|Table of Contents|

Atmospheric visibility measurement based on image feature(PDF)


Research Field:
Publishing date:


Atmospheric visibility measurement based on image feature
Shi YuliWang BinBu Fan
School of Remote Sensing & Geomatics Engineering,Nanjing University of InformationScience & Technology,Nanjing 210044,China
visibility gradient contrast support vector machine random forest
In view of that the current methods of atmospheric visibility measurement based on the image have many problems,such as the complex erection of the target and difficult calculation of physical quantities,the atmospheric visibility measurement based on image features is proposed here. The gradient and contrast of the image are selected as image features. The support vector machine(SVM)algorithm and the random forest(RF)algorithm are used to build the model of the relationship between visibility values and image features. All results show that the gradient and contrast of the image are highly correlated with the atmospheric visibility value. The total number of sub-windows has effect on the accuracy of the model. The result of the SVM algorithm is typically better than that of the RF algorithm when the total number of sub-windows is less than 35. The sub-window with the size of 140×10 pixels performs best for the random forest algorithm. The R2 of the optimal model is 0.965 and the root-mean-square error is 658.13 m.


[1] 傅刚,李晓岚,魏娜. 大气能见度研究[J]. 中国海洋大学学报(自然科学版),2009,39(5):855-862.
Fu Gang,Li Xiaolan,Wei Na. Rewiew on the atmospheric visibility research[J]. Periodical of Ocean University of China,2009,39(5):855-862.
[2]邢向楠,崔岩梅,张富根,等. 能见度测量技术现状及发展趋势综述[J]. 计测技术,2010,30(5):15-20.
Xing Xiangnan,Cui Yanmei,Zhang Fugen,et al. Summary of present situation and development trend of visibility measurement technology[J]. Metrology & Measurement Technology,2010,30(5):15-20.
[3]陈文兵,张小磊. 基于图像边缘的能见度计算方法[J]. 微型电脑应用,2009,25(4):13-16.
Chen Wenbing,Zhang Xiaolei. The visibility calculation method based on the verge of real-time images[J]. Microcomputer Applications,2009,25(4):13-16.
[4]Park S,Lee D H,Kim Y G. Development of a transmissometer for meteorological visibility measurement[C]//Proceedings of Lasers and Electro-Optics Pacific Rim. Busan,South Korea:CLEO-PR,2015:1-2.
[5]韩明敏. 基于视频图像的高速公路能见度检测技术研究[D]. 北京:北京交通大学机械与电子控制工程学院,2016.
[6]Steffens C. Measurement of visibility by photographic photometry[J]. Ind Eng Chem,2002,41(11):2396-2399.
[7]Babari R,Hautière N,éric Dumont,et al. A model-driven approach to estimate atmospheric visibility with ordinary cameras[J]. Atmospheric Environment,2011,45(30):5316-5324.
[8]Hautière N,Tarel J P,Lavenant J,et al. Automatic fog detection and estimation of visibility distance through use of an onboard camera[J]. Machine Vision and Applications Journal,2006,17(1):8-20.
[9]谢兴生,陶善昌,周秀骥. 数字摄像法测量气象能见度[J]. 科学通报,1999,44(1):97-100.
Xie Xingsheng,Tao Shanchang,Zhou Xiuji. Measurement of meteorological visibility by digital camera method[J]. Chinese Science Bulletin,1999,44(1):97-100.
[10]项文书. 基于交通视频的能见度估计研究[D]. 上海:上海交通大学电子信息与电气工程学院,2014.
[11]曹世梅,武志强,巨辉. 基于雾的能见度黑体识别的研究[J]. 成都信息工程学院学报,2008,23(1):5-7.
Cao Shimei,Wu Zhiqiang,Ju Hui. A study of black box based on fog visibility[J]. Journal of Chengdu University of Imfornation Technology,2008,23(1):5-7.
[12]许茜,殷绪成,李岩,等. 基于图像理解的能见度测量方法[J]. 模式识别与人工智能,2013,26(6):543-551.
Xu Xi,Yin Xucheng,Li Yan,et al. Visibility measurement with image understanding[J]. Pattern Recognition and Artificial Intelligence,2013,26(6):543-551.
[13]Land E H. Recent advances in retinex theory and some implications for cortical computations:color vision and the natural image[J]. Proceedings of the National Academy of Sciences of the United States of America,1983,80(16):5163-5169.
[14]张雪峰,赵莉. 基于改进Retinex的图像增强算法[J]. 南京理工大学学报,2016,40(1):24-28.
Zhang Xuefeng,Zhao Li. Image enhancement algorithm based on improved Retinex[J]. Journal of Nanjing University of Science and Technology,2016,40(1):24-28.
[15]钟丽,吴关胜,谢斌,等. 基于图像分析的航道能见度评估算法研究[J]. 交通科技,2017(2):151-154.
Zhong Li,Wu Guansheng,Xie Bin,et al. Research on channel visibility evaluation algorithm based on image analysis[J]. Transportation Science & Technology,2017(2):151-154.
[16]Jourlin M,Pinoli J C. Logarithmic image processing:The mathematical and physical framework for the representation and processing of transmitted images[J]. Advances in Imaging & Electron Physics,2001,115(1):129-196.
[17]苏高利,邓芳萍. 关于支持向量回归机的模型选择[J]. 科技通报,2006,22(2):154-158.
Su Gaoli,Deng Fangping. Introduction to model selection of SVM regression[J]. Bulletin of Scinece and Technology,2006,22(2):154-158.
[18]Breiman L. Random forest[J]. Machine Learning,2001,45:5-32.
[19]Liaw A,Wiener M. Classification and regression by randomforest[J]. R News,2002,2(3):18-22.
[20]方匡南,吴见彬,朱建平,等. 随机森林方法研究综述[J]. 统计与信息论坛,2011,26(3):32-37.
Fang Kuangnan,Wu Jianbin,Zhu Jianping,et al. A review of technologies on random forests[J]. Statistics and Information Forum,2011,26(3):32-37.
[21]刘光徽,胡俊,於东军. 基于多视角特征组合与随机森林的G蛋白偶联受体与药物相互作用预测[J]. 南京理工大学学报,2016,40(1):1-9.
Liu Guanghui,Hu Jun,Yu Dongjun. Predicting GPCR-drug interactions with multi-view feature combination and random forest[J]. Journal of Nanjing University of Science and Technology,2016,40(1):1-9.


Last Update: 2018-10-30