高速公路夜间大雾图像特征及其识别
|
摘要
基于高速公路夜间交通监控图像,选择其附近能见度自动监测数据作为图像是否有大雾的标准,分析有雾或无雾环境对光源及其成像的影响,提取相应的特征值,利用支持向量机的方法建立了大雾识别模型。结果表明:大雾存在时空气消光系数增大,LED电子显示屏、车灯等光源在图像上呈现出亮度减弱而梯度小,散射较明显的特点;纹理特征表明有雾时图片纹理简单、纹理较浅分布均匀,像素之间相关性大,无雾时则反之;模型评估得出临界成功指数为0.74,虚警率为0.18,有较好的识别效果。
Based on the nighttime traffic monitoring images,the observation visibility data of nearby automatic stations are chosen as the criteria for whether the image is foggy.The effects of foggy and fogfree environments on light sources,and their imaging are analyzed;and the corresponding features are extracted.A recognition model is established to identify fogs by the method of the support vector machine.Results show that,due to the increase of air extinction coefficient in the presence of fogs,the light from LED electronic display or cars and their reflection in the monitoring image weaken.The image gradient,texture and other parameters are obviously different in foggy and clear weather.The critical success index of the model evaluation result is 0.74,and the false alarm rate is 0.18,which meet the needs of fog monitoring at night.
Based on the nighttime traffic monitoring images,the observation visibility data of nearby automatic stations are chosen as the criteria for whether the image is foggy.The effects of foggy and fogfree environments on light sources,and their imaging are analyzed;and the corresponding features are extracted.A recognition model is established to identify fogs by the method of the support vector machine.Results show that,due to the increase of air extinction coefficient in the presence of fogs,the light from LED electronic display or cars and their reflection in the monitoring image weaken.The image gradient,texture and other parameters are obviously different in foggy and clear weather.The critical success index of the model evaluation result is 0.74,and the false alarm rate is 0.18,which meet the needs of fog monitoring at night.
引文
[1]冯明学,顾松山,卞光辉.高速公路浓雾监测预警系统[J].中国公路学报,2004,17(3):92-97.
[2]曲晓黎,孟凯,赵娜,等.恶劣天气对河北高速公路通行影响分析[J].气象科技,2016,44(3):447-452.
[3]王敏,张世国,汪玮,等.前向散射式能见度仪示值对比及标定方法研究[J].气象科技,2017,45(2):217-222.
[4]刘承晓,周建平,翟振芳,等.2011-2015年安徽省高速公路低能见度变化特征[J].气象科技,2017,45(5):858-863.
[5]李勃,董蓉,陈启美.无需人工标记的视频对比度道路能见度检测[J].计算机辅助设计与图形学学报,2009,21(11):1575-1582.
[6]安明伟,陈启美,郭宗良.基于路况视频的气象能见度检测方法与系统设计[J].仪器仪表学报,2010,31(5):1148-1153.
[7]He K,Sun J,Tang X.Single image haze removal using dark channel prior[J].Pattern Analysis and Machine Intelligence,IEEE Transactions,2011,33(12),2341-2353.
[8]郭尚书,齐文新,齐宇.基于暗通道先验的视频能见度测量方法[J].计算机与数字工程,2014,42(4):694-697.
[9]李勇军,张玉钧,周毅,等.基于分水岭分割算法夜间能见度仪的图像处理方法研究[J].大气与环境光学学报,2012,7(2):131-138.
[10]林建,杨贵民,毛冬艳.我国大雾的时空分布特征及其发生的环流形势[J].气候与环境研究,2008,13(2):171-178.
[11]董德保,方海涛.一次低能见度事件中大气颗粒物的微物理特征[J].气象科技,2015,43(5):939-944.
[12]邓学良,石春娥,吴必文,等.1970~2009年安徽省大雾气候特征分析[J].长江流域资源与环境,2015,24(12):2152-2134.
[13]袁成松,卞光辉,冯民学,等.高速公路上低能见度的监测与预报[J].气象,2013,29(11):36-40.
