上海交通大学学报(自然版) ›› 2013, Vol. 47 ›› Issue (08): 1257-1263.

• 自动化技术、计算机技术 • 上一篇    下一篇

基于路面亮度特征估算的视频能见度检测系统

杨娴,李勃,丁文,陈启美   

  1. (南京大学 电子科学与工程学院, 南京 210093)
     
  • 收稿日期:2012-11-22 出版日期:2013-08-29 发布日期:2013-08-29
  • 基金资助:
    国家自然科学基金资助项目(61105015),江苏省自然科学基金资助项目(BK2011511),江苏省科技支撑计划(BE2011747)
     

Visibility Detection Based on Estimating Characteristic Luminance of Road Surface

YANG Xian,LI Bo,DING Wen,CHEN Qimei
  

  1. (School of Electronic Science and Engineering, Nanjing University, Nanjing 210093, China)
  • Received:2012-11-22 Online:2013-08-29 Published:2013-08-29

摘要:

为了解决现有的视频能见度算法适用面窄、检测不稳定的问题,提出了一种基于路面亮度特征估算的视频能见度检测算法.首先提取亮度、高度一致的路面区域,求取路面采样区域的视亮度,根据Koschmieder公式结合摄像机标定构建多组亮度幂函数关系,计算路面的固有亮度;最后对图像进行多点采样计算能见度距离并对计算结果进行聚类.实验数据表明,所提出的算法具有计算量小、计算精度高且普遍适用的优点.
 
 

关键词: 能见度检测,  , 路面固有亮度, 路面视亮度, Koschmieder理论

Abstract:

In order to overcome the shortcomings of state-of the-art visibility detection methods, a novel algorithm was proposed to measure the atmospheric visibility based on intrinsic luminance of road surface using a video camera. First, the luminance and height constant regions of the road were extracted. Then, the apparent luminance of sampled areas was computed, and power functions were built to calculate the intrinsic luminance according to Koschmieder formula and camera calibration technology. Finally, multipoints sampling was conducted to calculate the visibility distance whose the results were clustered. The experimental results show that this algorithm can lower computation costs and achieve a more precise atmospheric visibility.
 

Key words: visbility detection; , intrinsic luminance of roads; apparent luminance of roads; Koschmieder theory

中图分类号: