期刊
APPLIED SOFT COMPUTING
卷 102, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.asoc.2020.106884
关键词
Image dehazing; Deep learning; Feature extraction
资金
- National Natural Science Foundation of China [61972187, 61772254]
- Fuzhou Science and Technology Project [2020-RC-186]
- Natural Science Foundation of Fujian Province [2020J02024, 2019J01756]
- Government Guiding Regional Science and Technology Development [2019L3009]
- Fujian Provincial Leading Project [2019H0025]
- Open Project Program of Fujian Engineering and Research Center of New Chinese Lacquer Materials at Minjiang University [323030020102]
This paper proposes an end-to-end U-Net based residual network to enhance visibility of hazy images, which utilizes hybrid convolution and ResNet building blocks to prevent gradient vanishing, leading to significant improvement in image dehazing effect.
Low visibility in hazy weather causes the loss of image details in digital images captured by some imaging devices such as monitors. This paper proposes an end-to-end U-Net based residual network (URNet) to improve the visibility of hazy images. The encoder module of URNet uses hybrid convolution combining standard convolution with dilated convolution to expand the receptive field for extracting image features with more details. The URNet embeds several building blocks of ResNet into the junction between the encoder module and the decoder module. This prevents network performance degradation due to the vanishing gradient. After considering large absolute difference on image saturation and value components between hazy images and haze-free images in the HSV color space, the URNet defines a new loss function to better guide the network training. Experimental results on synthetic hazy images and real hazy images show that the URNet significantly improves the image dehazing effect compared to the state-of-the-art methods. (C) 2020 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据