基于移动车牌识别的套牌车辆快速检测技术研究与实现
|
摘要
通过在重要场所部署视频监控设备,不仅可以实时获得安全场所的现场状态或备份取证,还具有安全可靠、节省人力资源的优点。但是纯粹的视频监控系统有明显的不足,因为监控设备获取的是运动的连续数据,其中包含大量的无用信息,典型的如交通视频监控系统。在交通视频监控系统中获得的是成千上万的车辆运行信息,如何组织与利用这些信息并从其中提取准确数据是一项艰巨的工作,如果仅仅依靠人工的方式进行提取,不仅费时费力,而且获得的数据质量不高。为此把监控技术与视频识别技术结合起来自动提取与组织关键数据是实现自动化监控,提高管理效率的重要途径。然而,视频识别技术是视频处理的难点问题之
因为视频获得的是人眼可以识别的表示数据,与计算机所采用的表示方法差别很大,开发通用的计算机视觉系统是目前尚未攻克的难题。但是通过研究特定的场景进而开发以特定目标为对象的专用视频识别系统来满足特定的应用场合,已经成为当前研究的热点,这其中最为典型的是汽车牌照识别技术。
本文结合汽车牌照识别技术的研究现状,将视频识别技术与GIS技术相结合,主要完成了以下工作：
1)提出利用套牌车辆不能同时出现在同一地理位置的特点,通过对车辆牌照以及位置分析进行套牌车辆实时检测的思路,并以该思路为基础进行了套牌车辆检测系统的设计。
2)开发了一种结合地理位置启发式信息的汽车牌照的快速识别算法。
3)提出了两种能够在GIS系统中快速寻找两点之间最短路径的算法。
4)以C/S与B/S相结合的方式对套牌车辆实时检测系统进行了初步实现,验证了本文设计的正确性与有效性。
5)最后以基础功能测试以及完整的实验环境仿真的方式对系统进行了最终测试。
The deployed Video Surveillance Equipment at important place could supply live state, backup information, more safety and also save in manpower. Data got from the Video Surveillance contains much useless information, such as Traffic Surveillance System. Our mission is to get the information of running cars from the data flow, which cost great manpower. We combine Monitoring technology and Video recognition technology to automate monitoring the traffic flow. But, video recognition technology is one of the most difficult problems in field of computer science, because of the huge difference in data form between with human and computer can identify. Currently, we can only develop some video recognition applications limited in some special conditions. The technology of vehicle license plate recognition is one of them.
In our research, we propose a vehicle license plate recognition method to the specifically situation of traffics. According to recent research of vehicle license plate recognition, we combine video recognition and technology of GIS, doing the main works as bellow:
1) We propose a method of detecting false vehicle license in real time, which takes the point that false vehicle license will not appear at the same location at the same time. A false vehicle license detecting system also be designed to realizes the method.
2) Combining the heuristic method about geography location, we designed a fast algorithm to recognize vehicle license in video data.
3) We also design two algorithms to calculate the shortest path between two points on the map.
4) We combine the C/S and B/S modes to design the false license detect system, and verify the correction of our programming.
5) At last, we examine the system by basic function testing and real circumstance simulation.
