Affiliation:
1. Key Laboratory of Transportation Meteorology, China Meteorological Administration, Nanjing 210019, China
2. Jiangsu Provincial Meteorological Service Center, Nanjing 210019, China
Abstract
Poor visibility has a significant impact on road safety and can even lead to traffic accidents. The traditional means of visibility monitoring no longer meet the current needs in terms of temporal and spatial accuracy. In this work, we propose a novel deep network architecture for estimating the visibility directly from highway surveillance images. Specifically, we employ several image feature extraction methods to extract detailed structural, spectral, and scene depth features from the images. Next, we design a multi-scale fusion network to adaptively extract and fuse vital features for the purpose of estimating visibility. Furthermore, we create a real-scene dataset for model learning and performance evaluation. Our experiments demonstrate the superiority of our proposed method to the existing methods.
Funder
China Meteorological Administration Innovation and Development Project
China Meteorological Administration Joint Research Project on Meteorological Capacity Enhancement
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference23 articles.
1. Application of artificial neural network forecasts to predict fog at Canberra International Airport;Fabbian;Weather Forecast.,2007
2. Kwon, T.M. (2004, July 01). Atmospheric Visibility Measurements Using Video Cameras: Relative Visibility. Retrieved from the University of Minnesota Digital Conservancy. Available online: https://hdl.handle.net/11299/1027.
3. Liaw, J.J., Lian, S.B., Huang, Y.F., and Chen, R.C. (2009, January 2–4). Atmospheric visibility monitoring using digital image analysis techniques. Proceedings of the International Conference on Computer Analysis of Images and Patterns, Münster, Germany.
4. Investigation of urban atmospheric visibility by high-frequency extraction: Model development and field test;Luo;Atmos. Environ.,2005
5. Babari, R., Hautière, N., Dumont, E., Papelard, J.P., and Paparoditis, N. (2011, January 6–13). Computer vision for the remote sensing of atmospheric visibility. Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCV Workshops), Barcelona, Spain.