基于图像序列的输液可见异物检测系统研究
|
摘要
医用输液是一种在临床应用广泛的重要的制剂之一,溶液异物的检测直接关系着患者的生命安全。因此,输液可见异物在线高效自动检测成为现代企业实现规模化生产的迫切需求。本文基于图像序列的输液可见异物检测系统以输液中所含的可见异物为研究对象,展开了输液可见异物的在线检测,对整个系统的构架与开发作了详细的设计和阐述,并重点研究了其中所涉及的视觉检测技术,包括Mean shift算法在其中的应用。
首先,论述了机器视觉在工业检测过程中的应用,分析了目前存在的多种机器视觉系统,比较了各自的特点。在对机器视觉系统中通用的照明技术、图像获取技术进行了全面的论述和对各种光源的性能指标进行分析比较后,给出了多种实用的照明方式,设计了视觉传动系统、照明系统、剔除模块及电气自动控制系统；在此基础上,构建出了输液可见异物检测系统总体方案及其流程图。
其次,开展了输液成像系统理论及其算法的研究,文中分析了成像系统的标定,运动检测及可见异物识别的处理过程,采用线性模型来进行相机标定。针对输液中被检测微粒的运动不确定性,结合背景模型法和帧间差分法,将归一化的互相关系数作为评价图像差异的依据,通过帧差法获得背景模型,然后将所有帧与所得背景模型相减,即得各帧中的运动目标。为了提高识别精度,本文运用均值平移跟踪器识别出下落的可见异物的改进算法。为了验证算法的实际可行性,在Visual C++和MATLAB平台上验证了该算法的有效性和可行性。
最后,开发出一套输液可见异物智能检测实验软件。
Medical infusion is a wide range of important clinical application. The detection of foreign objects in the solution directly related to patients'safety. Therefore the efficient automated detection of foreign objects online can be seen as the urgent need of large-scale production for a modern enterprise. The research object of the detection system based on image sequence in infusion are the visible foreign objects contained in the infusion,which can implements smart visible foreign objects inspection online. In this paper, the entire system structure was designed and described.In the structure, the technology and the software implementation are mainly researched, including the applications of the Mean shift algorithm
Firstly, the application of machine vision in industry inspection is represented and the type of machine vision system is analyzed, whose characteristics are compared. A variety of practical ways in the lighting before lighting technology and image acquisition technology are a comprehensive discussion in machine vision system. The visual transmission system, lighting system, remove module and electrical automatic control system are designed. This paper shows the overall design program of foreign objects detection system in infusion.
Secondly, the infusion imaging system theory and its algorithm are researched. The camera calibration, motion inspection and the identity of foreign objects are discussed, and a linear model for camera calibration is used.
As for the movement of particles uncertainty, we combined with background model method and the inter-frame difference method
For the small foreign objects motion detection, A normalized cross correlation is used to obtain the frame, based on that the background is estimated from the first frame by inter-frame difference, and small moving objects are extracted from each frame. And the normalized cross-correlation coefficient based on the difference images is as an evaluation to obtain the background model by the frame difference method. Then all the frames and the background model derived from subtract to have the frame of the moving target In order to improve identification accuracy, an adapted mean shift tracker is adopted to find falling foreign objects. In order to verify the practical feasibility of the algorithm, we have verified the effectiveness and feasibility of the algorithm. in Visual C++and MATLAB platform
Finally, the software for inspection of foreign objects in transfusion bottles was developed
首先,论述了机器视觉在工业检测过程中的应用,分析了目前存在的多种机器视觉系统,比较了各自的特点。在对机器视觉系统中通用的照明技术、图像获取技术进行了全面的论述和对各种光源的性能指标进行分析比较后,给出了多种实用的照明方式,设计了视觉传动系统、照明系统、剔除模块及电气自动控制系统；在此基础上,构建出了输液可见异物检测系统总体方案及其流程图。
其次,开展了输液成像系统理论及其算法的研究,文中分析了成像系统的标定,运动检测及可见异物识别的处理过程,采用线性模型来进行相机标定。针对输液中被检测微粒的运动不确定性,结合背景模型法和帧间差分法,将归一化的互相关系数作为评价图像差异的依据,通过帧差法获得背景模型,然后将所有帧与所得背景模型相减,即得各帧中的运动目标。为了提高识别精度,本文运用均值平移跟踪器识别出下落的可见异物的改进算法。为了验证算法的实际可行性,在Visual C++和MATLAB平台上验证了该算法的有效性和可行性。
最后,开发出一套输液可见异物智能检测实验软件。
Medical infusion is a wide range of important clinical application. The detection of foreign objects in the solution directly related to patients'safety. Therefore the efficient automated detection of foreign objects online can be seen as the urgent need of large-scale production for a modern enterprise. The research object of the detection system based on image sequence in infusion are the visible foreign objects contained in the infusion,which can implements smart visible foreign objects inspection online. In this paper, the entire system structure was designed and described.In the structure, the technology and the software implementation are mainly researched, including the applications of the Mean shift algorithm
Firstly, the application of machine vision in industry inspection is represented and the type of machine vision system is analyzed, whose characteristics are compared. A variety of practical ways in the lighting before lighting technology and image acquisition technology are a comprehensive discussion in machine vision system. The visual transmission system, lighting system, remove module and electrical automatic control system are designed. This paper shows the overall design program of foreign objects detection system in infusion.
