College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China;
Department of Applied Physics and Electronics, Umeå University, 90187 Umeå, Sweden;
Sensors (Basel). 2018 Jan 29;18(2):392. doi: 10.3390/s18020392.
Low visibility on expressways caused by heavy fog and haze is a main reason for traffic accidents. Real-time estimation of atmospheric visibility is an effective way to reduce traffic accident rates. With the development of computer technology, estimating atmospheric visibility via computer vision becomes a research focus. However, the estimation accuracy should be enhanced since fog and haze are complex and time-varying. In this paper, a total bounded variation (TBV) approach to estimate low visibility (less than 300 m) is introduced. Surveillance images of fog and haze are processed as blurred images (pseudo-blurred images), while the surveillance images at selected road points on sunny days are handled as clear images, when considering fog and haze as noise superimposed on the clear images. By combining image spectrum and TBV, the features of foggy and hazy images can be extracted. The extraction results are compared with features of images on sunny days. Firstly, the low visibility surveillance images can be filtered out according to spectrum features of foggy and hazy images. For foggy and hazy images with visibility less than 300 m, the high-frequency coefficient ratio of Fourier (discrete cosine) transform is less than 20%, while the low-frequency coefficient ratio is between 100% and 120%. Secondly, the relationship between TBV and real visibility is established based on machine learning and piecewise stationary time series analysis. The established piecewise function can be used for visibility estimation. Finally, the visibility estimation approach proposed is validated based on real surveillance video data. The validation results are compared with the results of image contrast model. Besides, the big video data are collected from the Tongqi expressway, Jiangsu, China. A total of 1,782,000 frames were used and the relative errors of the approach proposed are less than 10%.
高速公路上的低能见度是由大雾和霾引起的，这是交通事故的主要原因。实时估计大气能见度是降低交通事故率的有效方法。随着计算机技术的发展，通过计算机视觉估计大气能见度成为研究热点。然而，由于雾和霾复杂且随时间变化，估计的准确性需要提高。本文提出了一种基于全变差（TBV）的低能见度（小于 300m）估计方法。将雾和霾的监测图像作为模糊图像（伪模糊图像）进行处理，而在晴天选择的道路点的监测图像则作为清晰图像进行处理，此时将雾和霾视为叠加在清晰图像上的噪声。通过结合图像频谱和 TBV，可以提取雾和霾图像的特征。将提取结果与晴天图像的特征进行比较。首先，根据雾和霾图像的频谱特征，可以对低能见度监测图像进行过滤。对于能见度小于 300m 的雾和霾图像，傅里叶（离散余弦）变换的高频系数比小于 20%，而低频系数比在 100%到 120%之间。其次，基于机器学习和分段平稳时间序列分析，建立了 TBV 与实际能见度的关系。建立的分段函数可用于能见度估计。最后，基于真实监控视频数据验证了所提出的能见度估计方法。验证结果与图像对比度模型的结果进行了比较。此外，还从中国江苏的通启高速公路收集了大量视频数据。共使用了 1782000 帧，提出的方法的相对误差小于 10%。
