Single Pixel Imaging Based on Multiple Prior Deep Unfolding Network

Single-pixel imaging (SPI), an imaging technique based on the theory of compressed sensing, is limited in real-time imaging and high-resolution images due to its relatively slow imaging speed. In recent years, deep unfolding network compressed sensing reconstruction algorithms based on deep learning...

Full description

Saved in:
Bibliographic Details
Published in:IEEE photonics journal 2024-08, Vol.16 (4), p.1-10
Main Authors: Zou, Quan, Yan, Qiurong, Dai, Qianling, Wang, Ao, Yang, Bo, Li, Yi, Yan, Jinwei
Format: Article
Language:English
Subjects:
Algorithms
Compressed sensing
deep unfolding network
Image quality
Image reconstruction
Image resolution
Imaging
Imaging techniques
Iterative algorithms
joint optimization
Machine learning
multiple prior information
Optimization
Pixels
Radar imaging
Real time
Reconstruction algorithms
Sampling
Single pixel imaging
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Single-pixel imaging (SPI), an imaging technique based on the theory of compressed sensing, is limited in real-time imaging and high-resolution images due to its relatively slow imaging speed. In recent years, deep unfolding network compressed sensing reconstruction algorithms based on deep learning have proven to be an effective solution for faster and higher quality image reconstruction. However, existing deep unfolding networks mainly rely on a single piece of a priori information and may ignore other intrinsic structures of the image. Therefore, in this paper, we propose a deep unfolding network (MPDU-Net) that incorporates multiple prior information. To effectively fuse multiple prior information, we propose three different fusion strategies in the deep reconstruction sub-network. An unbiased convolutional layer is used to simulate the sampling reconstruction process to achieve joint reconstruction for effective removal of block artifacts. The sampling matrix is input into the deep reconstruction sub-network as a learnable parameter to achieve joint optimization of sampling reconstruction. Simulation and practical experimental results show that the proposed network outperforms existing compressed sensing reconstruction algorithms based on deep unfolding networks.
ISSN:1943-0655
1943-0647
DOI:10.1109/JPHOT.2024.3420787