基于高斯混合部件模型的铁路扣件检测
|
摘要
针对采集图像中铁路扣件存在形状的变化、扣件图像的光照差异较大和扣件被异物局部遮挡的问题,根据对可变形部件模型算法和高斯混合模型的研究,提出了高斯混合部件模型算法.结合扣件图像边缘特性及改进的Roberts算子计算图像梯度,将归一化后的方向梯度直方图特征作为高斯混合部件模型算法的底层特征,根据扣件形状划分部件,部件之间的相对位置采用星型连接方式度量,运用余弦相似性度量部件中方向梯度直方图特征的相似度,部件模型使用高斯混合模型并采用期望最大化算法迭代求解.将高斯混合部件模型算法应用于扣件检测中,最终平均检测效果为漏检率3.16%、误检率9.80%、正确率90.27%.
Herein, the shape deformations in the collected images of railway fasteners, the large illumination difference in the fastener image, and the partial occlusion of the fastener by foreign objects is addressed. A Gaussian mixture part model(GMPM) algorithm is proposed to address these issues. This model is based on previous research of deformable part model; however, it was further refined by combining with a Gaussian mixture model(GMM) algorithm. The image gradient was calculated by combining the edge characteristics of the fastener image and application of the improved Roberts operator to the image. Normalized histogram of oriented gradient(HOG) features were used as the basis of the GMPM algorithm. The image was divided into a number of regions considering the shape of the fastener,and a star connection was used to measure the relative positions of the various subsections of the subdivided image. Cosine similarities were computed to measure the similarity of the HOG features of the different parts of the image. The part model was solved iteratively by using the GMM with an expectation-maximization algorithm. By using the GMPM algorithm to detect defects in railway fasteners,an average accuracy of 90.27% for detection rate is achieved,while the average missed detection rate,and the average false detection rate are 3.16% and 9.80%,respectively.
Herein, the shape deformations in the collected images of railway fasteners, the large illumination difference in the fastener image, and the partial occlusion of the fastener by foreign objects is addressed. A Gaussian mixture part model(GMPM) algorithm is proposed to address these issues. This model is based on previous research of deformable part model; however, it was further refined by combining with a Gaussian mixture model(GMM) algorithm. The image gradient was calculated by combining the edge characteristics of the fastener image and application of the improved Roberts operator to the image. Normalized histogram of oriented gradient(HOG) features were used as the basis of the GMPM algorithm. The image was divided into a number of regions considering the shape of the fastener,and a star connection was used to measure the relative positions of the various subsections of the subdivided image. Cosine similarities were computed to measure the similarity of the HOG features of the different parts of the image. The part model was solved iteratively by using the GMM with an expectation-maximization algorithm. By using the GMPM algorithm to detect defects in railway fasteners,an average accuracy of 90.27% for detection rate is achieved,while the average missed detection rate,and the average false detection rate are 3.16% and 9.80%,respectively.
引文
[1]刘甲甲,李柏林,罗建桥,等.融合PHOG和MSLBP特征的铁路扣件检测算法[J].西南交通大学学报,2015,50(2):256-263.LIU Jiajia,LI Bailin,LUO Jianqiao,et al.Railway fastener detection algorithm integrating PHOG and MSLBP features[J].Journal of Southwest Jiaotong University,2015,50(2):256-263.
[2]刘甲甲,熊鹰,李柏林,等.基于计算机视觉的轨道扣件缺陷自动检测算法研究[J].铁道学报,2016,38(8):73-80.LIU Jiajia,XIONG Ying,LI Bailin,et al.Research on automatic inspection algorithm for railway fastener defects based on computer vision[J].Journal of the China Railway Society,2016,38(8):73-80.
[3]MARINO F,DISTANTE A,MAZZEO P L,et al.Areal-time visual inspection system for railway maintenance:automatic hexagonal-headed bolts detection[J].IEEE Transactions on Systems Man&Cybernetics Part C:Applications&Reviews,2007,37(3):418-428.
[4]DOU Yunguang,HUANG Yaping,LI Qingyong,et al.A fast template matching-based algorithm for railway bolts detection[J].International Journal of Machine Learning&Cybernetics,2014,5(6):835-844.
[5]HORAUD R,FORBES F,YGUEL M,et al.Rigid and articulated point registration with expectation conditional maximization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(3):587-602.
[6]JIAN Bing,VEMURI B C.Robust point set registration using gaussian mixture models[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2011,33(8):1633-1645.
[7]MYRONENKO A,SONG Xubo.Point set registration:coherent point drift[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(12):2262-2275.
[8]SáNCHEZ J,PERRONNIN F,MENSINK T,et al.Image classification with the fisher vector:theory and practice[J].International Journal of Computer Vision,2013,105(3):222-245.