因为视频获得的是人眼可以识别的表示数据,与计算机所采用的表示方法差别很大,开发通用的计算机视觉系统是目前尚未攻克的难题。但是通过研究特定的场景进而开发以特定目标为对象的专用视频识别系统来满足特定的应用场合,已经成为当前研究的热点,这其中最为典型的是汽车牌照识别技术。
本文结合汽车牌照识别技术的研究现状,将视频识别技术与GIS技术相结合,主要完成了以下工作：
1)提出利用套牌车辆不能同时出现在同一地理位置的特点,通过对车辆牌照以及位置分析进行套牌车辆实时检测的思路,并以该思路为基础进行了套牌车辆检测系统的设计。
2)开发了一种结合地理位置启发式信息的汽车牌照的快速识别算法。
3)提出了两种能够在GIS系统中快速寻找两点之间最短路径的算法。
4)以C/S与B/S相结合的方式对套牌车辆实时检测系统进行了初步实现,验证了本文设计的正确性与有效性。
5)最后以基础功能测试以及完整的实验环境仿真的方式对系统进行了最终测试。
The deployed Video Surveillance Equipment at important place could supply live state, backup information, more safety and also save in manpower. Data got from the Video Surveillance contains much useless information, such as Traffic Surveillance System. Our mission is to get the information of running cars from the data flow, which cost great manpower. We combine Monitoring technology and Video recognition technology to automate monitoring the traffic flow. But, video recognition technology is one of the most difficult problems in field of computer science, because of the huge difference in data form between with human and computer can identify. Currently, we can only develop some video recognition applications limited in some special conditions. The technology of vehicle license plate recognition is one of them.
In our research, we propose a vehicle license plate recognition method to the specifically situation of traffics. According to recent research of vehicle license plate recognition, we combine video recognition and technology of GIS, doing the main works as bellow:
1) We propose a method of detecting false vehicle license in real time, which takes the point that false vehicle license will not appear at the same location at the same time. A false vehicle license detecting system also be designed to realizes the method.
2) Combining the heuristic method about geography location, we designed a fast algorithm to recognize vehicle license in video data.
3) We also design two algorithms to calculate the shortest path between two points on the map.
4) We combine the C/S and B/S modes to design the false license detect system, and verify the correction of our programming.
5) At last, we examine the system by basic function testing and real circumstance simulation.
引文
[1]中华人民共和国道路交通安全法.2007.
[2]徐鑫华.浅谈套牌车产生的原因危害及对策.安全与健康,下半月,2007.
[3]王镜,王庆辉,王江.假牌、套牌车非法营运的经济博弈分析.物流技术2007年第26卷第12期,2007.
[4]靳引利,王建平.基于车流信息采集的套牌车辆治理方法研究.中国水运(学术版),2007年09期.
[5]唐洪明.无牌车套牌车社会的危害.http://xcnews.zjol.com.cn/xcnews/system/2007/09/10/000415228.shtml,20072007-09-10.
[6]徐鑫华,浅谈“套牌车”产生的原因、危害及对策.安全与健康,2007年10期.
[7]卢晓春,周欣,蒋欣荣,潘薇,王峰.基于网格化监控的套牌车检测系统.计算机应用,2009年10期.
[8]东莞阳光网.套牌车存在的危害.http://www.sun0769.com/subject/2008/taopaiche/taopaiche2/t20090106_443583.htm,2009.
[9]东莞阳光网.东莞警方严打套牌车.http://www.sun0769.com/subject/2008/taopaiche/,2009.
[10]凌海市公安局.识别套牌车四法.http://www.jzlhsga.gov.cn/html/news_305.htm,20092009-10-15.
[11]Tuite D.视频处理技术为运动图像带来新的意义.Electronic Design,20062006-12-01.
[12]云长江,齐驰.基于牌照识别的公安综合业务管理系统.仪器仪表用户2008年2期,2008.
[13]姚颖东.车牌识别技术在城市交通管理中的应用测试.市政设施管理,2008.
[14]杜圣康,毛力.汽车牌照识别系统的设计与实现.电脑学习,2008.
[15]中国新闻网.全国机动车保有量达到1.8亿辆.http://www.chinanews.com.cn/gn/news/2009/09-16/1870170.shtml,2009.
[16]Haralick R M, Lee J S. The Facet Approach to Optical Flow. Image Understating Workshop, pp. 74-83,1984.
[17]Horprasert T, Harwood D, Davis L S. A Statistical Approach for Real-time Robust Background Subtraction and Shadow Detection, presented at IEEE ICCV'99 Frame-Rate Workshop,1999.
