货车超限检测系统中图像处理方法研究
|
摘要
本文以货车超限检测系统为研究背景,研究了图像法在超限检测系统中的应用。以数字图像处理技术为基础,重点介绍了小波相关理论在对货车图像的去噪及边缘检测中的应用。
文章首先阐述了课题研究目的及意义,从实际的工程背景出发建立图像模型及确定技术方案。图像去噪方面,考虑到货车在运行过程中受特殊环境的影响,采集的货车图像含有椒盐噪声及高斯噪声等混合噪声。在小波传统阈值去噪的基础上,利用多级中值滤波可较好的抑制椒盐噪声并能较好保持图像细节而提升小波在抑制高斯噪声方面响应快等特点,本文采用了基于多级中值滤波与提升小波相结合的图像去噪算法,取得了比较好的实验效果,从而为有效地检测货车图像边缘打下好的基础。
由于超限检测系统中采集的货车图像均是以天空为背景,本文采用小波变换模极大值边缘检测及边缘跟踪技术就能有效的检测出货车图像边缘;同时为了减少边缘检测所需时间,在去除伪边缘的阈值的选取上,采用改进型的最大方差自动取阈值法,不仅使阈值选取准确,而且很大程度上减少了阈值选取时间,从而降低边缘检测时间。实验表明:本文方法能有效的检测出货车边缘,为超限检测打下基础。
文章最后简单介绍厂货车超限的相关基础知识,指出了判断货车超限方法及依据,分析了超限检测系统中图像处理部分所完成的功能。
Based on the background of freight train gauge-exceeding detecting system, the thesis makes research on the image processing applied in the system. Based on the digital image processing,the thesis especially introduces the wavelet relevant theory applied in the freight train image denoising and the edge detecting.
The thesis first presents the purpose and meaning, it builds the image module and decides the technology way from the practical project background. In the facet of image, According to the freight train will be influenced when it runs, so the collecting image includes the mix noise. Based on the common wavelet shrinkage, because the multistage median filter can not only denoise the salt and pepper noise but also keep the details of the image. The lifting wavelet can dismiss the time of denoising the gauss noise, so the thesis applys the two ways to deniose the mix noise. It gets good effect through practicing the image denoising by the thesis introduced way. So it can build the good foundation for the edge detecting.
As the freight train image is collected by the background of the sky. The thesis applies the wavelet modulus maxima technique and the edge following technique to detect the freight train edge, which gets good outcome. According to the realistic and validity of the detecting, the thesis chooses the improved otsu way, it not only strongs the adaptive and accurate, but also dismisses the time of the choosed threshold and the edge detecting .The practices demonstrates that the way of the thesis can detecting the freight train edge, it builds the good foundation for the train gauge-exceeding detecting.
In the end of the thesis, it introduces the related fundamental theories of the freight train gauge-exceeding detecting system, points to how to judge the freight train exceeding the gauge and analyzes the function of the image processing in the freight train gauge-exceeding detecting system.
文章首先阐述了课题研究目的及意义,从实际的工程背景出发建立图像模型及确定技术方案。图像去噪方面,考虑到货车在运行过程中受特殊环境的影响,采集的货车图像含有椒盐噪声及高斯噪声等混合噪声。在小波传统阈值去噪的基础上,利用多级中值滤波可较好的抑制椒盐噪声并能较好保持图像细节而提升小波在抑制高斯噪声方面响应快等特点,本文采用了基于多级中值滤波与提升小波相结合的图像去噪算法,取得了比较好的实验效果,从而为有效地检测货车图像边缘打下好的基础。
由于超限检测系统中采集的货车图像均是以天空为背景,本文采用小波变换模极大值边缘检测及边缘跟踪技术就能有效的检测出货车图像边缘;同时为了减少边缘检测所需时间,在去除伪边缘的阈值的选取上,采用改进型的最大方差自动取阈值法,不仅使阈值选取准确,而且很大程度上减少了阈值选取时间,从而降低边缘检测时间。实验表明:本文方法能有效的检测出货车边缘,为超限检测打下基础。
文章最后简单介绍厂货车超限的相关基础知识,指出了判断货车超限方法及依据,分析了超限检测系统中图像处理部分所完成的功能。
Based on the background of freight train gauge-exceeding detecting system, the thesis makes research on the image processing applied in the system. Based on the digital image processing,the thesis especially introduces the wavelet relevant theory applied in the freight train image denoising and the edge detecting.
