视频交通流参数检测技术研究
|
摘要
伴随着图像处理、计算机视觉、模式识别以及人工智能等学科的兴起,基于视频的交通参数检测技术已经成为计算机视觉领域新兴的研究方向,具有较高的学术价值和理论研究意义。
本文以路口固定的摄像头所拍摄的视频图像为研究对象,深入研究了图像序列中运动目标检测与跟踪,完成了运动目标的实时检测,并在此基础上采用VC++6.0以及Open CV视觉库图像开发包,开发出了一套完整的视频交通流参数检测系统,取得了良好的实验效果。
运动目标检测算法是视频交通流参数检测的主流算法。本文通过分析背景差法、高斯-贝叶斯建模、帧间差法,边缘检测法等运动目标检测算法的技术特点与优势,提出了一种综合交通流参数检测模型。对于标清视频采用高斯贝叶斯混合模型的策略进行交通流参数的检测与跟踪；而对于高清视频(高清视频像素值为2592×1936或者更大),为解决现有的背景建模方法应用高清图像的车辆检测时存在计算量大的问题,提出一种基于亮度曲线的高清图像自适应背景更新算法,该算法首先设置检测区域,然后对检测区域的背景图像和当前帧图像生成亮度曲线,利用两条亮度曲线,检测车辆的存在与否,解决了高清图像在实际应用中背景建模耗时多,不能完成实时检测的难题。
实验表明,该算法实时性较高,简单有效,可实时完成高清和标清视频的分车道流量统计,对于50万以内像素的视频可以完成车辆跟踪、车速测定、轨迹生成、逆行以及超车的判断等,通过48小时的现场测试,车流量统计的准确率达92%,车速的测定准确率达80%,车道占有率、是否逆行、行驶方向、超速状态的判定已达到了90%。对于高清视频图像可以完成实时车流量检测,其检测准确率达99.2%。
With the advance of image processing、computer vision, pattern recognition、artificial intelligence and other disciplines, traffic parameter detection technology based on video has became the new direction of computer vision field which contains high academic value and significant theory.
In this paper, the video images captured by a fixed camera in intersection were used to be objects for this study. The moving target detection and tracking in image sequence was studied in depth and we completed real-time detection of moving targets and on this basis, using VC+ +6.0 and the Open CV library visual image development kit, then we finished the video traffic flow measurement system and obtain good experimental results.
Video motion detection algorithm is the mainstream of traffic flow parameters detection algorithm. By analyzing the features and advantages of some moving target detection algorithms such as the background subtraction method、Gauss-Bayesian modeling, frame difference method、edge detection algorithms, we propose a Comprehensive Traffic Flow Detection Model algorithm. Use Gaussian mixture model and Bayesian strategy to do traffic flow parameters of the detection and tracking for standard definition video; while for the high-definition video (pixel value of HD video is 2592×1936, or larger), in order to solve the problem of large computation when using the method of background modeling in the high-resolution images, a new algorithm is proposed which is based on intensity curve of high-resolution image in traffic detection. First of all, set the detection areas, then the intensity curves of the background image and current frame are drawn, which are used to detect the presence of vehicles, so it can solve the problem that time-consuming is enormous and vehicles can not be detected in real-time in high-resolution images.
The experiments show that the algorithm is real-time, simple and effective which can accomplish the sub-drive traffic statistics of standard definition video and high-resolution video in real time. This algorithm can accomplish the vehicle tracking、speed determination、trajectory generation、retrograde、overtaking in the video within 500,000 pixels. According to field test of 48 hours, the accuracy of traffic flow statistics reached 92% and the accuracy of speed reached 80%. The accuracy of traffic lane share, retrograde drive detection, driving direction and speeding reached 90%. In the HD video, traffic flow can be detected in real-time and the accuracy is up to 99.2%.