[18]Abramczuk T. A Microcomputer based TV Detector for Road Traffic, ymposium on Road Research Program T, vol.3, pp.145-147,1984.
[19]韩永强,李世祥.汽车牌照子图像的定位算法.微型电脑应用,pp.14-16,1999.
[20]李宏升.利用牌照识别技术的停车场安全防盗系统.计算机系统应用,pp.14-16,1999.
[21]郁梅.基于视觉的车辆牌照检测.计算机应用研究,pp.65-67,1999.
[22]郭军.发展中的文字识别理论与技术.电子学报,vol.23, pp.184-187,1998.
[23]王年.人工神经网络在公路车辆管理中的应用.电子技术应用,pp.11-12,1998.
[24]彭小桢,郝福珍,鄢楚平.基于B/S的视频监控系统客户端的设计与实现.计算机工程与应用,2007.
[25]张石,赵百超,王飞,et al.具有远程监控功能的视频服务器设计.单片机与嵌入式应用,2009.
[26]张晖,董育宁.基于视频的车辆检测算法综述.南京邮电大学学报,vol.27,pp.88-94,2007.
[27]Otsu N. A threshold selection method from gray-level histogram. IEEE Trans. SMC-9, pp.62-66,, 1979.
[28]殷蔚明,王典洪.Otsu法的多阈值推广及其快速实现.中国体视学与图像分析,vol.9, pp.219-223,2004.
[29]刘欣,杨红培.基于灰度直方图与投影的数字图像信息组织与检索方法研究.许昌学院学报,vol.26, pp.86-90,2007.
[30]余棉水,黎绍发,陈智斌.车牌自动识别技术的研究.机电工程技术,vol.32, pp.55-56,2003.
[31]魏武,张起森,王明俊,et al一种基于模板匹配的车牌识别方法.中国公路学报,vol.14, pp. 104-106,2001.
[32]Google地图. http://ditu.google.cn/maps?hl=zh-CN&tab=wl,20052005-09-06.
[33]城市吧地图. http://www.city8.com,2009.
[34]Z F B. Three Fastest Shortest Path Algorithms on Real Road Networks. Journal of Geographic Information and Decision Analysis,19971.
[35]耿春雨,任东风.MapInfo中道路拓扑与最优路径的实现.http://www.paper.edu.cn,中国科技论文在线,2008.
[36]李雪瑞,吕志平,赵冬青.基于MapX的道路拓扑与最短路径分析.地矿测绘20(3)：11-13,2004.
[37]Zhan F B, San Marcos. A Comparison Between Label-Setting and
Label-Correcting Algorithms for Computing
One-to-One Shortest Paths. Journal of Geographic Information and Decision Analysis 4(2):1-11,2000.
[38]百度公司.百度地图.http://map.baidu.com,20052005-09-26.
[39]百度地理驿站.关于地球表面两点最短线路的确定及距离计算.http://hi.baidu.com/geok/blog/item/5332bfde09b45f51ccbflalf.html/cmtid/c09cd53322e4ad4fad4b5 fdd,2009.
[40]张海潮.球面三角形的AAA定理.Inst. Math. Academia Sinica,20062006-11-15.
[41]尹德安.视频采集与基于H.264标准编码压缩系统的研究.中国海洋大学硕士研究生学位论文,20062006-05-01.
[42]Association N M E. NMEA 0183 standard. http://www.nmea.org/content/nmea_standards/nmea_083_v_400.asp.
[43]Agency N G. Office of GEOINT Sciences:World Geodetic System 1984 (WGS 84). http://earth-info.nga.mil/GandG/wgs84/,1984.
[44]彭玮.基于RTP的流媒体实时传输机制研究与实现.昆明理工大学硕士学位论文,20052005-04-01.
[45]Schulzrinne H, Casner S, Design P, et al. RFC3550-RTP:A Transport Protocol for Real-Time Applications.20032003-06-01.
