Deep Convolutional Neural Network for Fog Detection
Fog detection has becomes more and more important in recent years, real-time monitoring information is very beneficial for people to arrange production and life. In this paper, based on meterological satellite data (Himawari-8 standard data, HSD8), Covolutional Neural Network (CNN) is used to detect fog. Since HSD8 consists of 16 channels, the original CNN is extended to multiple channels for HSD8. Multiple Channels CNN (MCCNN) can make the full exploitation of spatial and spectral information effectively. A dataset is created from Anhui Area which consists of ground station data and grid data. Different image sizes and convolutional kernels are used to validate the proposed methods. The experimental results show that the proposed method achieves 91.87% accuracy.
KeywordsFog CNN Detection Himawari-8
This work was supported by Jiangsu Province Meteorological Bureau Bei Ji Ge grant Nos. BJG201707, Anhui Province Meteorological Bureau meteorologist special grant Nos. KY201704, Anhui Provincial Natural Science Foundation (grant number 1608085MF136).
- 1.Linping, S., Chi, X.: The analysis and forecast of fog in North China Plain. Meteorol. Monthly (1995)Google Scholar
- 2.Anderson, R.K., Farr, G.R., Ashman, J.P., Smith, A.H., Ritter, L.F.: Application of meteorological satellite data in analysis and forecasting. J. Pharm. Pharmacol. 38, 107–112 (1974)Google Scholar
- 5.Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. Computer Science, pp. 357–361 (2014)Google Scholar
- 6.Szegedy, C., Toshev, A., Erhan, D.: Deep neural networks for object detection. Adv. Neural. Inf. Process. Syst. 26, 2553–2561 (2013)Google Scholar
- 8.Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
- 10.Wang, J.,Yang, Y., Mao, J., Huang, Z., Huang, C., Xu, W.: CNN-RNN: a unified framework for multi-label image classification, pp. 2285–2294 (2016)Google Scholar
- 11.Agarwal, A., El-Ghazawi, T., El-Askary, H., Le-Moigne, J.: Efficient hierarchical-PCA dimension reduction for hyperspectral imagery. In: IEEE International Symposium on Signal Processing and Information Technology, pp. 353–356 (2008)Google Scholar