基于视频图像的车辆实时检测系统
|
摘要
针对道路车辆的实时监测系统检测效率和精度较低的问题,设计一套实时监测系统。对视频图形进行灰度化、滤波及增强,并分割出统计区域。在分割出的图像中,设计统计众值法构建背景模型,设置阈值获得前景图像,采用Canny算子检测车辆边缘,将前景图像与车辆边缘叠加进行形态学运算以获取车流量统计结果。实验结果表明,该系统准确率高达98. 45%,能够满足智能交通系统对检测效率和精度的需求。
To solve the problem that the detection efficiency and accuracy of the real-time monitoring system for vehicle are low,a real-time vehicle detection system is designed. First,the system grayscales,filters,and enhances the video images to segment the statistical regions. Then,in the segmentation image,the statistical mode method is designed to construct the background model and the Canny operator is used to detect the vehicle edge. At last,the foreground and vehicle edge images are superimposed for morphological operation to obtain the vehicle counting. Experimental results show that the accuracy of the system is up to 98. 45%,which can meet the needs of intelligent transportation systems for detection efficiency and accuracy.
To solve the problem that the detection efficiency and accuracy of the real-time monitoring system for vehicle are low,a real-time vehicle detection system is designed. First,the system grayscales,filters,and enhances the video images to segment the statistical regions. Then,in the segmentation image,the statistical mode method is designed to construct the background model and the Canny operator is used to detect the vehicle edge. At last,the foreground and vehicle edge images are superimposed for morphological operation to obtain the vehicle counting. Experimental results show that the accuracy of the system is up to 98. 45%,which can meet the needs of intelligent transportation systems for detection efficiency and accuracy.
引文
[1]杨东凯,吴今培,张其善.智能交通系统(ITS)的发展及其模型化研究[J].北京航空航天大学学报,2000,26(1):22-25.
[2] REN J,ASTHEIMER P,FENG D D. Real-time moving object detection under complex background[C]//Proceedings of the3rd IEEE International Symposium on Image and Signal Processing and Analysis. Washington D. C.,USA:IEEE Press,2003:662-667.
[3] KAMIO S,SAKAUCHI M. Illumination invariant and occlusion robust vehicle tracking by spatio temporal M RF model[C]//Proceedings of the 9th World Congress on Intelligent Transport Systems. Chieago,USA:[s. n.],2002.
[4] KIM Z, MALIK J. Fast vehicle detection with probabilistic feature grouping and its application to vehicle tracking[C]//Proceedings of the 9th IEEE International Conference on Computer Vision.Washington D. C.,USA:IEEE Press,2003:524-531.
[5] MAGEE D. Tracking multiple vehicles using foreground background and motion models[J]. Image and Vision Computing,2004,22(2):143-145.
[6] PARAGIOS N,DERICHE R. Geodesic active regions:a new paradigm to deal w ith frame partition problems in computer vision[J]. Journal of Visual Communication and Image Representation,2002,13(1/2):249-268.
[7]徐勇军,高梅国,毛二可.智能运输系统中的雷达车辆检测器[J].北京理工大学学报,2001,21(2):256-259.
[8]陈振学,汪国有,刘成云.基于计算机视觉的汽车流量检测统计[J].华中科技大学学报(自然科学版),2006,34(5):46-49.
[9]王洪建,李志敏.基于视频图像的车辆流量实时检测系统[J].光学精密工程,2005,13(增刊):222-226.
[10]檀甲甲,张建秋.实时采集道路车流量信息的视频新方法[J].仪器仪表学报,2008,29(1):158-166.
[11]张桂梅,孙晓旭,陈彬彬,等.结合分数阶微分和Canny算子的边缘检测[J].中国图象图形学报,2016,21(8):1028-1038.
[12]张鹏,黄毅,阮雅端,等.基于稀疏特征的交通流视频检测算法[J].南京大学学报(自然科学版),2015,51(2):264-270.
[13]陈银,任侃,顾国华,等.基于改进的单高斯背景模型运动目标检测算法[J].中国激光,2014,41(11):245-253.