[14]Nebuloni R.Empirical relationships between extinction coefficient and visibility in fog[J].APPLIED OPTICS,2005,44(18):3795-3804.
[15]白雪冰,王克奇,王辉.基于灰度共生矩阵的木材纹理分类方法的研究[J].哈尔滨工业大学学报,2005,37(12):1667-1670.
[16]周云龙,陈飞,孙斌.基于灰度共生矩阵和支持向量机的气液两相流流型识别[J].化工学报,2007,58(9):2231-2237.
[17]张策,臧淑英,金竺,等.基于支持向量机的扎龙湿地遥感分类研究[J].湿地科学,2011,9(3):263-269.
[18]陈永义,俞小鼎,高学浩,等.处理非线性分类和回归问题的一种新方法(I)---支持向量机方法简介[J].应用气象学报,2004,15(3):345-354.
[19]林剑艺,程春田.支持向量机在中长期径流预报中的应用[J].水利学报,2006,37(6):681-686.
[20]Chang C C,Lin C J.LIBSVM:a library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2:27:1-27.
[2]曲晓黎,孟凯,赵娜,等.恶劣天气对河北高速公路通行影响分析[J].气象科技,2016,44(3):447-452.
[3]王敏,张世国,汪玮,等.前向散射式能见度仪示值对比及标定方法研究[J].气象科技,2017,45(2):217-222.
[4]刘承晓,周建平,翟振芳,等.2011-2015年安徽省高速公路低能见度变化特征[J].气象科技,2017,45(5):858-863.
[5]李勃,董蓉,陈启美.无需人工标记的视频对比度道路能见度检测[J].计算机辅助设计与图形学学报,2009,21(11):1575-1582.
[6]安明伟,陈启美,郭宗良.基于路况视频的气象能见度检测方法与系统设计[J].仪器仪表学报,2010,31(5):1148-1153.
[7]He K,Sun J,Tang X.Single image haze removal using dark channel prior[J].Pattern Analysis and Machine Intelligence,IEEE Transactions,2011,33(12),2341-2353.
[8]郭尚书,齐文新,齐宇.基于暗通道先验的视频能见度测量方法[J].计算机与数字工程,2014,42(4):694-697.
[9]李勇军,张玉钧,周毅,等.基于分水岭分割算法夜间能见度仪的图像处理方法研究[J].大气与环境光学学报,2012,7(2):131-138.
[10]林建,杨贵民,毛冬艳.我国大雾的时空分布特征及其发生的环流形势[J].气候与环境研究,2008,13(2):171-178.
[11]董德保,方海涛.一次低能见度事件中大气颗粒物的微物理特征[J].气象科技,2015,43(5):939-944.
[12]邓学良,石春娥,吴必文,等.1970~2009年安徽省大雾气候特征分析[J].长江流域资源与环境,2015,24(12):2152-2134.
[13]袁成松,卞光辉,冯民学,等.高速公路上低能见度的监测与预报[J].气象,2013,29(11):36-40.
[14]Nebuloni R.Empirical relationships between extinction coefficient and visibility in fog[J].APPLIED OPTICS,2005,44(18):3795-3804.
[15]白雪冰,王克奇,王辉.基于灰度共生矩阵的木材纹理分类方法的研究[J].哈尔滨工业大学学报,2005,37(12):1667-1670.
[16]周云龙,陈飞,孙斌.基于灰度共生矩阵和支持向量机的气液两相流流型识别[J].化工学报,2007,58(9):2231-2237.
[17]张策,臧淑英,金竺,等.基于支持向量机的扎龙湿地遥感分类研究[J].湿地科学,2011,9(3):263-269.
[18]陈永义,俞小鼎,高学浩,等.处理非线性分类和回归问题的一种新方法(I)---支持向量机方法简介[J].应用气象学报,2004,15(3):345-354.
[19]林剑艺,程春田.支持向量机在中长期径流预报中的应用[J].水利学报,2006,37(6):681-686.
[20]Chang C C,Lin C J.LIBSVM:a library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology,2011,2:27:1-27.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |