《计算机应用研究》|Application Research of Computers

视频图像的车辆速度实时检测算法研究

Vehicle speed detection algorithm research of real-time video image

免费全文下载 (已被下载 次)  
获取PDF全文
作者 巨志勇,王超男,何晓蕾
机构 上海理工大学 光电信息与计算机工程学院,上海 200093
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)09-2822-03
DOI 10.3969/j.issn.1001-3695.2017.09.057
摘要 在监控视频图像中因拍摄角度的问题,导致图像中的车道线并不是竖直的。针对在此图像中选取对应块,实现车辆速度实时检测的问题,分析了车身的特征及图像中车道线的倾斜角度,选择车灯作为对应块,选取车灯存在的候选区域;然后根据车灯的对称性强度筛选车灯带,实现车灯的准确定位,并把车灯移动的距离通过摄像机标定转换到实际坐标中,从而实现车辆速度的实时检测。实验结果证明,该方法运行速度快、定位准确,因此可以广泛地应用于红绿灯路口环境中,实现视频图像的车速实时检测。
关键词 倾斜矫正;车灯定位;对称性;摄像机标定;车速检测
基金项目 国家自然科学基金资助项目(81101116)
本文URL http://www.arocmag.com/article/01-2017-09-057.html
英文标题 Vehicle speed detection algorithm research of real-time video image
作者英文名 Ju Zhiyong, Wang Chaonan, He Xiaolei
机构英文名 SchoolofOpticalElectrical&ComputerEngineering,UniversityofShanghaiforScience&Technology,Shanghai200093,China
英文摘要 The lane line in the video, due to the shooting angle, is not vertical, thus leads to a difficulty to detect the real-time speed of cars passing by taken areas in the image. With regard to this problem, this paper analysed the features of the car and the inclination angle of the lane line in the image, and selected the car headlight as the reference area to define the candidate area which was existed the car lights. Then, the paper selected car lights zone according to the symmetry of light intensity to realize the pinpointing of the car lights, and with the camera calibration, transformed the move distance of car headlight into world coordinate, leading to achieve real-time speed detection of passing cars. The results show that this is fast method with accurate locating ability. So this algorithm can be widely used in realizing the real-time speed detection in video image of traffic light intersection.
英文关键词 slant correction; locate vehicle headlight; symmetry; camera calibration; vehicle speed detection
参考文献 查看稿件参考文献
  [1] 支晨蛟, 唐慧明. 基于视频特征角点特征匹配的车速检测方法[J] . 计算机工程, 2013, 39(12):176-180.
[2] 郑成勇. 一种RGB色空间中的车牌定位新方法[J] . 中国图象图形学报, 2010, 15(11):1623-1628.
[3] 逯鹏, 李亚萍, 李世杰, 等. 基于视觉机制的非结构环境下车速检测算法研究[J] . 计算机应用研究, 2015, 32(5):1559-1562.
[4] 胡峰松, 朱浩. 基于多重特征和SURF算法的车牌定位研究[J] . 计算机工程与应用, 2015, 51(17):182-187.
[5] 童剑军, 邹明福. 基于监控视频图像的车辆测速[J] . 中国图象图形学报, 2005, 10(2):192-196.
[6] Dodey D, McGinley B , Hughes C, et al. A blind-zone detection method using a rear-mounted fisheye camera with combination of vehicle detection methods[J] . IEEE Trans on Intelligent Transportation Systems, 2016, 17(1):264-278.
[7] Li Xin, Zhou Zenggang, Li Xiaoyuan, et al. Vehicle segmentation and speed detection based on binocular stereo vision[C] //Proc of the 8th International Conference on Computational Intelligence and Security. 2012:369-373.
[8] Wang Liang, Song Junfang. The speed detection algorithm based on video sequences[C] //Proc of IEEE International Conference on Computer Science & Service System. 2012:217-220.
[9] 高磊, 李超, 朱成军, 等. 基于边缘对称性的视频车辆检测算法[J] . 北京航空航天大学学报:自然科学版, 2008, 34(9):1113-1116.
[10] 陈志强, 刘东权. 基于对称性的快速车辆检测方法[J] . 计算机工程与设计, 2012, 33(3):1042-1046.
[11] 石菲, 俞一彪, 孙兵. 《数字信号处理》中”奇偶分量分解”实例教学[J] . 实验科学与技术, 2012, 10(5):111-113.
[12] 于艳玲, 王韬, 袁彬, 等. 基于视频的车速检测算法研究[J] . 现代电子技术, 2013, 36(2):158-161.
收稿日期 2016/6/12
修回日期 2016/7/26
页码 2822-2824,2853
中图分类号 TP391.41
文献标志码 A