中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 人工智能与机器学习
Dual feature enhanced video super-resolution network based on low-light scenarios

文献类型：期刊论文

作者Zhang, Huan2; Cao, Yihao2; Cai, Jianghui1,2; Cai, Xingjuan2; Zhang, Wensheng3
刊名SIGNAL PROCESSING-IMAGE COMMUNICATION
出版日期2023-07-01
卷号115页码:8
ISSN号0923-5965
关键词Video super-resolution (VSR) Feature enhancement Information re-fusion Attention mechanism
DOI10.1016/j.image.2023.116984
通讯作者Cai, Xingjuan(caixingjuan@tyust.edu.cn)
英文摘要Video super-resolution (VSR) reconstruction technique aims to improve the spatiotemporal resolution of consecutive low resolution (LR) frames. Most of previous methods use the correlation of inter-frame to restore pixels. It is still a challenge to exploit intra-frame and inter-frame correlations to recover high-resolution (HR) frames, especially reconstruction of video in low-light conditions for sharp imaging results has been a bottleneck in current industrial environments. Therefore, this paper proposes a novel VSR network. Specifically, we first generate the hidden information of the current frame by using the appropriate combination of the front and rear frames. Then, a re-fusion block (RFB) is designed, which utilizes the hidden information to re-fuse with corresponding LR frame. After that, we integrate an improved dual attention mechanism (DAM) into network to extract more accurate feature of intra-frame without increasing the number of parameters. The technology has important practical significance in low-light and dim scenes, so we collect some industrial video sequences and make datasets to complete VSR task. Experimental results show that our model significantly outperforms state-of-the-art methods in performance.
资助项目National Natural Science Foundation of China[U1636220,61961160707,61976212] ; National Natural Sci-ence Foundation of China[YDZJSX2021A038] ; Sci-ence and Technology Development Foundation of the Central Guiding Local ; [U1931209]
WOS研究方向Engineering
语种英语
出版者ELSEVIER
WOS记录号WOS:001053124700001
资助机构National Natural Science Foundation of China ; National Natural Sci-ence Foundation of China ; Sci-ence and Technology Development Foundation of the Central Guiding Local
源URL[http://ir.ia.ac.cn/handle/173211/54104]  
专题精密感知与控制研究中心_人工智能与机器学习
通讯作者Cai, Xingjuan
作者单位1.North Univ China NUC, Taiyuan 030051, Shanxi, Peoples R China
2.Taiyuan Univ Sci & Technol TYUST, Taiyuan 030024, Shanxi, Peoples R China
3.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Huan,Cao, Yihao,Cai, Jianghui,et al. Dual feature enhanced video super-resolution network based on low-light scenarios[J]. SIGNAL PROCESSING-IMAGE COMMUNICATION,2023,115:8.
APA Zhang, Huan,Cao, Yihao,Cai, Jianghui,Cai, Xingjuan,&Zhang, Wensheng.(2023).Dual feature enhanced video super-resolution network based on low-light scenarios.SIGNAL PROCESSING-IMAGE COMMUNICATION,115,8.
MLA Zhang, Huan,et al."Dual feature enhanced video super-resolution network based on low-light scenarios".SIGNAL PROCESSING-IMAGE COMMUNICATION 115(2023):8.

入库方式： OAI收割

来源：自动化研究所

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。