计算机科学 ›› 2017, Vol. 44 ›› Issue (Z11): 233-237.doi: 10.11896/j.issn.1002-137X.2017.11A.049

• 模式识别与图像处理 • 上一篇    下一篇

基于视频的夜间车辆检测与跟踪算法研究

董天阳,朱浩楠,王浩   

  1. 浙江工业大学计算机科学与技术学院 杭州310023,浙江工业大学计算机科学与技术学院 杭州310023,浙江工业大学计算机科学与技术学院 杭州310023
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金项目(61672464)资助

Video-based Nighttime Vehicle Detection and Tracking Algorithm

DONG Tian-yang, ZHU Hao-nan and WANG Hao   

  • Online:2018-12-01 Published:2018-12-01

摘要: 针对夜间高速光照条件差、车灯种类多样、环境因素干扰等导致的车辆难以检测的问题,提出了一种基于视频的夜间车辆的检测与跟踪算法。该方法首先将OTSU与一维最大熵阈值分割算法相结合来实现车灯的提取,剔除非车灯光源;然后利用车灯的时空特性完成车灯的匹配,解决了一车多灯和并排同速车辆的问题;最后利用kalman滤波器完成车灯的预测跟踪。在交通弱光流畅交通、正常光流畅交通和正常光拥堵交通3种应用场景下对所提算法进行应用和结果分析,实验结果表明所提方法在保证实时性的同时具有较高的准确率。

关键词: 夜间高速,车辆检测,智能交通

Abstract: In the night,the vehicles on highway are difficult to detect because of a variety of factors,such as bad highway lighting conditions and different type of lights.To solve the problem,a video-based nighttime vehicle detection and tracking algorithm was proposed.Firstly,this algorithm combines OTSU and one dimensional maximum entropy threshol-ding algorithm to extract vehicle lights,eliminating non-vehicle lights.After that,this method makes use of temporal and spatial characteristics of light to distinguish a car with multiple lights and side-by-side vehicles.Finally,the kalman filter is used to predict and track the vehicle lights.This paper analyzed the result of the algorithm in three different application scenarios,weak light smooth traffic,normal light smooth traffic and normal light congestion traffic.The experi-mental results prove that the proposed method has high accuracy and pretty real-time performance.

Key words: Nighttime highway,Vehicle detection,Smart traffic

[1] SALVI G.An Automated Nighttime Vehicle Counting and Detection System for Traffic Surveillance[C]∥International Conference on Computational Science and Computational Intelligence (CSCI).New York:IEEE,2014:131-136.
[2] LIN S P,CHEN Y H,WU B F.A real-time multiple-vehicle detection and tracking system with prior occlusion detection and resolution,and prior queue detection and resolution[C]∥18th International Conference on Pattern Recognition.New York:IEEE,2006:828-831.
[3] HSIEH J W,YU S H,CHEN Y S,et al.An Automatic traffic surveillance system for vehicle tracking and classification[J].IEEE Transactions on Intelligent Transportation Systems,2003,7(2):175-187.
[4] SONG X,NEVATIA R.Robust Vehicle Blob Tracking with Split/Merge Handling[C]∥Proceedings of the 1st international eva-luation conference on Classification of events,activities and relationships(CLEAR’06).Verlag Berlin:Springer,2006:216-222.
[5] ZHOU S,LI J,SHEN Z,et al.A night time application for areal-time vehicle detection algorithm based on computer vision[J].In Res.J.Appl.Sci.Eng.Technol,2013,5(10):3037-3043.
[6] 王鹏,黄凯奇.基于视频的夜间高速公路车辆事件检测[J].中国图象图形学报,2010,15(2):301-306.
[7] WU B F,CHEN Y L,CHIU C C.A Discriminant AnalysisBased Recursive Automatic Thresholding Approach for Image Segmentation[J].Ieice Transactions on Information & Systems,2005,88(7):1716-1723.
[8] ZHANG W,WU Q M J,WANG G,et al.Tracking and pairing vehicle headlight in night scenes[J].IEEE Transactions on Intelligent Transportation Systems,2012,13(1):140-153.
[9] WU J T,LEE J D,CHIEN J C,et al.Nighttime Vehicle Detection at Close Range Using Vehicle Lamps Information[C]∥International Symposium on Computer,Consumer and Control.New York:IEEE,2014,7-1240.
[10] WANG W,SHEN C,ZHANG J,et al.A two-layer night-timevehicle detector[M]∥Digital Image Computing:Techniques and Applications.New York:IEEE,2009:162-167.
[11] VIOLA P,JONES M.Rapid Object Detection using a Boosted Cascade of Simple Features[C]∥Computer Vision and Pattern Recognition.Washington D C:IEEE Computer Society,2001:511.
[12] ROBERT K.Night-time traffic surveillance:A robust frame-work for multi-vehicle detection,classification and tracking[C]∥Advanced Video and Signal Based Surveillance.New York:IEEE,2009:1-6.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!