本文以路口固定的摄像头所拍摄的视频图像为研究对象,深入研究了图像序列中运动目标检测与跟踪,完成了运动目标的实时检测,并在此基础上采用VC++6.0以及Open CV视觉库图像开发包,开发出了一套完整的视频交通流参数检测系统,取得了良好的实验效果。
运动目标检测算法是视频交通流参数检测的主流算法。本文通过分析背景差法、高斯-贝叶斯建模、帧间差法,边缘检测法等运动目标检测算法的技术特点与优势,提出了一种综合交通流参数检测模型。对于标清视频采用高斯贝叶斯混合模型的策略进行交通流参数的检测与跟踪；而对于高清视频(高清视频像素值为2592×1936或者更大),为解决现有的背景建模方法应用高清图像的车辆检测时存在计算量大的问题,提出一种基于亮度曲线的高清图像自适应背景更新算法,该算法首先设置检测区域,然后对检测区域的背景图像和当前帧图像生成亮度曲线,利用两条亮度曲线,检测车辆的存在与否,解决了高清图像在实际应用中背景建模耗时多,不能完成实时检测的难题。
实验表明,该算法实时性较高,简单有效,可实时完成高清和标清视频的分车道流量统计,对于50万以内像素的视频可以完成车辆跟踪、车速测定、轨迹生成、逆行以及超车的判断等,通过48小时的现场测试,车流量统计的准确率达92%,车速的测定准确率达80%,车道占有率、是否逆行、行驶方向、超速状态的判定已达到了90%。对于高清视频图像可以完成实时车流量检测,其检测准确率达99.2%。
With the advance of image processing、computer vision, pattern recognition、artificial intelligence and other disciplines, traffic parameter detection technology based on video has became the new direction of computer vision field which contains high academic value and significant theory.
In this paper, the video images captured by a fixed camera in intersection were used to be objects for this study. The moving target detection and tracking in image sequence was studied in depth and we completed real-time detection of moving targets and on this basis, using VC+ +6.0 and the Open CV library visual image development kit, then we finished the video traffic flow measurement system and obtain good experimental results.
Video motion detection algorithm is the mainstream of traffic flow parameters detection algorithm. By analyzing the features and advantages of some moving target detection algorithms such as the background subtraction method、Gauss-Bayesian modeling, frame difference method、edge detection algorithms, we propose a Comprehensive Traffic Flow Detection Model algorithm. Use Gaussian mixture model and Bayesian strategy to do traffic flow parameters of the detection and tracking for standard definition video; while for the high-definition video (pixel value of HD video is 2592×1936, or larger), in order to solve the problem of large computation when using the method of background modeling in the high-resolution images, a new algorithm is proposed which is based on intensity curve of high-resolution image in traffic detection. First of all, set the detection areas, then the intensity curves of the background image and current frame are drawn, which are used to detect the presence of vehicles, so it can solve the problem that time-consuming is enormous and vehicles can not be detected in real-time in high-resolution images.
The experiments show that the algorithm is real-time, simple and effective which can accomplish the sub-drive traffic statistics of standard definition video and high-resolution video in real time. This algorithm can accomplish the vehicle tracking、speed determination、trajectory generation、retrograde、overtaking in the video within 500,000 pixels. According to field test of 48 hours, the accuracy of traffic flow statistics reached 92% and the accuracy of speed reached 80%. The accuracy of traffic lane share, retrograde drive detection, driving direction and speeding reached 90%. In the HD video, traffic flow can be detected in real-time and the accuracy is up to 99.2%.
引文
[11史忠科等.交通控制系统导论.北京：科学出版社,2003.
[2]Simon A, Becker JC.Vehicle guidance for an autonomous vehicle.Proceedings of 1999 IEEE International Conference on Intelligent Transportation System.1999:429-434.
[3]M.M.Trivedi, LMikic and G.Kogut.Distributed video networks for incident detection and managent.Proceeding of IEEE Intl.Conference on Intelligent Transportation Systems, 2000:155-160.
[4]Lin Honwen, Yang Shaoqing, XiaZhijun.A Moving objects Detection Approach for Smart Sensor.Proeeedings of the 5th International Conference on Machine Learing and Cyberneties.Dalian, August,2006.
[5]Rafael M Inigo.Application of machine vision to traffic monitoring and control.IEEE Transactions on Vehicular Technology,1989,38(3):112-122.
[6]Xin Li, XiaoCao Yao.A real-time vehicle detection and tracking System in outer door traffic Scenes.Pattern recognition,2004(2):761-764.
