In this paper, an end-to-end single image defogging algorithm is proposed which can achieve significant defogging effect under railway conditions. We present a method of fusing multi-scale feature information based on the residual network, which can extract more effective information at different scales. The method uses multi-scale convolution kernels to obtain different scale feature information, but it will increase computational cost and reduce the network depth. By increasing the bottleneck layer, we can deepen the residual network and ensure that the network can achieve better dehazing results. The proposed method can achieve better results than the state-of-the-art algorithms based on synthetic datasets and railway images.
Single Image Dehazing of Railway Images via Multi-scale Residual Networks
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2019 ; Qingdao, China October 25, 2019 - October 27, 2019
Proceedings of the 4th International Conference on Electrical and Information Technologies for Rail Transportation (EITRT) 2019 ; Chapter : 47 ; 503-512
2020-04-02
10 pages
Article/Chapter (Book)
Electronic Resource
English
Single Image Dehazing of Railway Images via Multi-scale Residual Networks
British Library Conference Proceedings | 2020
|Springer Verlag | 2021
|Enhanced densely dehazing network for single image haze removal under railway scenes
DOAJ | 2021
|Image Dehazing Network Based on Multi-scale Feature Extraction
TIBKAT | 2022
|