大工至善|大学至真分享 http://blog.sciencenet.cn/u/lcj2212916

博文

[转载]【信息技术】【2007.01】基于视频的车辆检测预警智能交通系统

已有 349 次阅读 2020-1-11 21:38 |系统分类:科研笔记|文章来源:转载

本文为美国内华达拉斯维加斯大学(作者:Naveen Chintalacheruvu)的硕士论文,共135页。

 

基于视频的车辆检测与监控技术是智能交通系统(ITS)的重要组成部分,它具有非侵入性和捕获全局、特定车辆行为数据的能力。本文的初步目标是开发一个有效的基于视频检测的工作区拥塞和特殊事件预警ITS系统。本文设计的目标是:1)成功开发了基于现有组件的预警ITS系统;2)开发并评估了一种改进的车辆检测与跟踪算法。开发的预警ITS系统包括许多现成的设备,如“Autoscope”(基于视频的车辆检测器)、数字录像机、射频收发器、高增益八木天线、可变信息标志和接口处理器。所使用的基于视频的检测系统需要对配置参数进行校准和微调,以获得准确的结果。为此,采用Comer Harris算法开发了一个基于视频的汽车检测系统,消除了复杂标定和对比修改的需要。该算法是在运行WinXPE操作系统的Arcom Olympus Windows XP嵌入式开发工具包上使用OpenCV库实现的。算法的性能是为了提高车速和计数的准确性。该算法的性能相当于或优于Autoscope系统,无需对校准和分层调整进行任何修改

 

Video based vehicle detection andsurveillance technologies are an integral part of Intelligent TransportationSystem (ITS), due to its non-intrusiveness and capability of capturing globaland specific vehicle behavior data. The initial goal of this thesis is todevelop an efficient advance warning ITS system for detection of congestion atwork zones and special events based on video detection. The goals accomplishedby this thesis are; 1) successfully developed the advance warning ITS systemusing off-the-shelf components and 2) Develop and evaluate an improved vehicledetection and tracking algorithm. The advance warning ITS system developedincludes many off-the-shelf equipments like “Autoscope” (video based vehicledetector), Digital Video Recorders, RF Transceivers, high gain Yagi antennas,variable message signs and interface processors. The video based detectionsystem used requires calibration and fine tuning of configuration parametersfor accurate results. Therefore, an in-house video based vehicle detectionsystem was developed using the Comer Harris algorithm to eliminate the need ofcomplex calibration and contrasts modifications. The algorithm was implementedusing OpenCV library on a Arcom’s Olympus Windows XP Embedded development kitrunning WinXPE operating system. The algorithm performance is for accuracy invehicle speed and count is evaluated. The performance of the proposed algorithmis equivalent or better to the Autoscope system without any modifications tocalibration and lamination adjustments.

 

 

1. 引言

2. 车辆检测与跟踪

3. 系统设置

4. Harris-Corner检测

5. 结果与结论

附录详细规范


更多精彩文章请关注公众号:qrcode_for_gh_60b944f6c215_258.jpg



http://blog.sciencenet.cn/blog-69686-1213795.html

上一篇:[转载]【计算机科学】【2013.08】大学四年深入学习对学生认知需求的影响
下一篇:[转载]【计算机科学】【2015.05】基于卷积神经网络的鲁棒分类

0

该博文允许注册用户评论 请点击登录 评论 (0 个评论)

数据加载中...

Archiver|手机版|科学网 ( 京ICP备07017567号-12 )

GMT+8, 2020-2-24 21:14

Powered by ScienceNet.cn

Copyright © 2007- 中国科学报社

返回顶部