[7]宋新,罗军,王鲁平.基于GVF Snake的运动目标跟踪方法.红外与激光工程，2007,36(2)：226～228.
[8]Stringa, E.and Regazzoni, C.5.Real-time video-shot detection for scene surveillance applications.IEEE Transactions of Image Proeessing,2000,9(1):69-79.
[9]N.Martel-Brisson, A.Zaccarin.Moving Cast Shadow Detection from a Gaussian Mixture Shadow Model.in Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC,2005.
[10]Kmaijo, Y.Matsushita, K.Ikeuehi, M.Sakauehi.Traffic monitoring and accident detection at Intersections.IEEE Transactions on Intelligent Transportation Systems, June,2000, 1(2):108-118.
[11]Birchfield S T,Rangarajan S.Spatiograms versus histograms for region-based tracking.IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR).[S.1]:IEEE,2005:1158-1163.
[12]Bertalmio M, Sapiroo G and Randll G.Morphing active contours.IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(7):733-737.
[13]J.M.Collado, C.Hilario, A.de la Escalera, J.M Armingol.Model Based Vehicle Detection for Intelligent Vehicles.IEEE Intelligent Vehicles Symposium,2004:572-577.
[14]Paragios N and Deriche R.Geodesic active contours and level sets for the detection and tracking of moving objects.IEEE Trans Pattern Analysis and Machine Intelligence,2000, 22(3):266-280.
[15]Low D. GDistinctive Image Features from Scale-Invariant Key-Point. International Journal of Computer Vision,2004,2(60):91-110.
[16]Karaulova I,Hall P and Marshall A.A hierarchical model of dynamics for tracking people with a single video camera.In:British Machine Vision Conference, Bristol, UK, 2000:352-361.
[17]Kumar P, Sengupta K., Lee A..A comparative study of different color spaces for foreground and shadow detection for traffic monitoring system.The IEEE 5th international conference on intelligent transportation systems,Singapore,2002:100-105.
[18]Jun-Wei Hsieh, Wen-Fong Hu, etc.Shadow elimination for effective moving objection by Gaussian shadow modeling.Image and Version computing,2003,21:505-516.
[19]Paul L.Rosin, Efstathios Ioannidis.Evaluation of global image thresholding for change detection[J].Pattern Recognit.Lett,2003,24(14):2345-2356.
[20]LMikic, P.Cosman, G.Kogut and M.M.Trivedi.Moving shadow and object detection in traffic scenes.Proceedings of Intl.Conference on Pattern Recognition,2000,1:321-324.
[21]Dovgard.R.Holographic image representation with reduced aliasing and noise affects IEEE Transactions on Image Processing, July,2004.
[22]史忠科,曹力.交通图像检测与分析.北京：科学出版社,2007：16～19.
[23]Andrea Prati, Ivana Mikie, Costantino Grana, Mohan M.trivedi.Shadow Detection Algorithms for Traffic Flow Analysis:a Comparative Study.2001 IEEE Intelligent Transportation Systems Conference Proceedings-Oakland(CA), USA-August,2001:25-29.
[24]Wu Zeju, Chen Jundong, Liu Yun.Video object segmentation of still background[J]. Journal of Qingdao Univesity of Science and Technology,2004,25(5):457-460.
[25]Bastian Leibe.interleaved Object Categorization and Segmentation, Ph.D.thesis, University of Swiss Federal institute of Technology Zurieh,2004.
[26]CUCCHIARA R, GRANA C, PICCARDI M.Improving shadow suppression in moving object detection with HSV color information.Proc of IEEE Int'l Conference onIntelligent Transp0rtati0n Systems.Oakland:IEEE,2001:334-339.
[27]WangJ.M., Chung.YC., Chang C.L.etal.shadow detection and removal for traffic images.Porceeding of the 2004 IEEE international conference on Networking, sensing & control, Taipei, Taiwan,2004:649-654.
[28]Rita Cuchiara, Costantino Grana, Massioo Pieeardi.Improving Shadow Suppression in Moving object Detection with HSV Color lnformation.In:2001 IEEE Intelligent Transportation Systems Conferenee Proeeedings-oakland(CA), USA-August,2001:25-29.