The thesis first presents the purpose and meaning, it builds the image module and decides the technology way from the practical project background. In the facet of image, According to the freight train will be influenced when it runs, so the collecting image includes the mix noise. Based on the common wavelet shrinkage, because the multistage median filter can not only denoise the salt and pepper noise but also keep the details of the image. The lifting wavelet can dismiss the time of denoising the gauss noise, so the thesis applys the two ways to deniose the mix noise. It gets good effect through practicing the image denoising by the thesis introduced way. So it can build the good foundation for the edge detecting.
As the freight train image is collected by the background of the sky. The thesis applies the wavelet modulus maxima technique and the edge following technique to detect the freight train edge, which gets good outcome. According to the realistic and validity of the detecting, the thesis chooses the improved otsu way, it not only strongs the adaptive and accurate, but also dismisses the time of the choosed threshold and the edge detecting .The practices demonstrates that the way of the thesis can detecting the freight train edge, it builds the good foundation for the train gauge-exceeding detecting.
In the end of the thesis, it introduces the related fundamental theories of the freight train gauge-exceeding detecting system, points to how to judge the freight train exceeding the gauge and analyzes the function of the image processing in the freight train gauge-exceeding detecting system.
引文
[1]吴育俭,郭维鸿,刘东岭.铁路货运技术.中国铁道工业出版社,2000.
[2]朱志武,吴长厚.铁路货车装载超限检测装置的研制.铁路技术创新,2004(12):5-6.
[3]许绍兴,邓杰.建立货物列车装载运行安全监测系统设想.铁道运输与经济.2002,24(1):21-23.
[4]毛庆洲,李清泉,陈长军,刘勇.铁路货车装载尺寸超限自动测量技术研究.2007,29(5):8-12.
[5]Gonzalez R.Woods R著.阮秋琦,阮宁智译.数字图像处理.第二版.电子工业出版社,2007.
[6]罗军辉,冯平,哈力旦·A.MATLAB7.0在图像处理中的应用机械工业出版社,2005.
[7]陈武凡.小波分析及其在图像处理中的应用.科学出版社,2002.
[8]飞思科技产品研发中心.小波分析理论与MATLAB7实现.电子工业出版社,2005.
[9]王润生.图像理解.国防科技大学出版社,1995.
[10]彭玉华.小波变换与工程应用.科学出版社,1999.
[11]余成波.数字图像处理及MATLAB实现.重庆大学出版社,2003.
[12]董长虹,高志,余啸海.Matlab小波分析工具箱原理与应用.国防工业出版社,2004.
[13]魏明果.实用小波分析.北京理工大学出版社,2005.
[14]杨建国.小波分析及工程应用.机械工业出版社,2005.
[15]程正兴.小波分析算法与应用.西安交通大学出版社,1998.
[16]陈静.基于小波域HMT模型的图像去噪研究.郑州大学硕士学位论文,2006.
[17]J.J.Benedetto,M.W Frazier.Wavelets-Mathematics and Applications.USA:CRC Press,1994,90-95.
[18]Mahbubur Rahman S M,Kamurul Hasan Md.Wavelet-domain iterative center weighted median filter for image denoising.Signal Processing,2003,83(5):1001-1012.
[19]孙延奎.小波分析及其应用.机械工业出版社,2004.
[20]黄爱民,安向京,骆力.数字图像处理与分析基础.中国水利水电出版社,2005.
[21]周伟,桂林,周林,张家祥.MATLAB小波分析高级教程.西安电子科技大学出版社,2006.
[22]胡广书.现代信号处理教程.清华大学出版社,2004.
[23]刘涛,曾利祥,曾军.实用小波分析入门.国防工业出版社,2006.
[24]周艳,唐权华,蒋朝哲.图像快速自适应加权中值滤波.微计算机信息.2008.07-3(24):168-169.
[25]Stepien J,Zielinski T,Rumian R.Image Denoising for Adaptive lifting Scheme.Proc.European Siyaol Proces.signal Comf erenace E USIPCO -2000,Finland:Tampere,2000.
