Low-Light Image Enhancement Based on Deep Symmetric Encoder–Decoder Convolutional Networks
A low-light image enhancement method based on a deep symmetric encoder−decoder convolutional network (LLED-Net) is proposed in the paper. In surveillance and tactical reconnaissance, collecting visual information from a dynamic environment and accurately processing that data is critical to...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/12/3/446 |
| _version_ | 1798041268263059456 |
|---|---|
| author | Qiming Li Haishen Wu Lu Xu Likai Wang Yueqi Lv Xinjie Kang |
| author_facet | Qiming Li Haishen Wu Lu Xu Likai Wang Yueqi Lv Xinjie Kang |
| author_sort | Qiming Li |
| collection | DOAJ |
| description | A low-light image enhancement method based on a deep symmetric encoder−decoder convolutional network (LLED-Net) is proposed in the paper. In surveillance and tactical reconnaissance, collecting visual information from a dynamic environment and accurately processing that data is critical to making the right decisions and ensuring mission success. However, due to the cost and technical limitations of camera sensors, it is difficult to capture clear images or videos in low-light conditions. In this paper, a special encoder−decoder convolution network is designed to utilize multi-scale feature maps and join jump connections to avoid gradient disappearance. In order to preserve the image texture as much as possible, by using structural similarity (SSIM) loss to train the model on the data sets with different brightness level, the model can adaptively enhance low-light images in low-light environments. The results show that the proposed algorithm provides significant improvements in quantitative comparison with RED-Net and several other representative image enhancement algorithms. |
| first_indexed | 2024-04-11T22:19:09Z |
| format | Article |
| id | doaj.art-611df34d9ac4495baa794ccd4cf9c21b |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-11T22:19:09Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-611df34d9ac4495baa794ccd4cf9c21b2022-12-22T04:00:16ZengMDPI AGSymmetry2073-89942020-03-0112344610.3390/sym12030446sym12030446Low-Light Image Enhancement Based on Deep Symmetric Encoder–Decoder Convolutional NetworksQiming Li0Haishen Wu1Lu Xu2Likai Wang3Yueqi Lv4Xinjie Kang5Department of Computer Science and Technology, Shanghai Maritime University, Shanghai 201306, ChinaDepartment of Computer Science and Technology, Shanghai Maritime University, Shanghai 201306, ChinaDepartment of Computer Science and Technology, Shanghai Maritime University, Shanghai 201306, ChinaDepartment of Computer Science and Technology, Shanghai Maritime University, Shanghai 201306, ChinaDepartment of Computer Science and Technology, Shanghai Maritime University, Shanghai 201306, ChinaDepartment of Computer Science and Technology, Shanghai Maritime University, Shanghai 201306, ChinaA low-light image enhancement method based on a deep symmetric encoder−decoder convolutional network (LLED-Net) is proposed in the paper. In surveillance and tactical reconnaissance, collecting visual information from a dynamic environment and accurately processing that data is critical to making the right decisions and ensuring mission success. However, due to the cost and technical limitations of camera sensors, it is difficult to capture clear images or videos in low-light conditions. In this paper, a special encoder−decoder convolution network is designed to utilize multi-scale feature maps and join jump connections to avoid gradient disappearance. In order to preserve the image texture as much as possible, by using structural similarity (SSIM) loss to train the model on the data sets with different brightness level, the model can adaptively enhance low-light images in low-light environments. The results show that the proposed algorithm provides significant improvements in quantitative comparison with RED-Net and several other representative image enhancement algorithms.https://www.mdpi.com/2073-8994/12/3/446deep convolutional neural networkconvolution–deconvolution residual networklow-light image enhancementsymmetric encoder–decoder network structure |
| spellingShingle | Qiming Li Haishen Wu Lu Xu Likai Wang Yueqi Lv Xinjie Kang Low-Light Image Enhancement Based on Deep Symmetric Encoder–Decoder Convolutional Networks Symmetry deep convolutional neural network convolution–deconvolution residual network low-light image enhancement symmetric encoder–decoder network structure |
| title | Low-Light Image Enhancement Based on Deep Symmetric Encoder–Decoder Convolutional Networks |
| title_full | Low-Light Image Enhancement Based on Deep Symmetric Encoder–Decoder Convolutional Networks |
| title_fullStr | Low-Light Image Enhancement Based on Deep Symmetric Encoder–Decoder Convolutional Networks |
| title_full_unstemmed | Low-Light Image Enhancement Based on Deep Symmetric Encoder–Decoder Convolutional Networks |
| title_short | Low-Light Image Enhancement Based on Deep Symmetric Encoder–Decoder Convolutional Networks |
| title_sort | low light image enhancement based on deep symmetric encoder decoder convolutional networks |
| topic | deep convolutional neural network convolution–deconvolution residual network low-light image enhancement symmetric encoder–decoder network structure |
| url | https://www.mdpi.com/2073-8994/12/3/446 |
| work_keys_str_mv | AT qimingli lowlightimageenhancementbasedondeepsymmetricencoderdecoderconvolutionalnetworks AT haishenwu lowlightimageenhancementbasedondeepsymmetricencoderdecoderconvolutionalnetworks AT luxu lowlightimageenhancementbasedondeepsymmetricencoderdecoderconvolutionalnetworks AT likaiwang lowlightimageenhancementbasedondeepsymmetricencoderdecoderconvolutionalnetworks AT yueqilv lowlightimageenhancementbasedondeepsymmetricencoderdecoderconvolutionalnetworks AT xinjiekang lowlightimageenhancementbasedondeepsymmetricencoderdecoderconvolutionalnetworks |