[46]Jacobson V, Frederick R, Schulzrinne H, et al. RFC 1889-RTP:A Transport Protocol for Real-Time Applications.19961996-01-01.
[47]Gis足迹.VC6.0+MapX编程总结.http://www.gisfoot.com/post/19.html,20072007-09-26.
[48]System M M O H. The MapX Object Model Diagram.20072007-09-26.
[49]Liu J.组件式GIS与MapX. http://www.mygis.com.cn/articles/04-802-802.htm,20042004-02-10.
[50]胡耀锋.基于Mapx的广州市电子地图的制作.http://www.gissky.com/Gis/ShowArticle.asp?SID=12&ID=925,20042004-09-06.
[51]张婧华.MapX研究——MapX核心技术剖析.开源盛世-源代码下载网http://www.vscodes.com/article/show.asp?id=454,20052005-05-13.第66页
[2]徐鑫华.浅谈套牌车产生的原因危害及对策.安全与健康,下半月,2007.
[3]王镜,王庆辉,王江.假牌、套牌车非法营运的经济博弈分析.物流技术2007年第26卷第12期,2007.
[4]靳引利,王建平.基于车流信息采集的套牌车辆治理方法研究.中国水运(学术版),2007年09期.
[5]唐洪明.无牌车套牌车社会的危害.http://xcnews.zjol.com.cn/xcnews/system/2007/09/10/000415228.shtml,20072007-09-10.
[6]徐鑫华,浅谈“套牌车”产生的原因、危害及对策.安全与健康,2007年10期.
[7]卢晓春,周欣,蒋欣荣,潘薇,王峰.基于网格化监控的套牌车检测系统.计算机应用,2009年10期.
[8]东莞阳光网.套牌车存在的危害.http://www.sun0769.com/subject/2008/taopaiche/taopaiche2/t20090106_443583.htm,2009.
[9]东莞阳光网.东莞警方严打套牌车.http://www.sun0769.com/subject/2008/taopaiche/,2009.
[10]凌海市公安局.识别套牌车四法.http://www.jzlhsga.gov.cn/html/news_305.htm,20092009-10-15.
[11]Tuite D.视频处理技术为运动图像带来新的意义.Electronic Design,20062006-12-01.
[12]云长江,齐驰.基于牌照识别的公安综合业务管理系统.仪器仪表用户2008年2期,2008.
[13]姚颖东.车牌识别技术在城市交通管理中的应用测试.市政设施管理,2008.
[14]杜圣康,毛力.汽车牌照识别系统的设计与实现.电脑学习,2008.
[15]中国新闻网.全国机动车保有量达到1.8亿辆.http://www.chinanews.com.cn/gn/news/2009/09-16/1870170.shtml,2009.
[16]Haralick R M, Lee J S. The Facet Approach to Optical Flow. Image Understating Workshop, pp. 74-83,1984.
[17]Horprasert T, Harwood D, Davis L S. A Statistical Approach for Real-time Robust Background Subtraction and Shadow Detection, presented at IEEE ICCV'99 Frame-Rate Workshop,1999.
[18]Abramczuk T. A Microcomputer based TV Detector for Road Traffic, ymposium on Road Research Program T, vol.3, pp.145-147,1984.
[19]韩永强,李世祥.汽车牌照子图像的定位算法.微型电脑应用,pp.14-16,1999.
[20]李宏升.利用牌照识别技术的停车场安全防盗系统.计算机系统应用,pp.14-16,1999.
[21]郁梅.基于视觉的车辆牌照检测.计算机应用研究,pp.65-67,1999.
[22]郭军.发展中的文字识别理论与技术.电子学报,vol.23, pp.184-187,1998.
[23]王年.人工神经网络在公路车辆管理中的应用.电子技术应用,pp.11-12,1998.
[24]彭小桢,郝福珍,鄢楚平.基于B/S的视频监控系统客户端的设计与实现.计算机工程与应用,2007.