[26]S.Mallat,A Wavelet Tour of Signal Processing.Second Edition.Academic Press,1999.
[27]Donoho D.De-noising by soft-thresholding.IEEE Trans Inform Theiry 1995;41:612-27.
[28]I.Daubechies,W.Sweldens,"Factoring Wavelet Transforms into Lifting Steps,J.Fourier Anal.Appl.,Vol.4,Nr.3,1998.
[29]Chang S G,Yu B and Veterli MSpatially adaptive wavelet thresholding with context modeling for image denoising.IEEETrans.on IP.2000.9(9).1522-1531
[30]Javad Musevi Niya,Ali Aghagolzadeh.Edge detection using directional wavelet transform.IEEE MELECON 2004.Dubrovnik,Croatia,2004.
[31]Zhang X P.Thresholding neural networks for adaptive noise reduction.IEEE Transactions on Neural Networks.2001,12(3):567-582.
[32]张永学,陈丽霞,钟正斌.提升小波变换在信号去噪中的应用.石油仪器.2007,21(1):80-82.
[33]Henk J.A.M.Heijmans,G Piella,B.Pesquet-Popescu.Building Adaptive 2D Wavelet Decompositions by Update Lifting Proceedings of the IEEE International Conference on Image Processing(ICIP 2002),Rochester,USA,2002:397-400.
[34]G Pidlla,B.Pesquecu,Henk J.A.M.Heijmans.Adaptive Update Lifting with a Decision Rule Based on Derivative Filters.IEEE Signal Process.2002,9(10):329-332.
[35]王志武,丁国清,颜国正,林良明.自适应提升小波变换与图象去噪.红外 与毫米波学报.2002,21(6):447-450.
[36]Henk J.A.M.Heijmans,B e atrice Pesquet-Popescu,Gemma Piella.Building Nonredunant Adaptive Wavelets by Update Lifting,Preprint Submitted to Elsevier Science 2 November 2004:17-28.
[37]W.Sweldens.The lifting scheme:A construction of second generation wavelets.SIAM J.MATIH.ANAL.Vol.29,No2,pp.511-546,March 1998.
[38]杨兴明,吴永忠,孙锐,杨萍.基于小波多分辨率分析和新的阈值自适应的信号去噪.合肥工业大学学报.2007.30(12).1580-1583.
[39]Lei Zhang,Paul Bao.Denoising by spatial correlation thresholding.IEEE Trans.on Circuits and System for Video Technology.2003.13.535-538
[40]Stepien J,Zielinski T,Rumian R.Image Denoising for Adaptive lifting Scheme.Proc.European Signal Processing Conference EUSIPCO-2000,Finland:Tampere,2000.
[41]Ho W J,Chang W T.Adaptive predictor based on maxi-mally fiat halfband filter in lifting scheme.IEEE Transactions on Signal Processing,1999,47(11):2965-2977.
[42]王发牛,粱栋,唐俊,屈磊.小波变换模极大值多尺度边缘检测.仪器仪表学报.2006,27(6):2147-2149.
[43]张艳华.基于二提升小波的MR图像自适应阈值去噪研究.华中师范大学硕士学位论文.2007.
[44]张毅军等.二维熵图像阈值分割的快速递推算法.模糊识别与人工智能.1997,10(3):259-264.
[45]章毓晋,图像分割.科学出版社,2001.
[46]Shubhankar R,Bani K.A Bayesian transformation model for wavelet shrinkage.IEEE Trans.on IP 2003.12(12).1512-1520.
[47]Javad Musevi Niya,Ali Aghagolzadeh.Edge detection using directionalwavelet transform.IEEE MELECON 2004.Dubrovnik,Croatia,2004.
[48]Wang X.H,,Robert S.H.Istepanian,Yong Hua Song.Application of wavelet modulus maxima in microarray spots recognition,IEEE transactions on Nanobioscience.December 2003.vol.2.no.4.
[49]Young Hyun Baek,Oh Sung Byun,Sung-Rung Moon.Image edge detection using adaptive morphology Meyer wavelet,Neural Networks,2003.Proceedings of the International Joint Conference on Volume 2,20-24 July 2003 Page(s):1219-1222 vol.2.
[50]张兴峰,沈兰荪.图像分割技术研究.电路与系统学报.9(2),2004.
