123-134.]
[25]YANG M,KPALMA K,RONSIN J.Asurvey of shape feature extraction techniques[EB/OL].[2018-10-27].https://cdn.intechopen.com/pdfs/5781.pdf.
[26]HAYKIN S S.Neural networks and learning machines[M].Upper Saddle River,N.J.,USA:Pearson,2009.
[2]HE Y,HENG L,ZHANG Z,et al.Advances and trends on tube bending forming technologies[J].Chinese Journal of Aeronautics,2012,25(1):1-12.
[3]JIN P,LIU J,LIU S,et al.A new multi-vision-based reconstruction algorithm for tube inspection[J].The International Journal of Advanced Manufacturing Technology,2017,93(5/6/7/8):2021-2035.
[4]LUHMANN T.Close range photogrammetry for industrial applications[J].ISPRS Journal of Photogrammetry and Remote Sensing,2010,65(6):558-569.
[5]TANGELDER J W H,ERMES P,VOSSELMAN G,et al.CAD-based photogrammetry for reverse engineering of industrial installations[J].Computer-Aided Civil and Infrastructure Engineering,2003,18(4):264-274.
[6]ERMES P.Constraints in CAD models for reverse engineering using photogrammetry[J].International Archives of Photogrammetry and Remote Sensing,2000,33:215-221.
[7]VOSSELMANG,TANGELDERJ W H.3Dreconstruction of industrial installations by constrained fitting of CAD models to images[M]//Mustererkennung 2000.Berlin,Germany:Springer-Verlag,2000:285-292.
[8]JONES M A,CHAPMAN D P,HAMID A A,et al.Close range photogrammetry using geometric primitives for efficient CAD modelling of industrial plant[J].International Archives of Photogrammetry and Remote Sensing,1996,31:284-289.
[9]NAVAB N.Canonical representation and three view geometry of cylinders[J].International Archives Of Photogrammetry Remote Sensing And Spatial Information Sciences,2002,34:218-224.
[10]NAVABN,APPEL M.Canonical representation and multiview geometry of cylinders[J].International Journal of Computer Vision,2006,70(2):133-149.
[11]WU Jigang,BIN Hongzan.Dimensional inspecting system of thin sheet parts based on machine vision[J].Optics and Precision Engineering,2007,15(1):123-130(in Chinese).[伍济钢,宾鸿赞.机器视觉的薄片零件尺寸检测系统[J].光学精密工程,2007,15(1):124-130.]
[12]BAO Lijun,PU Zhaobang,TANG Wenyan.Aviation springwire socket measurement system based on computer vision[J].Semiconductor Optoelectronics,2006,27(3):333-336(in Chinese).[包立君,浦昭邦,唐文彦.航空接插件线簧孔视觉检测系统的研制[J].半导体光电,2006,27(3):333-336.]
[13]LEI L.A machine vision system for inspecting bearing-diameter[C]//Proceedings of the 5th World Congress on Intelligent Control and Automation.Washington,D.C.,USA:IEEE,2004:3904-3906.
[14]YANG Hui,YANG Huicheng.Parts shape recognition based on improved harris corner detection algorithm[J].Journal of Chongqing Institute of Technology:Natural Sciences,2013,27(12):64-67(in Chinese).[杨惠,杨会成.改进Harris角点检测算法的零件形状识别[J].重庆理工大学学报:自然科学版,2013,27(12):64-67.]
[15]WAN Xin,WAN Wen.Thread parameter detection based on machine vision[J].Journal of Nanchang Hangkong University:Natural Sciences,2016,30(3):97-102(in Chinese).[万鑫,万文.基于机器视觉的螺纹参数检测系统设计[J].南昌航空大学学报:自然科学版,2016,30(3):97-102.]
[16]ZHANG Xiaojie,DUAN Jun.Application of improved hough transforming in parts center positioning[J].Machinery&E-lectronics,2016,34(10):62-64(in Chinese).[张小洁,段峻.改进的Hough变换在零件圆心定位中的应用[J].机械与电子,2016,34(10):62-64.]
[17]RABBANI T,VAN DEN HEUVEL F A.Efficient hough transform for automatic detection of cylinders in point clouds[EB/OL].[2018-10-26].https://www.isprs.org/proceedings/xxxvi/3-w19/papers/060.pdf.
[18]MARSHALL D,LUKACS G,MARTIN R.Robust segmentation of primitives from range data in the presence of geometric degeneracy[J].IEEE Transactions on pattern analysis and machine intelligence,2001,23(3):304-314.
[19]SARTI A,TUBARO S.Detection and characterisation of planar fractures using a 3D Hough transform[J].Signal Processing,2002,82(9):1269-1282.
[20]LIU Y J,ZHANG J B,HOU J C,et al.Cylinder detection in large-scale point cloud of pipeline plant[J].IEEE Transactions on Visualization and Computer Graphics,2013,19(10):1700-1707.
[21]TRAN T T,CAO V T,LAURENDEAU D.Extraction of cylinders and estimation of their parameters from point clouds[J].Computers&Graphics,2015,46(C):345-357.
[22]BAUER U,POLTHIER K.Parametric reconstruction of bent tube surfaces[C]//Proceedings of the International Conference on Cyberworlds.Washingtong,D.C.,USA:IEEE,2007:465-474.
[23]BAUER U,POLTHIER K.Generating parametric models of tubes from laser scans[J].Computer-Aided Design,2009,41(10):719-729.
[24]ZHANG Tian,LIU Shaoli,TANG Chengtong,et al.Measurement and 3Dreconstruction method for pipeline's joints based on shape feature[J].Computer Integrated Manufacturing Systems,2015,21(1):123-134(in Chinese).[张天,刘少丽,唐承统,等.基于形状特征的管路接头测量和三维重建方法[J].计算机集成制造系统,2015,21(1):123-134.]
[25]YANG M,KPALMA K,RONSIN J.Asurvey of shape feature extraction techniques[EB/OL].[2018-10-27].https://cdn.intechopen.com/pdfs/5781.pdf.
[26]HAYKIN S S.Neural networks and learning machines[M].Upper Saddle River,N.J.,USA:Pearson,2009.