[9]YU Guoshen,SAPIRO G,MALLAT S.Solving inverse problems with piecewise linear estimators:from Gaussian mixture models to structured sparsity[J].IEEETransactions on Image Processing,2012,21(5):2481-2499.
[10]FELZENSZWALB P,MCALLESTER D,RAMANAND.A discriminatively trained,multiscale,deformable part model[C]//Computer Vision and Pattern Recognition.Piscataway:IEEE,2008:1-8.
[11]FELZENSZWALB P F,GIRSHICK R B,MCALLESTERD,et al.Object detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645.
[12]FELZENSZWALB P F,GIRSHICK R B,MCALLES-TER D.Cascade object detection with deformable part models[C]//Computer Vision and Pattern Recognition.Piscataway:IEEE,2010:2241-2248.
[13]FELZENSZWALB P F,MCALLESTER D.Object detection grammars[C]//ICCV Workshops.Piscataway:IEEE,2011:691.
[14]YANG Yi,RAMANAN D.Articulated pose estimation with flexible mixtures-of-parts[C]//Computer Vision and Pattern Recognition.Piscataway:IEEE,2011:1385-1392.
[15]YANG Yi,RAMANAN D.Articulated human detection with flexible mixtures of parts[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2013,35(12):2878-2890.
[16]SEO H J,MILANFAR P.Training-free,generic object detection using locally adaptive regression kernels[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1688-704.
[17]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition.Piscataway:IEEE,2005:886-893.
[18]MACQUEEN J.Some methods for classification and analysis of multivariate observations[C]//Proc of Berkeley Symposium on Mathematical Statistics&Probability.California:University of California Press,1967:281-297.
[2]刘甲甲,熊鹰,李柏林,等.基于计算机视觉的轨道扣件缺陷自动检测算法研究[J].铁道学报,2016,38(8):73-80.LIU Jiajia,XIONG Ying,LI Bailin,et al.Research on automatic inspection algorithm for railway fastener defects based on computer vision[J].Journal of the China Railway Society,2016,38(8):73-80.
[3]MARINO F,DISTANTE A,MAZZEO P L,et al.Areal-time visual inspection system for railway maintenance:automatic hexagonal-headed bolts detection[J].IEEE Transactions on Systems Man&Cybernetics Part C:Applications&Reviews,2007,37(3):418-428.
[4]DOU Yunguang,HUANG Yaping,LI Qingyong,et al.A fast template matching-based algorithm for railway bolts detection[J].International Journal of Machine Learning&Cybernetics,2014,5(6):835-844.
[5]HORAUD R,FORBES F,YGUEL M,et al.Rigid and articulated point registration with expectation conditional maximization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(3):587-602.
[6]JIAN Bing,VEMURI B C.Robust point set registration using gaussian mixture models[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2011,33(8):1633-1645.
[7]MYRONENKO A,SONG Xubo.Point set registration:coherent point drift[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(12):2262-2275.
[8]SáNCHEZ J,PERRONNIN F,MENSINK T,et al.Image classification with the fisher vector:theory and practice[J].International Journal of Computer Vision,2013,105(3):222-245.
[9]YU Guoshen,SAPIRO G,MALLAT S.Solving inverse problems with piecewise linear estimators:from Gaussian mixture models to structured sparsity[J].IEEETransactions on Image Processing,2012,21(5):2481-2499.
[10]FELZENSZWALB P,MCALLESTER D,RAMANAND.A discriminatively trained,multiscale,deformable part model[C]//Computer Vision and Pattern Recognition.Piscataway:IEEE,2008:1-8.
[11]FELZENSZWALB P F,GIRSHICK R B,MCALLESTERD,et al.Object detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645.
[12]FELZENSZWALB P F,GIRSHICK R B,MCALLES-TER D.Cascade object detection with deformable part models[C]//Computer Vision and Pattern Recognition.Piscataway:IEEE,2010:2241-2248.
[13]FELZENSZWALB P F,MCALLESTER D.Object detection grammars[C]//ICCV Workshops.Piscataway:IEEE,2011:691.
[14]YANG Yi,RAMANAN D.Articulated pose estimation with flexible mixtures-of-parts[C]//Computer Vision and Pattern Recognition.Piscataway:IEEE,2011:1385-1392.
[15]YANG Yi,RAMANAN D.Articulated human detection with flexible mixtures of parts[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2013,35(12):2878-2890.
[16]SEO H J,MILANFAR P.Training-free,generic object detection using locally adaptive regression kernels[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1688-704.
[17]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition.Piscataway:IEEE,2005:886-893.
[18]MACQUEEN J.Some methods for classification and analysis of multivariate observations[C]//Proc of Berkeley Symposium on Mathematical Statistics&Probability.California:University of California Press,1967:281-297.