[51]季虎,孙即祥,邵晓芳,毛玲.图像边缘提取方法及展望.计算机下程与应用.2004(14):70-73.
[52]张光远.铁路超限检测系统研究.西南交通大学硕士论文,2003.
[53]Hanmandlu M,See J,Vasikarla S.Fuzzy edge detector using entropy optimization.Proceedings of the International Conference on Information Technology:Ceding and Computing.2004:665-670.
[54]杨煊,梁德群.基于方向信息的多尺度边缘检测方法.西安电子科技大学学报,1997,24(4):524-530.
[55]J.Canny.A Computational Approach to Edge Detection,IEEE Transactions on Pattern Analysis and Machine Inteligence,Novemeber 1986,Vol.PAMI-8,No.6.
[56]S.Mallat.A Wavelet Tour of Signal Processing 2ed,Academic Press;1999.
[57]章毓晋.过渡区和图像分割.电子学报.1996a,24(1):12-17.
[58]Ming Ye.Robust visual motion analysis:piecewise-smooth optical flow and motion-based detection and tracking.University of Washington,2002.
[59]章毓晋.图像分割评价技术分类和比较.中国图像图形学报.1996c,1(2):170-174.
[60]龚声蓉,刘纯平,王强.数字图像处理与分析,2006.
[61]朱为鹏.基于数字图像处理的货车超限监测算法研究.西南交通大学硕士学位论文,2003.
[62]柴雪松,杨凤春,边久松,罗林.货车装载安全状态监测系统的研制.2002,4(61):7-9.
[63]于冬,顾培亮,陈钟,高璇.铁路货车装载状态监视和超限检测系统的研究.中国铁道科学.2004,25(10):141-144.
[64]鞠殿铭,王存喜.超限货物运输轮廓图的概念及应用.铁道货运.2000(4):27-28.
[65]Honggang Li,Qiao Wang etc.A Novel Design of Lifting Scheme from General Wavelet.Signal Processing,IEEE,Transactiens on 2001, 49(3):1714-1716.
[66]Kondo H,et al.Measurement of vehicle width by analyzing spectrum envelope of image.Transactions of the Institute of Electrical Engineers of Japan.1995,I15C(11):1304-9.
[67]裘镇宇,危辉.基于Freeman链码的边缘跟踪算法及直线段检测.2008(1):17-20.
[68]贾瑞良.铁路货运组织.中国铁道出版社,1994.
[69]康文超,张慧.货运检查站的设置及布局研究.铁道货运,2004(4):25-27
[70]Meer P,Georgescu B.Edge detection with embedded confi-dence.IEEE Transactions on Pattern Analysis and Machine Intel-ligence,2001,23(12):1351-1365.
[71]傅国东.对超限货物有关概念的理解与计算.铁道货运,2003(3):42-43.
[72]于忠.专用线采用货车超限检测系统的探讨.铁道货运.2008(8):31-32.
[2]朱志武,吴长厚.铁路货车装载超限检测装置的研制.铁路技术创新,2004(12):5-6.
[3]许绍兴,邓杰.建立货物列车装载运行安全监测系统设想.铁道运输与经济.2002,24(1):21-23.
[4]毛庆洲,李清泉,陈长军,刘勇.铁路货车装载尺寸超限自动测量技术研究.2007,29(5):8-12.
[5]Gonzalez R.Woods R著.阮秋琦,阮宁智译.数字图像处理.第二版.电子工业出版社,2007.
[6]罗军辉,冯平,哈力旦·A.MATLAB7.0在图像处理中的应用机械工业出版社,2005.
[7]陈武凡.小波分析及其在图像处理中的应用.科学出版社,2002.
[8]飞思科技产品研发中心.小波分析理论与MATLAB7实现.电子工业出版社,2005.
[9]王润生.图像理解.国防科技大学出版社,1995.
[10]彭玉华.小波变换与工程应用.科学出版社,1999.
[11]余成波.数字图像处理及MATLAB实现.重庆大学出版社,2003.
[12]董长虹,高志,余啸海.Matlab小波分析工具箱原理与应用.国防工业出版社,2004.
[13]魏明果.实用小波分析.北京理工大学出版社,2005.
[14]杨建国.小波分析及工程应用.机械工业出版社,2005.