[29]Harini Veeraraghavan.Osama Masoud, NikolaosP.Papanikolopoulos.Computer Vision Algorithms for Intersections Monitoring IEEE Transactions on Intelligent TransportationSystems,2003,4(2):78-89.
[30]冈萨雷斯.数字图像处理.电子工业出版社,2005：250～385.
[31]陈兵旗,孙明.实用数字图像处理与分析.清华大学出版社,2008：251-308.
[32]Rafacel C.Gonzalez,Richard E.Woods.Digital image processing.Publishing House of Electronics Industry,2005:420-450.
[33]David Beymer, Philip McLauchlan.A Real-time computer vision system for vehicle tracking and traffic surveillance.Transportation Research:Part C,1998,6(4):271-288
[34]李俊韬,张海,范跃祖.复杂交通场景中多运动目标分割算法.北京航空航天大学学报，2006,32(3)：298～230.
[35]刘洋,李玉山,张大朴.基于动态目标建模的粒子滤波视频跟踪算法.光子学报,2008,37(2)：375～379.
[36]M.K.Sing.An intelligent traffic monitoring system for Expressways.Proe.6th Int.Con.On Application of Advanced Technologies in Transportation Engineering. Singapore, June, 2000:28-30.
[37]Ashit Talukder, Larry MatthieS.Real time Deteetion of Moving Objects from Moving Vehicles using Dense Stereo and optical Flow.Proeeedings of 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems.Sep-Oct, Sendal, Japan,2004.
[38]A.Elgammal, R.Duraiswami,D.Harwood, et al.Background and foreground modeling using nonparametric kernel density estimation for visual surveillance.Proceedings of the IEEE, 2002,90(7):1151-1163.
[39]D.R.Magee.Tracking multiple vehicles using foreground, background and motion models[J].Image and Vision Computing,2004,22(1):143-155.
[40]L.Belli, Tseng, Lin.Ching-Yun, et.al.Real-Time Video Surveillance for Traffic Monitoring Using Virtual Line Analysis.Multimedia and Expo,2002.ICME' 02.Proceedings.2002 IEEE International Conference on, Aug,2002,2:26-29.
[41]Peterfreund N.Robust tracking of position and velocity with Kalman snakes.IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(6):564-569.
[42]刘瑞祯,于仕琪.OpenCV教程基础篇.北京航空航天大学出版社,2008.
[43]熊昌镇,杨静,范五一.高分辨率图像亮度曲线在车流量检测算法中的应用.北京工业大学学报(EI检索),2009.
[44]张永丽,张太镒,毕建民.基于自适应背景初始化的车流量检测算法.微电子学与计算机,2007，24(5)：138～140.
[45]张懿慧,徐晓夏,陈泉林.基于阴影抑制和自适应背景更新的车辆检测系统.上海大学学报,2005,11(5)：465～471.
[46]Stauffer C, Grimson W.E.L., Learning patterns of activity using real-time tracking IEEE Transactions on Pattern Analysis&Machine Intelligence,2000,22(8):747-57.
[47]赵宇.视频处理中的目标分割与跟踪的研究.北京中国科学院自动化研究所,2004.
[48]关向荣,任金昌.视频监视中背景的提取与更新算法.微电子学与计算机,2005,22(1)：95～97.
[49]C.Stauffer, W.ErieandL.Grimson.Learning Patterns of Activity Using Real-time Tracking.IEEE Trans on Pattern Analysis and Machine Intelligence,2000,22(8):1-10.
[50](美)Bruce Eckel著,刘宗田,袁兆山,潘秋菱等译.C++编程思想第1卷：标准C++引导.机械工业出版社,2000：28～425.
[51]吴洁明,袁山龙.软件工程应用实践教程.北京：清华大学出版社,2005.
[2]Simon A, Becker JC.Vehicle guidance for an autonomous vehicle.Proceedings of 1999 IEEE International Conference on Intelligent Transportation System.1999:429-434.
[3]M.M.Trivedi, LMikic and G.Kogut.Distributed video networks for incident detection and managent.Proceeding of IEEE Intl.Conference on Intelligent Transportation Systems, 2000:155-160.
[4]Lin Honwen, Yang Shaoqing, XiaZhijun.A Moving objects Detection Approach for Smart Sensor.Proeeedings of the 5th International Conference on Machine Learing and Cyberneties.Dalian, August,2006.
[5]Rafael M Inigo.Application of machine vision to traffic monitoring and control.IEEE Transactions on Vehicular Technology,1989,38(3):112-122.
[6]Xin Li, XiaoCao Yao.A real-time vehicle detection and tracking System in outer door traffic Scenes.Pattern recognition,2004(2):761-764.
[7]宋新,罗军,王鲁平.基于GVF Snake的运动目标跟踪方法.红外与激光工程，2007,36(2)：226～228.
[8]Stringa, E.and Regazzoni, C.5.Real-time video-shot detection for scene surveillance applications.IEEE Transactions of Image Proeessing,2000,9(1):69-79.
[9]N.Martel-Brisson, A.Zaccarin.Moving Cast Shadow Detection from a Gaussian Mixture Shadow Model.in Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC,2005.
[10]Kmaijo, Y.Matsushita, K.Ikeuehi, M.Sakauehi.Traffic monitoring and accident detection at Intersections.IEEE Transactions on Intelligent Transportation Systems, June,2000, 1(2):108-118.
[11]Birchfield S T,Rangarajan S.Spatiograms versus histograms for region-based tracking.IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR).[S.1]:IEEE,2005:1158-1163.
[12]Bertalmio M, Sapiroo G and Randll G.Morphing active contours.IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(7):733-737.
[13]J.M.Collado, C.Hilario, A.de la Escalera, J.M Armingol.Model Based Vehicle Detection for Intelligent Vehicles.IEEE Intelligent Vehicles Symposium,2004:572-577.
[14]Paragios N and Deriche R.Geodesic active contours and level sets for the detection and tracking of moving objects.IEEE Trans Pattern Analysis and Machine Intelligence,2000, 22(3):266-280.
[15]Low D. GDistinctive Image Features from Scale-Invariant Key-Point. International Journal of Computer Vision,2004,2(60):91-110.
[16]Karaulova I,Hall P and Marshall A.A hierarchical model of dynamics for tracking people with a single video camera.In:British Machine Vision Conference, Bristol, UK, 2000:352-361.
[17]Kumar P, Sengupta K., Lee A..A comparative study of different color spaces for foreground and shadow detection for traffic monitoring system.The IEEE 5th international conference on intelligent transportation systems,Singapore,2002:100-105.
[18]Jun-Wei Hsieh, Wen-Fong Hu, etc.Shadow elimination for effective moving objection by Gaussian shadow modeling.Image and Version computing,2003,21:505-516.
[19]Paul L.Rosin, Efstathios Ioannidis.Evaluation of global image thresholding for change detection[J].Pattern Recognit.Lett,2003,24(14):2345-2356.
[20]LMikic, P.Cosman, G.Kogut and M.M.Trivedi.Moving shadow and object detection in traffic scenes.Proceedings of Intl.Conference on Pattern Recognition,2000,1:321-324.
[21]Dovgard.R.Holographic image representation with reduced aliasing and noise affects IEEE Transactions on Image Processing, July,2004.
[22]史忠科,曹力.交通图像检测与分析.北京：科学出版社,2007：16～19.
[23]Andrea Prati, Ivana Mikie, Costantino Grana, Mohan M.trivedi.Shadow Detection Algorithms for Traffic Flow Analysis:a Comparative Study.2001 IEEE Intelligent Transportation Systems Conference Proceedings-Oakland(CA), USA-August,2001:25-29.
[24]Wu Zeju, Chen Jundong, Liu Yun.Video object segmentation of still background[J]. Journal of Qingdao Univesity of Science and Technology,2004,25(5):457-460.
[25]Bastian Leibe.interleaved Object Categorization and Segmentation, Ph.D.thesis, University of Swiss Federal institute of Technology Zurieh,2004.
[26]CUCCHIARA R, GRANA C, PICCARDI M.Improving shadow suppression in moving object detection with HSV color information.Proc of IEEE Int'l Conference onIntelligent Transp0rtati0n Systems.Oakland:IEEE,2001:334-339.
