计算机应用 ›› 2010, Vol. 30 ›› Issue (06): 1552-1555.

• 图形图像处理与模式识别 • 上一篇    下一篇

基于单目视觉的道路图像理解综述

孟丽霞1,孙富春2,邵宇2   

  1. 1. 清华大学计算机系
    2.
  • 收稿日期:2009-12-25 修回日期:2010-03-03 发布日期:2010-06-01 出版日期:2010-06-01
  • 通讯作者: 孟丽霞
  • 基金资助:
    自然科学基金;863计划

Survey on road image interpretation based on monocular vision

  • Received:2009-12-25 Revised:2010-03-03 Online:2010-06-01 Published:2010-06-01

摘要: 基于视觉的道路图像提供了车辆运行局部环境的丰富的信息,对这些序列图像的分析理解在车辆辅助驾驶、自动导引车、室外移动机器人等多领域得到了广泛的应用。详细介绍了道路检测系统以及道路偏离预警等系统中对道路图像进行处理、分析、理解的各种方法,阐述了道路识别与跟踪的技术和方法,并进行了比较。最后给出了该领域今后的研究方向和发展趋势。

关键词: 计算机视觉, 道路检测, 道路识别, 道路跟踪

Abstract: Vision-based road images provide rich information about local environment during travelling. These serial images were analyzed and interpreted in many fields such as automatic guided vehicle, mobil robots, driving assistant systems and so on. Technologies and methods of road image processing, analyzing and interpreting in lane detection system and lane departure system were introduced in detail. Technologies of lane recognition and tracking were introduced and compared in detail. Finally future research and development direction were given.

Key words: computer vision, Lane detection, lane recognition, lane tracking