[15]程正兴.小波分析算法与应用.西安交通大学出版社,1998.
[16]陈静.基于小波域HMT模型的图像去噪研究.郑州大学硕士学位论文,2006.
[17]J.J.Benedetto,M.W Frazier.Wavelets-Mathematics and Applications.USA:CRC Press,1994,90-95.
[18]Mahbubur Rahman S M,Kamurul Hasan Md.Wavelet-domain iterative center weighted median filter for image denoising.Signal Processing,2003,83(5):1001-1012.
[19]孙延奎.小波分析及其应用.机械工业出版社,2004.
[20]黄爱民,安向京,骆力.数字图像处理与分析基础.中国水利水电出版社,2005.
[21]周伟,桂林,周林,张家祥.MATLAB小波分析高级教程.西安电子科技大学出版社,2006.
[22]胡广书.现代信号处理教程.清华大学出版社,2004.
[23]刘涛,曾利祥,曾军.实用小波分析入门.国防工业出版社,2006.
[24]周艳,唐权华,蒋朝哲.图像快速自适应加权中值滤波.微计算机信息.2008.07-3(24):168-169.
[25]Stepien J,Zielinski T,Rumian R.Image Denoising for Adaptive lifting Scheme.Proc.European Siyaol Proces.signal Comf erenace E USIPCO -2000,Finland:Tampere,2000.
[26]S.Mallat,A Wavelet Tour of Signal Processing.Second Edition.Academic Press,1999.
[27]Donoho D.De-noising by soft-thresholding.IEEE Trans Inform Theiry 1995;41:612-27.
[28]I.Daubechies,W.Sweldens,"Factoring Wavelet Transforms into Lifting Steps,J.Fourier Anal.Appl.,Vol.4,Nr.3,1998.
[29]Chang S G,Yu B and Veterli MSpatially adaptive wavelet thresholding with context modeling for image denoising.IEEETrans.on IP.2000.9(9).1522-1531
[30]Javad Musevi Niya,Ali Aghagolzadeh.Edge detection using directional wavelet transform.IEEE MELECON 2004.Dubrovnik,Croatia,2004.
[31]Zhang X P.Thresholding neural networks for adaptive noise reduction.IEEE Transactions on Neural Networks.2001,12(3):567-582.
[32]张永学,陈丽霞,钟正斌.提升小波变换在信号去噪中的应用.石油仪器.2007,21(1):80-82.
[33]Henk J.A.M.Heijmans,G Piella,B.Pesquet-Popescu.Building Adaptive 2D Wavelet Decompositions by Update Lifting Proceedings of the IEEE International Conference on Image Processing(ICIP 2002),Rochester,USA,2002:397-400.
[34]G Pidlla,B.Pesquecu,Henk J.A.M.Heijmans.Adaptive Update Lifting with a Decision Rule Based on Derivative Filters.IEEE Signal Process.2002,9(10):329-332.
[35]王志武,丁国清,颜国正,林良明.自适应提升小波变换与图象去噪.红外 与毫米波学报.2002,21(6):447-450.
[36]Henk J.A.M.Heijmans,B e atrice Pesquet-Popescu,Gemma Piella.Building Nonredunant Adaptive Wavelets by Update Lifting,Preprint Submitted to Elsevier Science 2 November 2004:17-28.
[37]W.Sweldens.The lifting scheme:A construction of second generation wavelets.SIAM J.MATIH.ANAL.Vol.29,No2,pp.511-546,March 1998.
[38]杨兴明,吴永忠,孙锐,杨萍.基于小波多分辨率分析和新的阈值自适应的信号去噪.合肥工业大学学报.2007.30(12).1580-1583.
[39]Lei Zhang,Paul Bao.Denoising by spatial correlation thresholding.IEEE Trans.on Circuits and System for Video Technology.2003.13.535-538
[40]Stepien J,Zielinski T,Rumian R.Image Denoising for Adaptive lifting Scheme.Proc.European Signal Processing Conference EUSIPCO-2000,Finland:Tampere,2000.
[41]Ho W J,Chang W T.Adaptive predictor based on maxi-mally fiat halfband filter in lifting scheme.IEEE Transactions on Signal Processing,1999,47(11):2965-2977.
