Compressive Reconstruction Based on Sparse Autoencoder Network Prior for Single-Pixel Imaging
文献类型:期刊论文
作者 | Zeng, Hong3; Dong, Jiawei1,2; Li, Qianxi1,2; Chen, Weining2; Dong, Sen2; Guo, Huinan2; Wang, Hao2 |
刊名 | PHOTONICS |
出版日期 | 2023-10 |
卷号 | 10期号:10 |
ISSN号 | 2304-6732 |
关键词 | sparse autoencoder network prior single-photon counting compressive imaging single-pixel imaging multi-channel prior numerical gradient descent |
DOI | 10.3390/photonics10101109 |
产权排序 | 2 |
英文摘要 | The combination of single-pixel imaging and single photon-counting technology enables ultra-high-sensitivity photon-counting imaging. In order to shorten the reconstruction time of single-photon counting, the algorithm of compressed sensing is used to reconstruct the underdetermined image. Compressed sensing theory based on prior constraints provides a solution that can achieve stable and high-quality reconstruction, while the prior information generated by the network may overfit the feature extraction and increase the burden of the system. In this paper, we propose a novel sparse autoencoder network prior for the reconstruction of the single-pixel imaging, and we also propose the idea of multi-channel prior, using the fully connected layer to construct the sparse autoencoder network. Then, take the network training results as prior information and use the numerical gradient descent method to solve underdetermined linear equations. The experimental results indicate that this sparse autoencoder network prior for the single-photon counting compressed images reconstruction has the ability to outperform the traditional one-norm prior, effectively improving the reconstruction quality. |
语种 | 英语 |
出版者 | MDPI |
WOS记录号 | WOS:001095296800001 |
源URL | [http://ir.opt.ac.cn/handle/181661/97014] |
专题 | 西安光学精密机械研究所_动态光学成像研究室 |
通讯作者 | Wang, Hao |
作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China 3.DFH Satellite Co Ltd, Beijing 100094, Peoples R China |
推荐引用方式 GB/T 7714 | Zeng, Hong,Dong, Jiawei,Li, Qianxi,et al. Compressive Reconstruction Based on Sparse Autoencoder Network Prior for Single-Pixel Imaging[J]. PHOTONICS,2023,10(10). |
APA | Zeng, Hong.,Dong, Jiawei.,Li, Qianxi.,Chen, Weining.,Dong, Sen.,...&Wang, Hao.(2023).Compressive Reconstruction Based on Sparse Autoencoder Network Prior for Single-Pixel Imaging.PHOTONICS,10(10). |
MLA | Zeng, Hong,et al."Compressive Reconstruction Based on Sparse Autoencoder Network Prior for Single-Pixel Imaging".PHOTONICS 10.10(2023). |
入库方式: OAI收割
来源:西安光学精密机械研究所
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。