[25]张石,赵百超,王飞,et al.具有远程监控功能的视频服务器设计.单片机与嵌入式应用,2009.
[26]张晖,董育宁.基于视频的车辆检测算法综述.南京邮电大学学报,vol.27,pp.88-94,2007.
[27]Otsu N. A threshold selection method from gray-level histogram. IEEE Trans. SMC-9, pp.62-66,, 1979.
[28]殷蔚明,王典洪.Otsu法的多阈值推广及其快速实现.中国体视学与图像分析,vol.9, pp.219-223,2004.
[29]刘欣,杨红培.基于灰度直方图与投影的数字图像信息组织与检索方法研究.许昌学院学报,vol.26, pp.86-90,2007.
[30]余棉水,黎绍发,陈智斌.车牌自动识别技术的研究.机电工程技术,vol.32, pp.55-56,2003.
[31]魏武,张起森,王明俊,et al一种基于模板匹配的车牌识别方法.中国公路学报,vol.14, pp. 104-106,2001.
[32]Google地图. http://ditu.google.cn/maps?hl=zh-CN&tab=wl,20052005-09-06.
[33]城市吧地图. http://www.city8.com,2009.
[34]Z F B. Three Fastest Shortest Path Algorithms on Real Road Networks. Journal of Geographic Information and Decision Analysis,19971.
[35]耿春雨,任东风.MapInfo中道路拓扑与最优路径的实现.http://www.paper.edu.cn,中国科技论文在线,2008.
[36]李雪瑞,吕志平,赵冬青.基于MapX的道路拓扑与最短路径分析.地矿测绘20(3)：11-13,2004.
[37]Zhan F B, San Marcos. A Comparison Between Label-Setting and
Label-Correcting Algorithms for Computing
One-to-One Shortest Paths. Journal of Geographic Information and Decision Analysis 4(2):1-11,2000.
[38]百度公司.百度地图.http://map.baidu.com,20052005-09-26.
[39]百度地理驿站.关于地球表面两点最短线路的确定及距离计算.http://hi.baidu.com/geok/blog/item/5332bfde09b45f51ccbflalf.html/cmtid/c09cd53322e4ad4fad4b5 fdd,2009.
[40]张海潮.球面三角形的AAA定理.Inst. Math. Academia Sinica,20062006-11-15.
[41]尹德安.视频采集与基于H.264标准编码压缩系统的研究.中国海洋大学硕士研究生学位论文,20062006-05-01.
[42]Association N M E. NMEA 0183 standard. http://www.nmea.org/content/nmea_standards/nmea_083_v_400.asp.
[43]Agency N G. Office of GEOINT Sciences:World Geodetic System 1984 (WGS 84). http://earth-info.nga.mil/GandG/wgs84/,1984.
[44]彭玮.基于RTP的流媒体实时传输机制研究与实现.昆明理工大学硕士学位论文,20052005-04-01.
[45]Schulzrinne H, Casner S, Design P, et al. RFC3550-RTP:A Transport Protocol for Real-Time Applications.20032003-06-01.
[46]Jacobson V, Frederick R, Schulzrinne H, et al. RFC 1889-RTP:A Transport Protocol for Real-Time Applications.19961996-01-01.
[47]Gis足迹.VC6.0+MapX编程总结.http://www.gisfoot.com/post/19.html,20072007-09-26.
[48]System M M O H. The MapX Object Model Diagram.20072007-09-26.
[49]Liu J.组件式GIS与MapX. http://www.mygis.com.cn/articles/04-802-802.htm,20042004-02-10.
[50]胡耀锋.基于Mapx的广州市电子地图的制作.http://www.gissky.com/Gis/ShowArticle.asp?SID=12&ID=925,20042004-09-06.
[51]张婧华.MapX研究——MapX核心技术剖析.开源盛世-源代码下载网http://www.vscodes.com/article/show.asp?id=454,20052005-05-13.第66页