矿井监控图像中空列车的识别
|
摘要
基于井下空列车与其他物体的几何形状差别,提出空列车监控图像的识别算法.运用圆形结构元素对监控图像进行形态学的先开启、后闭合的操作,用Canny边缘检测算子来检测图像的边缘,并对边缘的图像进行变换分析,突出了空列车图像边缘的直线性质.结果表明:形态学操作有效地减弱了其他对象的边缘,得到比较满意地空列车图像的直线性质的边缘;在不同监控对象的图像的Radon变换域中的特征最大值比Hough变换域中的特征最大值有更好的可分离性.Radon变换作为识别算法中的变换方法,可识别了煤矿井下红外监控系统中的空列车图像.
Based on the difference of the geometrical shape between the empty trains and other objects.A recognition algorithm of the empty-trains-image was proposed.The monitoring images were opened and closed using a circle structural element in morphological in the algorithm,and their edges were detected with Canny operator.With the transform analysis of the edges images,the linear characteristics of the edges of the empty-trains-images were outstood.The results show that the linear edges of the empty trains were gotten satisfactorily,while that of the other objects were weakened efficiently,and the separability of the diagnostic maximum of the different monitored object in Radon transformation field is better than that in Hough transformation field.The Radon transform can recognize the empty-trains-image in the coal mine infrared monitoring system.
Based on the difference of the geometrical shape between the empty trains and other objects.A recognition algorithm of the empty-trains-image was proposed.The monitoring images were opened and closed using a circle structural element in morphological in the algorithm,and their edges were detected with Canny operator.With the transform analysis of the edges images,the linear characteristics of the edges of the empty-trains-images were outstood.The results show that the linear edges of the empty trains were gotten satisfactorily,while that of the other objects were weakened efficiently,and the separability of the diagnostic maximum of the different monitored object in Radon transformation field is better than that in Hough transformation field.The Radon transform can recognize the empty-trains-image in the coal mine infrared monitoring system.
引文
[1]CHENG C M,REES N W,CHAN A.Fuzzy speedcontrol of a coal train[C/OL].Essex,UK.FormaraLtd.1998.UKACC International Conference onControl'98.[2006-06-11].http://ieeexplore.ieee.org/iel4/5883/15689/00727979.pdf?tp=&arnumber=727979&isnumber=15689.
[2]李玉良.机车信号监控技术及其应用[J].中国矿业大学学报,1997,26(4):54-56.LI Yu-liang.Locomotive signal monitoring technolo-gy and Its application[J].Journal of China Universityof Mining&Technology,1997,26(4):54-56.
[3]朱华,葛世荣,左明,等.矿车红外探测报警系统研制[J].中国矿业大学学报,2002,31(2):166-170.ZHU Hua,GE Shi-rong,ZUO Ming,et al.Devel-opment of infrared detecting and warning system forbody targets in mine cars[J].Journal of China Uni-versity of Mining&Technology,2002,31(2):166-170.
[4]孙继平,关永,张杰.DSP极低码率的矿井远程视频监控系统[J].西安科技学院学报,2003,23(3):283-286.SUN Ji-ping,GUAN Yong,ZHANG Jie.The ex-tremely low rated long-range video supervision sys-tem based on DSP[J].Journal of Xi’an University ofScience and Technology,2003,23(3):283-286.
[5]关永.基于红外探测技术的矿井远程视频监控系统[D].北京:中国矿业大学机电与信息工程学院,2004.
[6]黄新武,吴律,牛滨华.基于抛物线拉东变换的地震道重构[J].中国矿业大学学报,2003,32(5):534-539.HUANG Xin-wu,WU Lu,NIU Bin-hua.Recon-struction of seismic traces by parabolic Radon trans-form[J].Journal of China University of Mining&Technology,2003,32(5):534-539.
[7]TABBONE S,WENDLING L.Recognition of sym-bols in grey level line-drawings from an adaptation ofthe Radon transform[J].Pattern Recognition,2004(2):570-573.
[8]TOFT P A.Using the generalized Radon transformfor detection of curves in noisy images[J].Acous-tics,Speech,and Signal Processing,1996(4):2219-2222.
[9]GōTZ W A,DRUCKMūLLER H J.A fast digitalradon transform:an efficient means for evaluatingthe Hough transform[J].Pattern Recognition,1996,29:711-718.
[10]章毓晋.图象处理和分析[M].北京:清华大学出版社,1999.
[11]YANG Hua-chao,DENG Ka-zhong,ZHANG Shu-bi,et al.Non-metric CCD camera calibration algo-rithm in a digital photogrammetry system[J].Jour-nal of China University of Mining&Technology,2006,16(2):119-122.
[2]李玉良.机车信号监控技术及其应用[J].中国矿业大学学报,1997,26(4):54-56.LI Yu-liang.Locomotive signal monitoring technolo-gy and Its application[J].Journal of China Universityof Mining&Technology,1997,26(4):54-56.
[3]朱华,葛世荣,左明,等.矿车红外探测报警系统研制[J].中国矿业大学学报,2002,31(2):166-170.ZHU Hua,GE Shi-rong,ZUO Ming,et al.Devel-opment of infrared detecting and warning system forbody targets in mine cars[J].Journal of China Uni-versity of Mining&Technology,2002,31(2):166-170.
[4]孙继平,关永,张杰.DSP极低码率的矿井远程视频监控系统[J].西安科技学院学报,2003,23(3):283-286.SUN Ji-ping,GUAN Yong,ZHANG Jie.The ex-tremely low rated long-range video supervision sys-tem based on DSP[J].Journal of Xi’an University ofScience and Technology,2003,23(3):283-286.
[5]关永.基于红外探测技术的矿井远程视频监控系统[D].北京:中国矿业大学机电与信息工程学院,2004.
[6]黄新武,吴律,牛滨华.基于抛物线拉东变换的地震道重构[J].中国矿业大学学报,2003,32(5):534-539.HUANG Xin-wu,WU Lu,NIU Bin-hua.Recon-struction of seismic traces by parabolic Radon trans-form[J].Journal of China University of Mining&Technology,2003,32(5):534-539.
[7]TABBONE S,WENDLING L.Recognition of sym-bols in grey level line-drawings from an adaptation ofthe Radon transform[J].Pattern Recognition,2004(2):570-573.
[8]TOFT P A.Using the generalized Radon transformfor detection of curves in noisy images[J].Acous-tics,Speech,and Signal Processing,1996(4):2219-2222.
[9]GōTZ W A,DRUCKMūLLER H J.A fast digitalradon transform:an efficient means for evaluatingthe Hough transform[J].Pattern Recognition,1996,29:711-718.
[10]章毓晋.图象处理和分析[M].北京:清华大学出版社,1999.
[11]YANG Hua-chao,DENG Ka-zhong,ZHANG Shu-bi,et al.Non-metric CCD camera calibration algo-rithm in a digital photogrammetry system[J].Jour-nal of China University of Mining&Technology,2006,16(2):119-122.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心