计算机应用 ›› 2017, Vol. 37 ›› Issue (2): 593-596.DOI: 10.11772/j.issn.1001-9081.2017.02.0593

• 应用前沿、交叉与综合 • 上一篇    下一篇

基于DSP的单车道车流量实时监测算法

杨婷1, 李博1, 石雯婧2, 张成飞1   

  1. 1. 仪器科学与动态测试教育部重点实验室(中北大学), 太原 030051;
    2. 图像视频处理与通信实验室(新墨西哥大学), 阿尔伯克基 新墨西哥州 87131, 美国
  • 收稿日期:2016-06-22 修回日期:2016-09-06 出版日期:2017-02-10 发布日期:2017-02-11
  • 通讯作者: 李博,libo@nuc.edu.cn
  • 作者简介:杨婷(1991-),女,内蒙巴彦淖尔人,硕士研究生,主要研究方向:嵌入式视频图像处理;李博(1972-),男,山西吕梁人,副教授,博士,主要研究方向:嵌入式电子电路系统;石雯婧(1992-),女,江苏南通人,硕士研究生,主要研究方向:视频图像处理;张成飞(1990-),男,安徽亳州人,博士研究生,主要研究方向:电子电路系统。
  • 基金资助:
    国家自然科学基金资助项目(61471325)。

Real-time vehicle monitoring algorithm for single-lane based on DSP

YANG Ting1, LI Bo1, SHI Wenjing2, ZHANG Chengfei1   

  1. 1. Key Laboratory of Instrumentation Science & Dynamic Measurement, Ministry of Education(North University of China), Taiyuan Shanxi 030051, China;
    2. Image and Video Processing and Communications Lab(University of New Mexico), Albuquerque New Mexico 87131, United States
  • Received:2016-06-22 Revised:2016-09-06 Online:2017-02-10 Published:2017-02-11
  • Supported by:
    This work is supported by the National Natural Science Foundation of China (61471325).

摘要: 针对传统的车流量检测系统采用感应器设备硬件安装繁杂及通用车流量检测算法无法判别车辆行驶方向的问题,提出一种基于数字信号处理器(DSP)的单车道车流量实时监测算法,并应用于停车场。首先,在虚拟检测带上使用背景差分法完成车辆检测,并对均值法背景建模进行改进;其次,提出一种邻帧二值归类算法对车辆行驶方向进行判别;最后,在虚拟检测带上进行车流量计数并将车位情况实时显示于LED显示屏上。通过模拟实验验证了所提算法的可行性,并在实际测试实验中,得到邻帧二值归类算法方向判别的准确率为96.5%,车位监控算法准确率为92.2%。实验结果表明,该单车道车流量实时监测算法准确率较高,节省了检测系统设备,可以应用于单车道停车场进行车流量实时监测。

关键词: 车流量监测, 单车道, 背景差分法, 背景建模, 虚拟检测带

Abstract: The traditional traffic flow detection system based on sensor device has complex hardware equipment and the universal traffic flow detection algorithm cannot distinguish the directions of vehicles. To resolve the above problems, a real-time vehicle monitoring algorithm for single-lane based on Digital Signal Processor (DSP) was proposed and applied to parking lot. Firstly, the background differential algorithm was used to detect vehicles on virtual detection zone and the method of mean background modeling was improved. Then, an adjacent frame two-value classification algorithm was proposed to distinguish the directions of vehicles. Finally, virtual detection zone was used for vehicle counting and the number of empty parking spots was real-time displayed on a Light Emitting Diode (LED) screen. The feasibility of the proposed algorithm was verified by the simulation experiment. The actual test results showed that the accuracy rate of the adjacent frame two-value classification algorithm for direction detection was 96.5% and the accuracy rate of parking spot monitoring algorithm was 92.2%. The proposed real-time vehicle monitoring algorithm for single-lane has high accuracy and needs less detection equipment, so it can be applied to single-lane parking lot for real-time vehicle monitoring.

Key words: vehicle monitoring, single-lane, background differential algorithm, background modeling, virtual detection zone

中图分类号: