交叉口机动车运动轨迹特征提取与标定

doi:10.3969/j.issn.0258-2724.2012.05.009

基金项目:

国家自然科学基金资助项目(51108208)

博士后科学基金资助项目(20110491307)

详细信息

通讯作者:
胡宏宇(1982-),男,讲师,研究方向为视频检测、交通控制,E-mail:huhongyu@jlu.edu.cn

计量
- 文章访问数:1110
- HTML全文浏览量:113
- PDF下载量:351
- 被引次数:0
出版历程
- 收稿日期:2012-03-02
- 刊出日期:2012-10-25

Extraction and Calibration of Trajectory Characteristics of Vehicles at Intersections

摘要

摘要:为探讨机动车在交叉口的运行特性,采用复合特征提取算法获取图像上机动车运行的轨迹特征;在多边形线性扫描算法的基础上,考虑摄像机成像畸变的影响,引入中心偏移因子,提出了考虑中心偏移的多区域扫描标定算法,将运行轨迹图像特征转化为真实的运动特征;最后,与多边形线性扫描算法的计算结果及实测数据进行了对比,结果表明:该算法能够有效地提取交叉口机动车的运行轨迹,准确地表征机动车在交叉口的相关运行特性;与实测车速相比,计算得到的机动车速度误差小于4%.
- 交通运输系统工程/
- 视频检测/
- 交叉口/
- 轨迹跟踪/
- 特征表达
Abstract:In order to probe into the running characteristics of vehicles at intersections, the composite feature extraction algorithm was used to obtain the trajectory characteristics of vehicles in images. Based on the algorithm of polygon linear scan calibration, considering the influence of the distortion of CCD (charge-coupled device) camera and introducing center deviation factor, an MRSCCO (multi-region scanning calibration considering about center offset) algorithm was proposed to transform the trajectory features of images into real motion features. Finally, data extracted using this algorithm were compared with both results obtained by the algorithm of polygon linear scan calibration and real data. The experimental results show that the proposed algorithm can effectively extract the trajectories of vehicles at intersections and accurately express the relevant characteristics. Compared with the real vehicle speed, the vehicle speed obtained by the MRSCCO algorithm has an error of less than 4%.
- engineering of communication and transportation system/
- video detection/
- intersection/
- trajectory tracking/
- feature representation

HTML全文

参考文献 (15)

MAURIN B, MASOUD O, PAPANIKOLOPOULOS N P. Tracking all traffic: algorithms for monitoring vehicles, individuals, and crowds[J]. Computer Vision Robotics & Automation Magazine, IEEE, 2005, 12(1): 29-36.

SAUNIER N, SAYED T. A feature-based tracking algorithm for vehicles in intersections//Proceedings of the 3rd Canadian Conference on Computer and Robot Vision.: IEEE, 2006: 59-59.

SAUNIER N, SAYED T. Probabilistic framework for automated analysis of exposure to road collisions[J]. Transportation Research Record: Journal of the Transportation Research Board, 2009(2083): 96-104.

ISMAIL K, SAYED T, SAUNIER N, et al. Automated analysis of pedestrian-vehicle conflicts using video data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2010(2140): 44-54.

SAYED T, LIM C. Probabilistic collision prediction for vision-based automated road safety analysis//Intelligent Transportation Systems Conference. Seattle: [s.n.], 2007: 872-878.

MAINI P. Development of a vehicle following model(VEHFOL) and a hetero generous traffic simulation model(HETSIM) for controlled intersections. Denver: Department of Civil Engineering, University of Colorado, 2001.

吕剑,史其信,杨新苗. 基于运动轨迹采集的混合交通特性研究[J]. 武汉理工大学学报:交通科学与工程版,2009,33(1): 1-4. LÜ Jian, SHI Qixin, YANG Xinmiao. Research of mixed traffic based on trajectories capture[J]. Journal of Wuhan University of Technology: Transportation Science & Engineering, 2009, 33(1): 1-4.

曲昭伟. 混合交通视频检测算法研究. 长春:吉林大学交通学院,2009.

胡宏宇,王殿海,李志慧,等. 基于视频的车辆特征表达与分类算法[J]. 交通与计算机,2008,26(6): 1-5. HU Hongyu, WANG Dianhai, LI Zhihui, et al. Feature representation and classification algorithm of vehicle based on video[J]. Computer and Communications, 2008, 26(6): 1-5.

杨涛,刘越,吕尤,等. 一种投影-摄像机交互系统中的全自动快速标定方法[J]. 系统仿真学报,2009,21(增刊1): 51-53. YANG Tao, LIU Yue, LÜ You, et al. Research on a rapid automatic calibration method for largeprojector-camera interaction system[J]. Journal of System Simulation, 2009, 21(Sup.1): 51-53.

曲巨宝. 基于智能Agent的车辆自适应跟踪技术[J]. 江南娱乐网页版入口官网下载安装学报,2011,46(4): 626-632. QU Jubao. Adaptive technology for vehicles tracking based on intelligent agent[J]. Journal of Southwest Jiaotong University, 2011, 46(4): 626-632.

江晟,王殿海,赵莹莹,等. 基于复合算法的混合交通流前景提取[J]. 吉林大学学报:工学版,2011,41(增刊1): 76-80. JIANG Sheng, WANG Dianhai, ZHAO Yingying, et al. Recombination algorithm for mixed traffic flow foreground abstracting[J]. Journal of Jilin University: Engineering and Technology Edition, 2011, 41(Sup.1): 76-80.

COIFMAN B, BEYMER D, MCLAUCHLAN P. A real-time computer vision system for vehicle track traffic surveillance[J]. Transportation Research Part C: Emerging Technologies, 1998, 6(4): 271-288.

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,2004,27(11): 56-58. ZHANG Lin, YE Haibing, HE Wei. Improved vehicle detection algorithm based on edge information[J]. Transaction of Chongqing University: Natural Science Edition, 2004, 27(11): 56-58.

罗东华,余志,李熙莹. 基于边缘的背景差法在车流量检测中的应用[J]. 光电工程,2007,34(11): 70-73. LUO Donghua, YU Zhi, LI Xiying. Application of edge-based background difference in traffic volume extraction[J]. Opto-Electronic Engineering, 2007,34(11): 70-73.

施引文献

附加材料 (0)

访问统计

点击查看大图

计量

文章访问数:1110
HTML全文浏览量:113
PDF下载量:351
被引次数:0