Secondly, the infusion imaging system theory and its algorithm are researched. The camera calibration, motion inspection and the identity of foreign objects are discussed, and a linear model for camera calibration is used.
As for the movement of particles uncertainty, we combined with background model method and the inter-frame difference method
For the small foreign objects motion detection, A normalized cross correlation is used to obtain the frame, based on that the background is estimated from the first frame by inter-frame difference, and small moving objects are extracted from each frame. And the normalized cross-correlation coefficient based on the difference images is as an evaluation to obtain the background model by the frame difference method. Then all the frames and the background model derived from subtract to have the frame of the moving target In order to improve identification accuracy, an adapted mean shift tracker is adopted to find falling foreign objects. In order to verify the practical feasibility of the algorithm, we have verified the effectiveness and feasibility of the algorithm. in Visual C++and MATLAB platform
Finally, the software for inspection of foreign objects in transfusion bottles was developed
引文
[1]大输液行业发展现状及趋势202.197.107.22:85/web/docview.aspx?chnid=25& leafid=70&docid= 1193002
[2]国家药典委员会.中华人民共和国药典,二部[Z].北京：化学工业出版社,2005附录6-7.
[3]徐安平,徐淼,刘小平.58例输液反应原因分析.中华医院感染学杂志,2006,16(4)：396-397
[4]C. Vaz, P. Carvalho, E. Duarte,et al. A vision-based system for automatic ring detection and measurement [J]. Computers & Industrial Engineering,2004,46(2):347—354.
[5]Automatic Inspection Machine.www.eisai-mc.co.jp/english/machines/aim_1.html
[6]H. Grindinger, H. Neusser,N. Seidenader, and V. Wedershoven,. Product testing apparatus. U.S. Patent 0,117,149,2005-07-02
[7]H.Yamazaki, T. Katane, H. Fukuda,K. Asano,and M.Matsushima, Inspection device and system for inspecting foreign matters in a liquid filled transparent container. U.S Patent 6,937,339,2005-08-30.
[8]段峰,王耀南,雷晓峰,等.机器视觉技术及其应用综述[J].自动化博览,2002(3)：59-62.
[9]李福建,张元培.机器视觉系统组成研究,自动化博览.2004,(02)
[10]刘焕军.机器视觉中的图像采集技术[J]电脑与信息技术.2003,(1)
[11]方建军,刘仕良,张虎.基于机器视觉的板栗实时分级系统.轻工机械.2004,(03)
[12]阳佳,吴久峰,邓志刚.基于机器视觉工业实时测量技术研究.制造业自动化,2003,02
[13]张磊,罗翔,史金飞.机器视觉实时问题的对策与研究方法综述.制造业自动化.2006.28(06)：28-32.78
[14]姚峰林,詹海英,李元宗.机器视觉中的边缘检测技术研究,机械工程与自动化.2005.(01)：108-110
[15]黄文清,汪亚明,周志宇.计算机视觉技术在工业领域中的应用.浙江工程学院学报,2002,19(2)：92-96.
[16]段峰,王耀南,雷晓峰,等.机器视觉技术及其应用综述[J].自动化博览,2002(3)：59262.
