本文为中国香港中文大学（作者：LAU Wai Hung）的硕士论文，共81页。
交通监控是智能交通系统（ITS）的重要组成部分。在世界各地的许多智能交通系统中，道路上都安装了摄像头来监测交通状况。在香港，不同于目前大多数的系统，一系列离散的图像而不是视频被捕获采集。本文开发了一个基于静态图像的交通监控系统。提出了几种基于边缘检测的道路车辆数量估计方法。与视频处理相比，该方法计算量小，通过分析静态图像的时间序列，可以得到合理的交通状况变化跟踪结果。
Traffic monitoring has been a majorcomponent of Intelligent Transport Systems (ITS). In many ITS around the world,cameras have been installed on the road to monitor the traffic condition. InHong Kong, differing from most of the current systems, a sequence of discretepictures instead of video is captured. In this thesis a static image-basedtraffic monitoring system is developed. Several methods based on edge detectionare proposed to estimate the number of vehicles on the road. It is lesscomputational demanding than video processing and yields reasonable results ontracking changes of traffic condition by analyzing a time series of thesestatic images.
- 引言
- 文献回顾
- 研究方法
- 实验与评估
- 分析
- 结论
附录A Sobel边缘检测
附录B 神经网络设置
附录C 数值结果
更多精彩文章请关注公众号：
