基于改进暗通道算法的雾天车辆偏离预警研究
|
摘要
针对在雾天工况下仅凭常规车道线识别方法无法准确提取车道线这一现状,给出了一种基于改进暗通道算法的雾天车道线识别算法.首先利用基于双边滤波器的暗通道算法对雾天工况下的图片进行去雾并对去雾图像进行亮度修正;然后利用Sobel算子和大津法得到包含清晰道路边缘的二值化图像;最后利用Hough变换对车道线精确提取.实验表明:该算法能够在雾天工况下对车道线进行准确、快速地识别;与常规算法相比,该算法具有更高的准确性和实时性,对于提高雾天车辆主动安全性具有较大意义.
In this paper,a new algorithm based on dark channel prior was proposed for lane detection in fog weather which couldn't be detected by traditional algorithm.Firstly,the lane images in fog weather was defogged by improved dark channel prior based on gauss bilateral filter and then luminosity of defogged pictures were adjusted.Secondly,binary images of road edges was obtained by Sobel operator and Ostu algorithm.Finally,the road lane was extracted by Hough transform.Experimental results showed this new algorithm could detect road lane in fog weather accurately and rapidly.Compared with traditional lane detection method,this new algorithm has higher accuracy and instantaneity thus has great influence on the improvement of automobile active safety in fog weather.
In this paper,a new algorithm based on dark channel prior was proposed for lane detection in fog weather which couldn't be detected by traditional algorithm.Firstly,the lane images in fog weather was defogged by improved dark channel prior based on gauss bilateral filter and then luminosity of defogged pictures were adjusted.Secondly,binary images of road edges was obtained by Sobel operator and Ostu algorithm.Finally,the road lane was extracted by Hough transform.Experimental results showed this new algorithm could detect road lane in fog weather accurately and rapidly.Compared with traditional lane detection method,this new algorithm has higher accuracy and instantaneity thus has great influence on the improvement of automobile active safety in fog weather.
引文
[1]徐兰梅.车道偏离预警系统是否可以有效减少安全事故发生[EB/OL].[2015-03-29].http://gps.carcav.com/qcdz/2015/0329/417-98.html.
[2]KIM Z W.Robust lane detection and tracking in challenging scenarios[J].IEEE Transactions on Intelligent Transportation Systems,2008,9(1):16-26.
[3]刘伟,黎宁,张丹,等.基于自适应分割阈值的夜间车道标志线识别[J].计算机与数字工程,2015,43(2):308-311.
[4]陈军.基于DSP的高速公路车道偏离报警系统研究[D].天津:天津大学,2010.
[5]祝培,朱虹,钱学明,等.一种有雾天气图像景物影像的清晰化方法[J].中国图像图形学报,2004,9(1):124-128.
[6]LEVIN A,LISCHINSKI D,WEISS Y.A closed form solution to natural image matting[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2008,30(2):228-42.
[7]HE K,SUN J,TANG X.Guided image filtering.[J].IEEE Transactions on Software Engineering,2013,35(6):1397-1409.
[8]吴笑天,丁兴号,吴奎.基于暗通道理论的雾天图像复原的快速算法[J].长春理工大学学报(自然科学版),2012,35(1):100-104.
[9]COX L J.Optics of the atmosphere-scattering by molecules and particles[J].Journal of Modern Optics,1977,14(7):698-699.
[10]方雯,刘秉瀚.多尺度暗通道先验去雾算法[J].中国体视学与图像分析,2013(3):230-237.
[11]HE K,SOU J,TANG X.Single image haze removal using dark channel prior.[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2010,33(12):2341-2353.
[12]胡平.基于图像分割的交通图像快速去雾算法[J].计算机系统应用,2014,23(9):134-138.
[13]陆宗骐,梁诚.用Sobel算子细化边缘[J].中国图像图形学报,2000,5(6):516-520.
[14]金辉,吴乐林,陈慧岩,等.结构化道路车道线识别的一种改进算法[J].北京理工大学学报,2007,27(6):501-505.
[15]鞠乾翱.基于机器视觉的快速车道线辨识研究[D].上海:上海交通大学,2013.
[16]林广宇,魏朗,蹇小平.基于嵌入式的车辆偏离预警系统研究[J].电子设计工程,2010,18(8):26-28.
[17]魏朗,刘永涛.一种客运车辆车道偏离预警装置及其判断方法:中国,ZL201210057758.X[P].2014-06-18.
[2]KIM Z W.Robust lane detection and tracking in challenging scenarios[J].IEEE Transactions on Intelligent Transportation Systems,2008,9(1):16-26.
[3]刘伟,黎宁,张丹,等.基于自适应分割阈值的夜间车道标志线识别[J].计算机与数字工程,2015,43(2):308-311.
[4]陈军.基于DSP的高速公路车道偏离报警系统研究[D].天津:天津大学,2010.
[5]祝培,朱虹,钱学明,等.一种有雾天气图像景物影像的清晰化方法[J].中国图像图形学报,2004,9(1):124-128.
[6]LEVIN A,LISCHINSKI D,WEISS Y.A closed form solution to natural image matting[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2008,30(2):228-42.
[7]HE K,SUN J,TANG X.Guided image filtering.[J].IEEE Transactions on Software Engineering,2013,35(6):1397-1409.
[8]吴笑天,丁兴号,吴奎.基于暗通道理论的雾天图像复原的快速算法[J].长春理工大学学报(自然科学版),2012,35(1):100-104.
[9]COX L J.Optics of the atmosphere-scattering by molecules and particles[J].Journal of Modern Optics,1977,14(7):698-699.
[10]方雯,刘秉瀚.多尺度暗通道先验去雾算法[J].中国体视学与图像分析,2013(3):230-237.
[11]HE K,SOU J,TANG X.Single image haze removal using dark channel prior.[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2010,33(12):2341-2353.
[12]胡平.基于图像分割的交通图像快速去雾算法[J].计算机系统应用,2014,23(9):134-138.
[13]陆宗骐,梁诚.用Sobel算子细化边缘[J].中国图像图形学报,2000,5(6):516-520.
[14]金辉,吴乐林,陈慧岩,等.结构化道路车道线识别的一种改进算法[J].北京理工大学学报,2007,27(6):501-505.
[15]鞠乾翱.基于机器视觉的快速车道线辨识研究[D].上海:上海交通大学,2013.
[16]林广宇,魏朗,蹇小平.基于嵌入式的车辆偏离预警系统研究[J].电子设计工程,2010,18(8):26-28.
[17]魏朗,刘永涛.一种客运车辆车道偏离预警装置及其判断方法:中国,ZL201210057758.X[P].2014-06-18.