[17]A.Ishii,T.Mizuta,and S.Todo.Detection of Foreign substances mixed in aplastic bottle of medicinal solution using real-time video image processing.In Fourteenth International Conference on Pattern Recognition.1998,1646-1650
[18]S.Boverie.A new class of intelligent sensors for the inner space monitoring the vehicle of the future, Control Engineering Practice,2002,10:1169-1178
[19]程开富.CMOS图像传感器及应用[M].半导体光电,2000(3):Vol.21 Supplemen.
[20]刘禾.数字图像处理及应用.中国电力出版社2006
[21]朗锐,数字图像处理学[M],北京：北京希望电子出版社,2002,46-168
[22]阮秋琦.数字图像处理学.北京：电子工业出版社.2001
[23]罗希平等,图像分割方法综述,模式识别与人工智能,1999,12(3)：301-312
[24]高茹.数字图像混合噪声的滤除方法研究[D].吉林大学,2007.
[25][美]桑肯S(okna, M.)等.图像处理、分析与机器视觉(第二版)[M],北京：人民邮电出版社2002
[26]崔屹.图象处理与分析——数学形态学方法及应用[M],北京：科学出版社,2001,1-26
[27]刘直芳,王运琼,朱敏.数字图像处理与分析[M].北京：清华大学出版社,2006.
[28]Rafael C.Gonzalez,Richard E.Woods.Digital Image Processing(second Edition).Pubulishing House of Electronics.Industry,2002,2.
[29]献毓晋.图像处理与分析[M],北京：清华大学出版社,2003,35-130
[30]杨敬安.基于照明参数与反射系数的分层SFS算法[J].自动化学报,1999,25(6)：7352742.
[31]杨敬安基于照明参数与反射系数的分层SFS算法[J],自动化学报,1999.11,Vol.25,No.6:735～742
[32]献毓晋.图像理解与计算机视觉[M],北京：清华大学出版社,2003,81—140
[33]MALREY Lee.3D ShaPe Reconsturetion of hybrid reflectance using the LMS algorithm [J].International Journal of Pattern Recongition & Artificial Intelligence,2001,15(4):723 —734
[34]Zhang R,Tsai P S,Cryer J,et al.Shape from Shading:A Survey[J].IEEE Transactions on PAMI,1999,21(8):690-706.
[35]Ragheb H,Hancock E RlSurface radiance correction for shape from shading[J].Pattern Recognition,2005,38:1574-1595.
[36]Horn B,Brooks M.The Variational Approach to Shape fromShading[J].Computer Vision,Graphics and Image Processing,1986,33(2):174-208.
[37]王旭辉,郭光亚.匀速运动模糊图像的快速恢复.微计算机信息,2000,16(5)：5～7
[38]Lee C H, Rosenfeld A. Improved methods of estimating shape from shading using the light source coordinate system.Artificial Intelligence,1985,262,26(2):125～143.
[39]Zheng Q, Chellapa R. Estimation of illuminant direction,albedo, and shape from shading.IEEE Trans PAMI,1991,137,13(7):680～702.
[40]Pentland A. Shape information from shading:a theory about human perception.Spatial Vision, 1989,43,4(3):165～182.
[41]Y. Zhong, A K Jain, M P Jolly. Object Tracking Using De-formable Templates[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2000,22(5):544-549.
[42]Adrian G Bors, loannis Pitas.Prediction and Tracking of Moving Objects in Image Sequences [J]. IEEE Trans on Image Processing,2000,9(8):1441-1445.
[43]王栓,艾海舟,何克忠.基于差分图像的多运动目标的检测与跟踪[J].中国图像图形学报,1999,4(6)：470-474.
[44郑世友,动态场景图像序列中运动目标检测与跟踪,博士学位论文,东南大学,2005.12
[45]李在铭,视频运动目标检测及其实时处理系统研究,博士学位论文,电子科技大学,2004.07
[46]常发亮,彩色图像分割与复杂场景下视觉目标跟踪方法,博士学位论文,山东大学,2005.10
[47]Halil Ibrahim Cuce. Mean-shift analysis for image and video applications [thesis]:Bilkent University,2005:2-3
[48]Yizong Cheng. Mean shift, mode seeking, and clustering. Pattern Analysis and Machine Intelligence, IEEE Transactions on.1995,17(8):790-799
[49]网冠科技Visual C++6.0 MFC时尚编程百例[M].北京：机械工业出版社,2004.
[50]Timothy.S.Rameteke,施平安.C和C++／基础教程与题解[M].北京：清华大学出版杜,2005.
[51]高成Matlab图像处理与应用[M].北京：国防工业出版社,2007.
[52][美]R C冈萨雷斯.数字图像处理(MATLAB版)[M].北京：电子工业出版社,2005.
[53]罗军辉,冯平,哈力旦A.MATLAB 7.0在图像处理中的应用[M].北京：机械工业出版社,2005.
[54]肖飞,于向军,吕震中,用InTouch、MATLAB和VC++开发工业监控系统软件,微计算机信息,2003第19卷11期：39～41
[55]高成Matlab接口技术与应用[M].北京：国防工业出版社,2007.
[56]杨丽娜.浅析VC++与MATLAB混合编程方法在图像处理中的应用.大众科技,No.2,2006
[57]Matrix VB User's Guide.The Math Works Inc.2000
[58]胡智文,邓铁如等,在VB应用程序中集成MATLAB,计算机工程与应用,2003.7：104～10
[2]国家药典委员会.中华人民共和国药典,二部[Z].北京：化学工业出版社,2005附录6-7.
[3]徐安平,徐淼,刘小平.58例输液反应原因分析.中华医院感染学杂志,2006,16(4)：396-397
[4]C. Vaz, P. Carvalho, E. Duarte,et al. A vision-based system for automatic ring detection and measurement [J]. Computers & Industrial Engineering,2004,46(2):347—354.
[5]Automatic Inspection Machine.www.eisai-mc.co.jp/english/machines/aim_1.html
[6]H. Grindinger, H. Neusser,N. Seidenader, and V. Wedershoven,. Product testing apparatus. U.S. Patent 0,117,149,2005-07-02
[7]H.Yamazaki, T. Katane, H. Fukuda,K. Asano,and M.Matsushima, Inspection device and system for inspecting foreign matters in a liquid filled transparent container. U.S Patent 6,937,339,2005-08-30.
[8]段峰,王耀南,雷晓峰,等.机器视觉技术及其应用综述[J].自动化博览,2002(3)：59-62.
[9]李福建,张元培.机器视觉系统组成研究,自动化博览.2004,(02)
[10]刘焕军.机器视觉中的图像采集技术[J]电脑与信息技术.2003,(1)
[11]方建军,刘仕良,张虎.基于机器视觉的板栗实时分级系统.轻工机械.2004,(03)
[12]阳佳,吴久峰,邓志刚.基于机器视觉工业实时测量技术研究.制造业自动化,2003,02
[13]张磊,罗翔,史金飞.机器视觉实时问题的对策与研究方法综述.制造业自动化.2006.28(06)：28-32.78
[14]姚峰林,詹海英,李元宗.机器视觉中的边缘检测技术研究,机械工程与自动化.2005.(01)：108-110
[15]黄文清,汪亚明,周志宇.计算机视觉技术在工业领域中的应用.浙江工程学院学报,2002,19(2)：92-96.
[16]段峰,王耀南,雷晓峰,等.机器视觉技术及其应用综述[J].自动化博览,2002(3)：59262.
[17]A.Ishii,T.Mizuta,and S.Todo.Detection of Foreign substances mixed in aplastic bottle of medicinal solution using real-time video image processing.In Fourteenth International Conference on Pattern Recognition.1998,1646-1650
[18]S.Boverie.A new class of intelligent sensors for the inner space monitoring the vehicle of the future, Control Engineering Practice,2002,10:1169-1178
[19]程开富.CMOS图像传感器及应用[M].半导体光电,2000(3):Vol.21 Supplemen.
[20]刘禾.数字图像处理及应用.中国电力出版社2006
[21]朗锐,数字图像处理学[M],北京：北京希望电子出版社,2002,46-168
[22]阮秋琦.数字图像处理学.北京：电子工业出版社.2001
[23]罗希平等,图像分割方法综述,模式识别与人工智能,1999,12(3)：301-312
[24]高茹.数字图像混合噪声的滤除方法研究[D].吉林大学,2007.
[25][美]桑肯S(okna, M.)等.图像处理、分析与机器视觉(第二版)[M],北京：人民邮电出版社2002
[26]崔屹.图象处理与分析——数学形态学方法及应用[M],北京：科学出版社,2001,1-26
[27]刘直芳,王运琼,朱敏.数字图像处理与分析[M].北京：清华大学出版社,2006.