[27]WangJ.M., Chung.YC., Chang C.L.etal.shadow detection and removal for traffic images.Porceeding of the 2004 IEEE international conference on Networking, sensing & control, Taipei, Taiwan,2004:649-654.
[28]Rita Cuchiara, Costantino Grana, Massioo Pieeardi.Improving Shadow Suppression in Moving object Detection with HSV Color lnformation.In:2001 IEEE Intelligent Transportation Systems Conferenee Proeeedings-oakland(CA), USA-August,2001:25-29.
[29]Harini Veeraraghavan.Osama Masoud, NikolaosP.Papanikolopoulos.Computer Vision Algorithms for Intersections Monitoring IEEE Transactions on Intelligent TransportationSystems,2003,4(2):78-89.
[30]冈萨雷斯.数字图像处理.电子工业出版社,2005：250～385.
[31]陈兵旗,孙明.实用数字图像处理与分析.清华大学出版社,2008：251-308.
[32]Rafacel C.Gonzalez,Richard E.Woods.Digital image processing.Publishing House of Electronics Industry,2005:420-450.
[33]David Beymer, Philip McLauchlan.A Real-time computer vision system for vehicle tracking and traffic surveillance.Transportation Research:Part C,1998,6(4):271-288
[34]李俊韬,张海,范跃祖.复杂交通场景中多运动目标分割算法.北京航空航天大学学报，2006,32(3)：298～230.
[35]刘洋,李玉山,张大朴.基于动态目标建模的粒子滤波视频跟踪算法.光子学报,2008,37(2)：375～379.
[36]M.K.Sing.An intelligent traffic monitoring system for Expressways.Proe.6th Int.Con.On Application of Advanced Technologies in Transportation Engineering. Singapore, June, 2000:28-30.
[37]Ashit Talukder, Larry MatthieS.Real time Deteetion of Moving Objects from Moving Vehicles using Dense Stereo and optical Flow.Proeeedings of 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems.Sep-Oct, Sendal, Japan,2004.
[38]A.Elgammal, R.Duraiswami,D.Harwood, et al.Background and foreground modeling using nonparametric kernel density estimation for visual surveillance.Proceedings of the IEEE, 2002,90(7):1151-1163.
[39]D.R.Magee.Tracking multiple vehicles using foreground, background and motion models[J].Image and Vision Computing,2004,22(1):143-155.
[40]L.Belli, Tseng, Lin.Ching-Yun, et.al.Real-Time Video Surveillance for Traffic Monitoring Using Virtual Line Analysis.Multimedia and Expo,2002.ICME' 02.Proceedings.2002 IEEE International Conference on, Aug,2002,2:26-29.
[41]Peterfreund N.Robust tracking of position and velocity with Kalman snakes.IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(6):564-569.
[42]刘瑞祯,于仕琪.OpenCV教程基础篇.北京航空航天大学出版社,2008.
[43]熊昌镇,杨静,范五一.高分辨率图像亮度曲线在车流量检测算法中的应用.北京工业大学学报(EI检索),2009.
[44]张永丽,张太镒,毕建民.基于自适应背景初始化的车流量检测算法.微电子学与计算机,2007，24(5)：138～140.
[45]张懿慧,徐晓夏,陈泉林.基于阴影抑制和自适应背景更新的车辆检测系统.上海大学学报,2005,11(5)：465～471.
[46]Stauffer C, Grimson W.E.L., Learning patterns of activity using real-time tracking IEEE Transactions on Pattern Analysis&Machine Intelligence,2000,22(8):747-57.
[47]赵宇.视频处理中的目标分割与跟踪的研究.北京中国科学院自动化研究所,2004.
[48]关向荣,任金昌.视频监视中背景的提取与更新算法.微电子学与计算机,2005,22(1)：95～97.
[49]C.Stauffer, W.ErieandL.Grimson.Learning Patterns of Activity Using Real-time Tracking.IEEE Trans on Pattern Analysis and Machine Intelligence,2000,22(8):1-10.
[50](美)Bruce Eckel著,刘宗田,袁兆山,潘秋菱等译.C++编程思想第1卷：标准C++引导.机械工业出版社,2000：28～425.
[51]吴洁明,袁山龙.软件工程应用实践教程.北京：清华大学出版社,2005.