基于BP神经网络的沥青路面裂缝识别方法研究
|
摘要
沥青路面图像噪声污染多,随机性较强。针对传统路面图像在进行滤波、边缘检测等裂缝识别过程中,不能较好地识别裂缝信息且存在大量类似于裂缝的噪声污染问题,利用BP神经网络的学习性和容错性提出一种基于神经网络的裂缝识别方法。首先对沥青路面图像同态滤波增强后,将其分成32像素×32像素的小方格区域,然后提取小方格内图像参数与其邻域方格预测结果用于神经网络训练,最后将训练后的沥青路面图像小方格分为有裂缝和无裂缝两种,从而实现沥青路面裂缝的初提取。结果表明,该方法对沥青路面裂缝的识别率达到90%以上,能够较好地满足沥青路面裂缝识别的要求,是一种可行性较高的方法。
Noise pollutions and randomness of asphalt pavement image are strong. The cracks cannot be better identified from a large number of similar noise cracks in the traditional filtering and edge detection of the pavement image. To solve the noise pollution problem,a new method of fracture recognition based on neural network is proposed by using BP neural network for learning and fault tolerance. Firstly,the asphalt pavement enhanced image is divided into 32 × 32 small square regions. Secondly,the image parameters of the small squares are extracted and its neighborhood squares are used for neural network training. Finally,the small trained images are divided into two kinds,on has cracks and another has no cracks,thus the initial extraction of asphalt pavement cracks is achieved. The experimental results show that the recognition rate of asphalt pavement cracks is above90%. It is a feasible method to meet the requirement of pavement crack recognition.
Noise pollutions and randomness of asphalt pavement image are strong. The cracks cannot be better identified from a large number of similar noise cracks in the traditional filtering and edge detection of the pavement image. To solve the noise pollution problem,a new method of fracture recognition based on neural network is proposed by using BP neural network for learning and fault tolerance. Firstly,the asphalt pavement enhanced image is divided into 32 × 32 small square regions. Secondly,the image parameters of the small squares are extracted and its neighborhood squares are used for neural network training. Finally,the small trained images are divided into two kinds,on has cracks and another has no cracks,thus the initial extraction of asphalt pavement cracks is achieved. The experimental results show that the recognition rate of asphalt pavement cracks is above90%. It is a feasible method to meet the requirement of pavement crack recognition.
引文
[1]曹佳煜.基于图像处理的路面裂缝自动检测技术研究[D].西安:长安大学,2014.CAO J Y.Research on the technology of Automatic pavement crack detection based on digital image processing[D].Xian:Chang'an University,2014.
[2]姜吉荣.基于图像分析的路面裂缝检测方法与识别研究[D].南京:南京邮电大学,2016.JIANG J R.Research on pavement crack detection and recognition methods based on image analysis[D].Nanjing:Nanjing University of Posts and Telecommunications,2016.
[3]高建贞,任明武,唐振民,等.路面裂缝的自动检测与识别[J].计算机工程,2003,19(2):149-150.GAO J Z,REN M W,TANG Z M,et al.Automatic road crack detection and identification[J].Computer Engineering,2003,19(2):149-150.
[4]彭博.基于路面高精三维图像的裂缝自动识别与分类算法[D].成都:西南交通大学,2014.PENG B.Automatic crack detection and classification algorithms based on high resolution 3D pavement images[D].Chengdu:Southwest Jiaotong University,2014.
[5]荣婧,潘玉利.基于图像的水泥刻槽路面裂缝识别方法[J].公路交通科技,2012,29(3):45-50.RONG J,PAN Y L.Image based crack detection algorithm with application to cement concrete pavement[J].Journal of Highway and Transportation Research and Development,2012,29(3):45-50.
[6]张宏,英红.频域滤波的水泥路面图像降噪增强方法[J].土木建筑与环境工程,2015,37(3):48-52.ZHANG H,YING H.Denoising and enhencing method in cement pavement image based on frequency domain filter[J].Journal of Civil,Architectural&Environmental Engineering,2015,37(3):48-52.
[7]孙波成,邱延峻,梁世庆.基于小波的路面裂缝识别研究[J].重庆交通大学学报(自然科学版),2010,29(1):69-72.SUN B C,QIU Y J,LIANG S Q.Cracking recognition of pavement surface based on wavelet technology[J].Journal of Chongqing Jiaotong University(Natural Science Edition),2010,29(1):69-72.
[8]樊海玮,张国翊,丁爱玲,等.BP改进算法及其在路面裂缝检测中的应用[J].长安大学学报(自然科学版),2010,30(1):46-53.FAN H W,ZHANG G Y,DING A L,et al.Improved BP algorithm and its application in detection of pavement crack[J].Journal of Chang'an University(Natural Science Edition),2010,30(1):46-53.
[9]丁爱玲,焦李成.基于支撑矢量机的路面破损识别[J].长安大学学报(自然科学版),2007,27(2):34-37.DING A L,JIAO L C.Automation of recognition pavement surface distress based on support vector machine[J].Journal of Chang'an University(Natural Science Edition),2007,27(2):34-37.
[10]余发山,李睿,陈步威.基于小波变换的Canny检测算法[J].河南理工大学学报(自然科学版),2009,28(1):71-74.YU F S,L R,CHEN B W.Canny operator detection based on wavelet transform[J].Journal of Henan Polytechnic University(Natural Science),2009,28(1):71-74.
[11]褚文涛,李郑明,陆键.路面病害检测中的裂缝信息快速识别方法研究[J].中外公路,2013(6):80-84.CHU W T,LI Z M,LU J.Rapid identification method of crack information in pavement distress detection[J].Journal of China&Foreign Highway,2013(6):80-84.
