Open AccessAttention‐based end‐to‐end image defogging network
Author(s) -
Yang Yan,
Zhang Chen,
Jiang Peipei,
Yue Hui
Publication year - 2020
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2020.1128
Subject(s) - benchmark (surveying) , visibility , feature (linguistics) , computer science , image (mathematics) , convolution (computer science) , artificial intelligence , channel (broadcasting) , image restoration , residual , backbone network , computer vision , pattern recognition (psychology) , algorithm , image processing , artificial neural network , telecommunications , linguistics , philosophy , physics , geodesy , optics , geography
Aiming at the problem that the traditional prior information‐based defogging algorithm fails in some special scenarios, an end‐to‐end convolutional defogging network based on attention mechanism is proposed. The network consists of two modules: parameter estimation and image restoration. First, multi‐scale convolution is used to extract image feature information. Residual network and skip connection methods are used to improve the utilisation rate of shallow network feature information. Secondly, the channel domain attention is used to add weight to the feature image input from the previous network and select useful feature information. Finally, the atmospheric visibility model is combined to achieve image visibility restoration. The experimental results show that the proposed algorithm can effectively improve the visibility of the image and the restoration effect is natural. The objective evaluation index of the benchmark datasets also shows the effectiveness of the algorithm.