[14]张立国,杨瑾,李晶,等.基于小波包和数学形态学结合的图像特征提取方法[J].仪器仪表学报,2010,31(10):2285-2290.
[15]常志国,李晶,胡云鹭,等.基于视频的车流量统计算法[J].计算机系统应用,2016,25(7):187-191.
[16]齐美彬,鲜柯,蒋建国,等.一种基于车辆遮挡模型的车流量统计算法[J].仪器仪表学报,2010,31(6):1335-1341.
[17] FELZENSZWALB P F,SCHWARTZ J D. Hierarchical matching of deformable shapes[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C.,USA:IEEE Press,2007:1-8.
[18]晏建洋,吴建星.基于LabVIEW和MATLAB的矿山微震信号小波分析与研究[J].安全与环境工程,2016,23(3):125-128.
[19]徐峰,刘婷薇,李平,等.基于LabVIEW与MATLAB混合编程的手势识别系统[J].电子设计工程,2017,25(8):32-36.
[2] REN J,ASTHEIMER P,FENG D D. Real-time moving object detection under complex background[C]//Proceedings of the3rd IEEE International Symposium on Image and Signal Processing and Analysis. Washington D. C.,USA:IEEE Press,2003:662-667.
[3] KAMIO S,SAKAUCHI M. Illumination invariant and occlusion robust vehicle tracking by spatio temporal M RF model[C]//Proceedings of the 9th World Congress on Intelligent Transport Systems. Chieago,USA:[s. n.],2002.
[4] KIM Z, MALIK J. Fast vehicle detection with probabilistic feature grouping and its application to vehicle tracking[C]//Proceedings of the 9th IEEE International Conference on Computer Vision.Washington D. C.,USA:IEEE Press,2003:524-531.
[5] MAGEE D. Tracking multiple vehicles using foreground background and motion models[J]. Image and Vision Computing,2004,22(2):143-145.
[6] PARAGIOS N,DERICHE R. Geodesic active regions:a new paradigm to deal w ith frame partition problems in computer vision[J]. Journal of Visual Communication and Image Representation,2002,13(1/2):249-268.
[7]徐勇军,高梅国,毛二可.智能运输系统中的雷达车辆检测器[J].北京理工大学学报,2001,21(2):256-259.
[8]陈振学,汪国有,刘成云.基于计算机视觉的汽车流量检测统计[J].华中科技大学学报(自然科学版),2006,34(5):46-49.
[9]王洪建,李志敏.基于视频图像的车辆流量实时检测系统[J].光学精密工程,2005,13(增刊):222-226.
[10]檀甲甲,张建秋.实时采集道路车流量信息的视频新方法[J].仪器仪表学报,2008,29(1):158-166.
[11]张桂梅,孙晓旭,陈彬彬,等.结合分数阶微分和Canny算子的边缘检测[J].中国图象图形学报,2016,21(8):1028-1038.
[12]张鹏,黄毅,阮雅端,等.基于稀疏特征的交通流视频检测算法[J].南京大学学报(自然科学版),2015,51(2):264-270.
[13]陈银,任侃,顾国华,等.基于改进的单高斯背景模型运动目标检测算法[J].中国激光,2014,41(11):245-253.
[14]张立国,杨瑾,李晶,等.基于小波包和数学形态学结合的图像特征提取方法[J].仪器仪表学报,2010,31(10):2285-2290.
[15]常志国,李晶,胡云鹭,等.基于视频的车流量统计算法[J].计算机系统应用,2016,25(7):187-191.
[16]齐美彬,鲜柯,蒋建国,等.一种基于车辆遮挡模型的车流量统计算法[J].仪器仪表学报,2010,31(6):1335-1341.
[17] FELZENSZWALB P F,SCHWARTZ J D. Hierarchical matching of deformable shapes[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C.,USA:IEEE Press,2007:1-8.
[18]晏建洋,吴建星.基于LabVIEW和MATLAB的矿山微震信号小波分析与研究[J].安全与环境工程,2016,23(3):125-128.
[19]徐峰,刘婷薇,李平,等.基于LabVIEW与MATLAB混合编程的手势识别系统[J].电子设计工程,2017,25(8):32-36.