[1]韩静,于平平,王震洲,等.基于数字相机响应曲线拟合道路能见度检测算法[J].燕山大学学报,2018,42(3):272-277.[doi:10.3969/j.issn.1007-791X.2018.03.013]
 HAN Jing,YU Pingping,WANG Zhenzhou,et al.An algorithm for visibility estimation based on response curve fitting of digital camera[J].Journal of YanShan University,2018,42(3):272-277.[doi:10.3969/j.issn.1007-791X.2018.03.013]
点击复制

基于数字相机响应曲线拟合道路能见度检测算法
分享到:

《燕山大学学报》[ISSN:1007-791X/CN:13-1219/N]

卷:
42
期数:
2018年第3期
页码:
272-277
栏目:
信息与计算机技术
出版日期:
2018-05-31

文章信息/Info

Title:
An algorithm for visibility estimation based on response curve fitting of digital camera
文章编号:
1007-791X(2018)03-0272-06
作者:
韩静1于平平2王震洲2*霍威2齐林2
1.河北科技大学  环境科学与工程学院,河北 石家庄 050018;2. 河北科技大学 信息科学与工程学院,河北 石家庄 050018
Author(s):
 HAN Jing1YU Pingping2WANG Zhenzhou2 HUO Wei2QI Lin2
1.School of Environmental Science and Engineering,Hebei University of Science and Technology,Shijiazhuang,Hebei 050018,China;2.School of Information Science and Engineering,Hebei University of Science and Technology,Shijiazhuang,Hebei 050018,China
关键词:
能见度检测响应曲线拟合双亮度差法监控视频
Keywords:
visibility detectioncurve response fittingdifferential luminance algorithmsurveillance video
分类号:
TP391.4
DOI:
10.3969/j.issn.1007-791X.2018.03.013
文献标志码:
A
摘要:
在分析各种能见度检测算法优缺点的基础上,为了进一步提高能见度检测的精度,本文设计了一种新的基于相机响应曲线拟合的能见度算法:通过对高速路上的监控相机设定严格的参数,用固定光圈,不同曝光时间,拍摄稳定均匀光源照明的均匀白色漫反射表面,选取拍摄图像的中间部分计算图像平均灰度值,拟合图像的平均灰度值与曝光时间的双对数曲线,得到视亮度与固有亮度之间相互转换的重要参数值。本算法利用高速监控设备,采用路面作为标志物,解决了在高速路上不易寻找目标物的问题,计算误差小,成本低,不需额外增加检测设备,非常适用于高速路上雾天能见度监测。
Abstract:
The advantages and weakness of the existing video visibility algorithms are analyzed and compared in this paper.In order to improve the accuracy of the visibility detection,this paper designs a new visibility detection algorithm which based on the digital camera response curve fitting.Experimental pictures are taken on the uniformity white diffuse surface with a fixed aperture,different exposure time.The average gray value of the pictures are calculated using the middle part of the experimental pictures.The double logarithmic curve is fitted of the pixel value of the image and exposure time.Then according to this curve,the value can be obtained,which is the conversion coefficient between the brightness and inherent brightness.The atmospheric extinction coefficient can be calculated by the inherent brightness,resulting in atmospheric visibility values.The algorithm chooses the pavement as a marker to solve the problem that the target is not easy to find on the road.The distance between the target point and the camera is calculated by the inherent lane mark line and the camera selfcalibration method.Experimental results show that the proposed visibility detection algorithm has high accuracy and low cost.It is very suitable for the fog visibility monitoring on the high speed road.

备注/Memo

备注/Memo:
 收稿日期:2018-01-18    责任编辑:孙峰
基金项目:河北省科技计划项目(16210805);河北省科技支撑计划项目(16273705D,16222101D-1)
作者简介:韩静(1978-),女,河北保定人,博士,讲师,主要研究方向为大气能见度观测及污染控制; *通信作者:王震洲(1978-),男,河北张家口人,博士,副教授,主要研究方向为智能信息处理,Email:chinawzz@163.com
更新日期/Last Update: 2018-07-16