基于复杂城市道路场景的消失点检测 Vanishing point detction（IET Computer Vision）个人主页：http://www.newneu.neu.edu.cn/?p=1

Efficient vanishing point detection method in complex urban road environments

Abstract:Detecting the vanishing point in a road image is important for robot navigation, intelligent transportation and other fields. This study proposes a new vanishing point detection method that uses the vertical information in complex urban road and street environments. First, all straight lines in the road image are detected based on curvature scale space and principal component analysis methods. Second, a new road region extraction method is proposed to support vanishing point detection. In this method, the image is decomposed into approximate sky, vertical and road regions using the estimation envelopes of the vertical lines. Third, the straight lines in the road region are xtracted using a path perspective triangle and line length limits. The straight lines are then categorised into groups using proposed grouping strategies. Finally, vanishing point candidates are calculated from paired lines extracted from different groups and from the same group, and the final vanishing point is then estimated for the urban road scene using the mean shift clustering method. The experimental results show that the proposed algorithm can estimate the vanishing point accurately and efficiently in complex urban road environments, despite interference from vehicles and pedestrians and on curved and unstructured roads.

Weili Ding   and  Yong Li， Efficient vanishing point detection method in complex urban road environments[J].IET Computer Vision, 2015DOI:  10.1049/iet-cvi.2014.0187

原文链接：http://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2014.0187

相关的论文可以登录：李勇个人主页：http://www.newneu.neu.edu.cn/?p=1477

我的第一篇SCI文章。CCF推荐期刊。推荐推荐自己的论文，哈哈~~~~~

消失点（消隐点/灭点）是相机标定，三维重建，汽车辅助驾驶，智能导航，深度估计，机器人导航等领域的重要信息。 本文是针对道路场景进行消失点检测，针对道路的消失点，可以做基于消失点信息的道路提取，基于消失点等信息的深度估计，基于消失点信息的导航线提取及偏离预警。

本文从KongHui等人公开的数据库以及网络公开的图像和自己拍摄的城市道路场景中选取了350幅不同类型的典型图像，如有需要，可以发送邮件给我们。

相关论文可以参考以下链接：

丁伟利,李勇,王文锋,曹秀燕. 基于轮廓特征理解的城市道路图像深度估计[J]. 光学学报, 2014, 34(7): 0715001

http://www.opticsjournal.net/abstract.htm?aid=OJ0625000013jPmSoV

王文锋,丁伟利,李勇,杨树军. 一种高效的基于平行边缘的道路识别算法[J]. 光学学报, 2015, 35(7): 0715001

 

2015年CVPR也有2篇关于Vanishing Point的文章：

Joint Vanishing Point Extraction and Tracking.

Real-time Joint Estimation of Camera Orientation and Vanishing Points