摘要
实时交通流数据的采集在智能交通系统中起着重要的作用。交通流检测有多种方式,而基于图像处理的视频检测方式近年发展很快,它具有大区域检测、设置灵活等优越性,已成为智能交通系统的一个研究热点。
本文致力于研究一种灵活可靠的视频交通流检测系统,将智能传感器的概念引入视频检测中,以提高检测效率。车辆的检测基于车道,在每个车道设置两组虚拟检测线(每组虚拟检测线包括横向和纵向虚拟检测线)来检测交通流参数,虚拟检测线的作用类似于电磁感应线圈。系统通过对视频虚拟检测线的预处理将二维的数字图像转化成一维的检测信号,减小了运算量,降低了运算负荷。该方法的特点是处理运算的图像区域小,避开了在二维图像空间中进行车辆跟踪。
通过大量的实验和分析,论文完成了复杂道路交通场景下的车辆检测和车速测量算法的开发工作,并利用Matlab进行了仿真和验证。论文的主要工作包括:
(1)改进了虚拟检测线的设置,每组虚拟检测线由横向和纵向两部分组成,在横向和纵向虚拟检测线上分别通过帧间差分和背景差分进行特征信号的提取。在分析虚拟检测线位置和大小对输出信号的影响基础上,提出虚拟检测线设置中应遵循的一些原则。
(2)采用形态除噪方法、Kirsch边缘检测方法、基于Kalman的背景更新方法以及基于结构单元的阴影去除方法进行图像预处理。
(3)在交通流信息采集系统中为了精确地在一维信号中跟踪车辆,系统引入了正负信任帧、正负信任段等重要参数及奖惩策略,同时为了提高速度测量的精度和减小计算量,系统利用车头分别进入上下两横向检测线时候的特征信号求取车辆的速度。
(4)利用基于ARM-Linux的嵌入式平台完成交通流检测原型系统的设计,验证算法的实时性和方便性。
实验证明本文提出的基于视频的交通流信息采集方法具有一定的稳健性,实时性,方便性和鲁棒性。
The collection of real-time traffic data plays a critical role in intelligent transportation system.Technological innovations have given rise to different types of traffic detectors. Meanwhile,a promising approach,video-based measurement system,has developed quickly.Since it has many advantages,for instance,wider-area detection and superior flexibility,many researches have been done in this area.
In this paper,in order to develop a flexible and reliable system for detecting the traffic parameters through image sequences,the intelligent image sensors is present to improve detecting efficiency.The vehicle detection is based on the roadway,which sets two virtual loops(every virtual loop contains a transverse area and a lengthways area),like the inductive loop sensor,to detect their traffic flow parameters.The key idea of the system is converting the two-dimensional image data to one-dimensional digital temporal signals by the virtual loop,which reduces computation load.
Vehicle detection and volume measurement algorithms have been accomplished through a large number of experiments and plentiful analysis in the traffic scene that can be simple or complicated.And algorithms have been emulated and testified by MATLAB.Contribution in this dissertation as follow:
(1) The virtual-loop set in the image has been improved,which contains a transverse area and a lengthways area.Each virtual-loop's output signals mainly derive from the pixel difference between consecutive image frames within the transverse virtual-loop area and the pixel cost of background subtraction image within the lengthways virtual-loop area.When the virtual-loop was set,some rules about position and size of the virtual-loop have been present.
(2) In the previous management of image,the mathematical morphology method,the Kirsch edge detection algorithm,the Kalman algorithm selected to updated the background within the lengthways virtual-loop area and the shadow eliminating method based on structural elements were used.
(3) In order to tracking the vehicle more inerrably,system uses some important parameters such as positively and negatively credible frame、positively、negatively credible segment and so on,and an effective algorithm(punishment and reward algorithm) was present.In order to measure the volume of vehicles more inerrably and easily,the output signal produced when the head of the vehicles drove into the two transverse virtual-loop area in one lane was used.
(4) A prototype system was also designed on embedded arm-linux and proved the system was real timely and convenient.
Experiments have proved that the method of traffic information detection based on video was simple and available,real timely,convenient,with good tolerance and applicability.
引文
[1]史新宏,蔡伯根,穆建成.智能交通系统的发展[J].北方交通大学学报.2002,26(1):29-34.
[2]《中国智能运输系统体系框架》专题组.中国智能运输系统体系框架[M].北京:人民交通出版社,2003.
[3]尹朝征.基于视频虚拟线圈的交通流参数检测[D].清华大学硕士学位论文.2002.
[4]李绪龙.基于图像处理技术的视频交通流信息采集系统研究[D].长安大学硕士学位论文.2003.
[5]刘智勇.智能交通控制理论及其应用[M].北京:科学出版社,2003.
[6]姜紫峰,谭光莉.车辆检测器的进展[J].公路交通科技.1996,13(1):62-65.
[7]阙大顺.车辆检测器及其发展研究[J].交通与计算机.1999,17(2):38-41.
[8]陆化普.智能运输系统[M].北京:人民交通出版社,2002.
[9]Matsuo T.,Kaneko Y.,Matano M,.Introduction of Intelligent Vehicle Detection Sensors[J].1999IEEE/IEEJ/JSAI International Conference,1999:709-713.
[10]夏文龙.基于计算机视觉的汽车流量检测研究[D].四川大学硕士学位论文.2003.
[11]徐晓夏,陈泉林.视频交通监控系统[J].现代电子技术.2003,(9):72-74.
[12]阮秋琦等译.数字图像处理[M].北京:电子工业出版社,2005.
[13]Rafael C.GONZALEZ,Richard E.WOODS.数字图像处理(第二版)[M].北京电子工业出版社,2003.
[14]Jean J.Labrosse.Emdedded systems building blocks[M].R&D Books,January 12,1999.
[15]杨枝灵,王开.Visual C++数字图像获取、处理及初中应用[M].北京人民邮电出版社,2003.
[16]Guo D.,Hwang Y.C.,Adrian Y.C.L.,Laugier C.,Traffic monitoring using short-long term background memory[J].The IEEE 5 International Conference on Intelligent Transportation Systems,2002:124-129.
[17]Cucchiara R.,Piccardi M.,Prati A.,Detecting moving objects,ghosts,and shadows in video streams[J].IEEE transactions on pattern analysis and machine intelligence.2003,(25):1337-1342.
[18]刘国衡.图像序列的目标检测[J].计算机工程及应用.1997.8:26-29.
[19]王栓.基于差分图像的多运动目标的检测与跟踪[J].中国图像图形学报.1999.4(6):470-475.
[20]尚裴,郭志芬.高速公路汽车目标检测[J].北京理工大学学报.1997,17(6):759-754.
[21]武想益,郑依展等.视频交通流检测演示系统[J].计算机工程,2003,29(21):151-153.
[22]王夏黎,周明全等.交通流视频检测系统的设计与实现[J].西北大学学报(自然科学版),2004,26(12):207-210.
[23]彭仁明,贺乔林等.基于视频的车流量检测(自然科学版)[J].西华师范大学学报,2004,25(4).404-408.
[24]Yang-Ju.Improvement of Background Update Method for Image Detector[J].5th Word Congress on Intelligent Transport Systems.1998:182-188.
[25]王俊杰,黄心汉.一种对图像进行快速二值化处理的方法[J].电子技术应用.1998,No.10:16-17.
[26]胡小锋,赵辉.Visual C++/MATLAB图像处理与识别应用案例精选[M].北京:人民邮电出版社,2003.
[27]张玲,叶海炳,何伟.一种基于边缘信息的改进车辆检测方法[J].重庆大学学报(自然科学版),2001,27(11):56-58.
[28]郁梅,蒋刚毅等.基于路面标记的车辆检测和计数[J].仪器仪表学报,2002,23(4):386-390.
[29]向世明.Visual C++数字图像与图形处理[M].北京:电子工业出版社,2003.
[30]陈纯.计算机图像处理技术与算法[M].北京:清华大学出版社,2003.
[31]章毓晋.图像工程(上册)-图像处理和分析[M].北京,清华大学出版社,1999.
[32]刘国衡.图像序列的目标检测[J].计算机工程及应用.1997.8:26-29.
[33]徐慧.Visual C++等数字图像实用工程案例精选[M].北京人民邮电出版社,2005.
[34]朱矿军.基于视频虚拟检测线特征的交通流参数检测[D].大连理工大学硕士学位论文.2005.
[35]叶永杰.基于动态图像理解技术的智能交通监控技术[D].浙江工业大学硕士学位论文.2007.
[36]刘昶.基于YUV色彩空间的车辆视频检测算法及实现[D].电子科技大学硕士学位论文.2004.
[37]曹治锦,唐慧明.视频图像中的车辆检测跟踪和分类[J].计算机应用.2004,(3):7-9.
[38]隋哗,马钱.交通监控系统中运动目标分类和跟踪研究[J].信息与控制.2003,32(1):61-64.
[39]马骏.高速公路行车安全距离的分析与研究[J].西安公路交通大学学报,1998,18(4):90-94.
[40]董小明,李怀阳,赵振等.一种创建小型化Linux系统的方法[J].计算机工程,2005,31(9):61-63.
[41]王亚军,刘金刚.Linux运用于嵌入式系统的技术分析[J].计算机应用研究,2005,20(5):102-104.
[42]MinnichR G.Give your bootstrap the boot:using the operating system to boot the operating system[J].Cluster Computing,2004,20(4):439-448.
[43]刘文峰,李程远,李善平.嵌入式Linux操作系统的研究[J],浙江大学学报(工学版),2004,38(4):447:452.
[44]Karim Yaghmour.Building Emdedded Linux Systems[M].USA:O'Reilly Media,April 22,2003.
[45]SchachSR,JinB,WrightDR.Maintain ability of the Linux kernel[J].Software Engineering,2002,149(1):18-23.
[46]魏平,夏良正,王岩.Linux体系结构及嵌入式Linux的移植方法[J].东南大学学报,2004,34(1):126-131.
[47]CheTaiLee,ZengWeiRong,JimMin Lin.Linux kernel customization for embedded systems by using call graph approach[C].Design Automation Conference.San Diego Convention Center 2001,47(3):33-37.
[48]ARM9 Linux实验指导书[M].深圳市英蓓特信息技术有限公司,2005.
[49]http://www.opencv.org.cn/index.php/Cv%E8%BF%90%E5%8A%A8%E5%88%86%E6%9E %90%E4%B8%8E%E5%AF%B9%E8%B1%A1%E8%B7%9F%E8%B8%AA#CvKalman