[12]王冲,王葆茜.沥青混凝土路面裂缝自动识别方法研究[J].中外公路,2013(6):51-55.WANG C,WANG B Q.Automatic identification method of asphalt concrete pavement cracks[J].Journal of China&Foreign Highway,2013(6):51-55.
[13]张雷,肖梅,马建,等.基于视觉模型的路面裂缝检测算法[J].长安大学学报(自然科学版),2009,29(5):21-24.ZHANG L,XIAO M,MA J,et al.Pavement crack detection based on visual model[J].Journal of Chang’an University(Natural Science Edition),2009,29(5):21-24.
[14]彭博,蒋阳升,蒲云.基于数字图像处理的路面裂缝自动分类算法[J].中国公路学报,2014,27(9):10-18.PENG B,JIANG Y S,PU Y.Automated classification algorithm of pavement crack based on digital image processing[J].China Journal of Highway and Transport,2014,27(9):10-18.
[15]徐婷,祝站东.基于改进神经网络的机器视觉的路面破损检测系统研究[J].公路,2012(9):210-214.XU T,ZHU Z D.Development of road surface inspection system based on computer vision with improved neural network[J].Highway,2012(9):210-214.
[16]JIANG M H,GEORGES G,DENG B X,et al.A fast learning algorithm for time-delay neural networks[J].Information Sciences,2002,24(3):27-39.
[2]姜吉荣.基于图像分析的路面裂缝检测方法与识别研究[D].南京:南京邮电大学,2016.JIANG J R.Research on pavement crack detection and recognition methods based on image analysis[D].Nanjing:Nanjing University of Posts and Telecommunications,2016.
[3]高建贞,任明武,唐振民,等.路面裂缝的自动检测与识别[J].计算机工程,2003,19(2):149-150.GAO J Z,REN M W,TANG Z M,et al.Automatic road crack detection and identification[J].Computer Engineering,2003,19(2):149-150.
[4]彭博.基于路面高精三维图像的裂缝自动识别与分类算法[D].成都:西南交通大学,2014.PENG B.Automatic crack detection and classification algorithms based on high resolution 3D pavement images[D].Chengdu:Southwest Jiaotong University,2014.
[5]荣婧,潘玉利.基于图像的水泥刻槽路面裂缝识别方法[J].公路交通科技,2012,29(3):45-50.RONG J,PAN Y L.Image based crack detection algorithm with application to cement concrete pavement[J].Journal of Highway and Transportation Research and Development,2012,29(3):45-50.
[6]张宏,英红.频域滤波的水泥路面图像降噪增强方法[J].土木建筑与环境工程,2015,37(3):48-52.ZHANG H,YING H.Denoising and enhencing method in cement pavement image based on frequency domain filter[J].Journal of Civil,Architectural&Environmental Engineering,2015,37(3):48-52.
[7]孙波成,邱延峻,梁世庆.基于小波的路面裂缝识别研究[J].重庆交通大学学报(自然科学版),2010,29(1):69-72.SUN B C,QIU Y J,LIANG S Q.Cracking recognition of pavement surface based on wavelet technology[J].Journal of Chongqing Jiaotong University(Natural Science Edition),2010,29(1):69-72.
[8]樊海玮,张国翊,丁爱玲,等.BP改进算法及其在路面裂缝检测中的应用[J].长安大学学报(自然科学版),2010,30(1):46-53.FAN H W,ZHANG G Y,DING A L,et al.Improved BP algorithm and its application in detection of pavement crack[J].Journal of Chang'an University(Natural Science Edition),2010,30(1):46-53.
[9]丁爱玲,焦李成.基于支撑矢量机的路面破损识别[J].长安大学学报(自然科学版),2007,27(2):34-37.DING A L,JIAO L C.Automation of recognition pavement surface distress based on support vector machine[J].Journal of Chang'an University(Natural Science Edition),2007,27(2):34-37.
[10]余发山,李睿,陈步威.基于小波变换的Canny检测算法[J].河南理工大学学报(自然科学版),2009,28(1):71-74.YU F S,L R,CHEN B W.Canny operator detection based on wavelet transform[J].Journal of Henan Polytechnic University(Natural Science),2009,28(1):71-74.
[11]褚文涛,李郑明,陆键.路面病害检测中的裂缝信息快速识别方法研究[J].中外公路,2013(6):80-84.CHU W T,LI Z M,LU J.Rapid identification method of crack information in pavement distress detection[J].Journal of China&Foreign Highway,2013(6):80-84.
[12]王冲,王葆茜.沥青混凝土路面裂缝自动识别方法研究[J].中外公路,2013(6):51-55.WANG C,WANG B Q.Automatic identification method of asphalt concrete pavement cracks[J].Journal of China&Foreign Highway,2013(6):51-55.
[13]张雷,肖梅,马建,等.基于视觉模型的路面裂缝检测算法[J].长安大学学报(自然科学版),2009,29(5):21-24.ZHANG L,XIAO M,MA J,et al.Pavement crack detection based on visual model[J].Journal of Chang’an University(Natural Science Edition),2009,29(5):21-24.
[14]彭博,蒋阳升,蒲云.基于数字图像处理的路面裂缝自动分类算法[J].中国公路学报,2014,27(9):10-18.PENG B,JIANG Y S,PU Y.Automated classification algorithm of pavement crack based on digital image processing[J].China Journal of Highway and Transport,2014,27(9):10-18.
[15]徐婷,祝站东.基于改进神经网络的机器视觉的路面破损检测系统研究[J].公路,2012(9):210-214.XU T,ZHU Z D.Development of road surface inspection system based on computer vision with improved neural network[J].Highway,2012(9):210-214.
[16]JIANG M H,GEORGES G,DENG B X,et al.A fast learning algorithm for time-delay neural networks[J].Information Sciences,2002,24(3):27-39.