[42]王发牛,粱栋,唐俊,屈磊.小波变换模极大值多尺度边缘检测.仪器仪表学报.2006,27(6):2147-2149.
[43]张艳华.基于二提升小波的MR图像自适应阈值去噪研究.华中师范大学硕士学位论文.2007.
[44]张毅军等.二维熵图像阈值分割的快速递推算法.模糊识别与人工智能.1997,10(3):259-264.
[45]章毓晋,图像分割.科学出版社,2001.
[46]Shubhankar R,Bani K.A Bayesian transformation model for wavelet shrinkage.IEEE Trans.on IP 2003.12(12).1512-1520.
[47]Javad Musevi Niya,Ali Aghagolzadeh.Edge detection using directionalwavelet transform.IEEE MELECON 2004.Dubrovnik,Croatia,2004.
[48]Wang X.H,,Robert S.H.Istepanian,Yong Hua Song.Application of wavelet modulus maxima in microarray spots recognition,IEEE transactions on Nanobioscience.December 2003.vol.2.no.4.
[49]Young Hyun Baek,Oh Sung Byun,Sung-Rung Moon.Image edge detection using adaptive morphology Meyer wavelet,Neural Networks,2003.Proceedings of the International Joint Conference on Volume 2,20-24 July 2003 Page(s):1219-1222 vol.2.
[50]张兴峰,沈兰荪.图像分割技术研究.电路与系统学报.9(2),2004.
[51]季虎,孙即祥,邵晓芳,毛玲.图像边缘提取方法及展望.计算机下程与应用.2004(14):70-73.
[52]张光远.铁路超限检测系统研究.西南交通大学硕士论文,2003.
[53]Hanmandlu M,See J,Vasikarla S.Fuzzy edge detector using entropy optimization.Proceedings of the International Conference on Information Technology:Ceding and Computing.2004:665-670.
[54]杨煊,梁德群.基于方向信息的多尺度边缘检测方法.西安电子科技大学学报,1997,24(4):524-530.
[55]J.Canny.A Computational Approach to Edge Detection,IEEE Transactions on Pattern Analysis and Machine Inteligence,Novemeber 1986,Vol.PAMI-8,No.6.
[56]S.Mallat.A Wavelet Tour of Signal Processing 2ed,Academic Press;1999.
[57]章毓晋.过渡区和图像分割.电子学报.1996a,24(1):12-17.
[58]Ming Ye.Robust visual motion analysis:piecewise-smooth optical flow and motion-based detection and tracking.University of Washington,2002.
[59]章毓晋.图像分割评价技术分类和比较.中国图像图形学报.1996c,1(2):170-174.
[60]龚声蓉,刘纯平,王强.数字图像处理与分析,2006.
[61]朱为鹏.基于数字图像处理的货车超限监测算法研究.西南交通大学硕士学位论文,2003.
[62]柴雪松,杨凤春,边久松,罗林.货车装载安全状态监测系统的研制.2002,4(61):7-9.
[63]于冬,顾培亮,陈钟,高璇.铁路货车装载状态监视和超限检测系统的研究.中国铁道科学.2004,25(10):141-144.
[64]鞠殿铭,王存喜.超限货物运输轮廓图的概念及应用.铁道货运.2000(4):27-28.
[65]Honggang Li,Qiao Wang etc.A Novel Design of Lifting Scheme from General Wavelet.Signal Processing,IEEE,Transactiens on 2001, 49(3):1714-1716.
[66]Kondo H,et al.Measurement of vehicle width by analyzing spectrum envelope of image.Transactions of the Institute of Electrical Engineers of Japan.1995,I15C(11):1304-9.
[67]裘镇宇,危辉.基于Freeman链码的边缘跟踪算法及直线段检测.2008(1):17-20.
[68]贾瑞良.铁路货运组织.中国铁道出版社,1994.
[69]康文超,张慧.货运检查站的设置及布局研究.铁道货运,2004(4):25-27
[70]Meer P,Georgescu B.Edge detection with embedded confi-dence.IEEE Transactions on Pattern Analysis and Machine Intel-ligence,2001,23(12):1351-1365.
[71]傅国东.对超限货物有关概念的理解与计算.铁道货运,2003(3):42-43.
[72]于忠.专用线采用货车超限检测系统的探讨.铁道货运.2008(8):31-32.