[28]Rafael C.Gonzalez,Richard E.Woods.Digital Image Processing(second Edition).Pubulishing House of Electronics.Industry,2002,2.
[29]献毓晋.图像处理与分析[M],北京：清华大学出版社,2003,35-130
[30]杨敬安.基于照明参数与反射系数的分层SFS算法[J].自动化学报,1999,25(6)：7352742.
[31]杨敬安基于照明参数与反射系数的分层SFS算法[J],自动化学报,1999.11,Vol.25,No.6:735～742
[32]献毓晋.图像理解与计算机视觉[M],北京：清华大学出版社,2003,81—140
[33]MALREY Lee.3D ShaPe Reconsturetion of hybrid reflectance using the LMS algorithm [J].International Journal of Pattern Recongition & Artificial Intelligence,2001,15(4):723 —734
[34]Zhang R,Tsai P S,Cryer J,et al.Shape from Shading:A Survey[J].IEEE Transactions on PAMI,1999,21(8):690-706.
[35]Ragheb H,Hancock E RlSurface radiance correction for shape from shading[J].Pattern Recognition,2005,38:1574-1595.
[36]Horn B,Brooks M.The Variational Approach to Shape fromShading[J].Computer Vision,Graphics and Image Processing,1986,33(2):174-208.
[37]王旭辉,郭光亚.匀速运动模糊图像的快速恢复.微计算机信息,2000,16(5)：5～7
[38]Lee C H, Rosenfeld A. Improved methods of estimating shape from shading using the light source coordinate system.Artificial Intelligence,1985,262,26(2):125～143.
[39]Zheng Q, Chellapa R. Estimation of illuminant direction,albedo, and shape from shading.IEEE Trans PAMI,1991,137,13(7):680～702.
[40]Pentland A. Shape information from shading:a theory about human perception.Spatial Vision, 1989,43,4(3):165～182.
[41]Y. Zhong, A K Jain, M P Jolly. Object Tracking Using De-formable Templates[J]. IEEE Trans on Pattern Analysis and Machine Intelligence,2000,22(5):544-549.
[42]Adrian G Bors, loannis Pitas.Prediction and Tracking of Moving Objects in Image Sequences [J]. IEEE Trans on Image Processing,2000,9(8):1441-1445.
[43]王栓,艾海舟,何克忠.基于差分图像的多运动目标的检测与跟踪[J].中国图像图形学报,1999,4(6)：470-474.
[44郑世友,动态场景图像序列中运动目标检测与跟踪,博士学位论文,东南大学,2005.12
[45]李在铭,视频运动目标检测及其实时处理系统研究,博士学位论文,电子科技大学,2004.07
[46]常发亮,彩色图像分割与复杂场景下视觉目标跟踪方法,博士学位论文,山东大学,2005.10
[47]Halil Ibrahim Cuce. Mean-shift analysis for image and video applications [thesis]:Bilkent University,2005:2-3
[48]Yizong Cheng. Mean shift, mode seeking, and clustering. Pattern Analysis and Machine Intelligence, IEEE Transactions on.1995,17(8):790-799
[49]网冠科技Visual C++6.0 MFC时尚编程百例[M].北京：机械工业出版社,2004.
[50]Timothy.S.Rameteke,施平安.C和C++／基础教程与题解[M].北京：清华大学出版杜,2005.
[51]高成Matlab图像处理与应用[M].北京：国防工业出版社,2007.
[52][美]R C冈萨雷斯.数字图像处理(MATLAB版)[M].北京：电子工业出版社,2005.
[53]罗军辉,冯平,哈力旦A.MATLAB 7.0在图像处理中的应用[M].北京：机械工业出版社,2005.
[54]肖飞,于向军,吕震中,用InTouch、MATLAB和VC++开发工业监控系统软件,微计算机信息,2003第19卷11期：39～41
[55]高成Matlab接口技术与应用[M].北京：国防工业出版社,2007.
[56]杨丽娜.浅析VC++与MATLAB混合编程方法在图像处理中的应用.大众科技,No.2,2006
[57]Matrix VB User's Guide.The Math Works Inc.2000
[58]胡智文,邓铁如等,在VB应用程序中集成MATLAB,计算机工程与应用,2003.7：104～10