A Single Image Derain Method Based on Residue Channel Decomposition in Edge Computing
文献类型：期刊论文
| 作者 | Cheng, Yong1; Yang, Zexuan5; Zhang, Wenjie3,4; Yang, Ling2; Wang, Jun1; Guan, Tingzhao1 |
| 刊名 | INTELLIGENT AUTOMATION AND SOFT COMPUTING
 |
| 出版日期 | 2023 |
| 卷号 | 37期号:2页码:1469-1482 |
| 关键词 | Single image derain method edge computing residue channel prior feature fusion module |
| ISSN号 | 1079-8587 |
| DOI | 10.32604/iasc.2023.038251 |
| 通讯作者 | Yang, Zexuan(yan8023mao@hotmail.com) |
| 英文摘要 | The numerous photos captured by low-price Internet of Things (IoT) sensors are frequently affected by meteorological factors, especially rainfall. It causes varying sizes of white streaks on the image, destroying the image texture and ruining the performance of the outdoor computer vision system. Existing methods utilise training with pairs of images, which is difficult to cover all scenes and leads to domain gaps. In addition, the network structures adopt deep learning to map rain images to rain-free images, failing to use prior knowledge effectively. To solve these problems, we introduce a single image derain model in edge computing that combines prior knowledge of rain patterns with the learning capability of the neural network. Specifically, the algorithm first uses Residue Channel Prior to filter out the rainfall textural features then it uses the Feature Fusion Module to fuse the original image with the background feature information. This results in a pre-processed image which is fed into Half Instance Net (HINet) to recover a high-quality rain-free image with a clear and accurate structure, and the model does not rely on any rainfall assumptions. Experimental results on synthetic and realworld datasets show that the average peak signal-to-noise ratio of the model decreases by 0.37 dB on the synthetic dataset and increases by 0.43 dB on the real-world dataset, demonstrating that a combined model reduces the gap between synthetic data and natural rain scenes, improves the generalization ability of the derain network, and alleviates the overfitting problem. |
| 资助项目 | National Natural Science Foundation of China[41975183] ; National Natural Science Foundation of China[41875184] ; State Key Laboratory of Resources and Environmental Information System |
| WOS研究方向 | Automation & Control Systems ; Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001032466700014 |
| 出版者 | TECH SCIENCE PRESS |
| 资助机构 | National Natural Science Foundation of China ; State Key Laboratory of Resources and Environmental Information System |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/195958]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Yang, Zexuan |
| 作者单位 | 1.Nanjing Univ Informat Sci & Technol, Sch Comp Sci, Nanjing 210044, Peoples R China 2.Nanjing Univ Informat Sci & Technol, Sch Appl Technol, Nanjing 210044, Peoples R China 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 4.Nanjing Univ Informat Sci & Technol, Sch Geog Sci, Nanjing 210044, Peoples R China 5.Nanjing Univ Informat Sci & Technol, Sch Automat, Nanjing 210044, Peoples R China |
| 推荐引用方式 GB/T 7714 | Cheng, Yong,Yang, Zexuan,Zhang, Wenjie,et al. A Single Image Derain Method Based on Residue Channel Decomposition in Edge Computing[J]. INTELLIGENT AUTOMATION AND SOFT COMPUTING,2023,37(2):1469-1482. |
| APA | Cheng, Yong,Yang, Zexuan,Zhang, Wenjie,Yang, Ling,Wang, Jun,&Guan, Tingzhao.(2023).A Single Image Derain Method Based on Residue Channel Decomposition in Edge Computing.INTELLIGENT AUTOMATION AND SOFT COMPUTING,37(2),1469-1482. |
| MLA | Cheng, Yong,et al."A Single Image Derain Method Based on Residue Channel Decomposition in Edge Computing".INTELLIGENT AUTOMATION AND SOFT COMPUTING 37.2(2023):1469-1482. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。