☆ 4.5 Article

High turbidity underwater single-pixel imaging based on Unet plus plus and attention mechanism at a low sampling

OPTICS COMMUNICATIONS (2024)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Optics

High-turbidity underwater active single-pixel imaging based on generative adversarial networks with double Attention U-Net under low sampling rate

Wei Feng et al.

Summary: In this paper, an underwater active SPI system based on generative adversarial network with double Attention U-Net is proposed to reconstruct the underwater target image with high turbidity under low sampling rates. The proposed method shows relatively strong reconstruction ability and generalization, and the PSNR and SSIM can be respectively improved by 0.75 times and 3 times compared with compressed sensing SPI.

OPTICS COMMUNICATIONS (2023)

添加到收藏夹

Article Optics

Active mode single-pixel imaging through strong scattering media via least squares conditional generative adversarial networks under low sampling rates

Wei Feng et al.

Summary: In this paper, an active mode single-pixel imaging (SPI) method based on a least-squares conditional generation adversarial network is proposed, which achieves imaging through strong scattering media at a low sampling rate. The proposed network's generator uses a U-shaped structure with an attention mechanism and integrates squeeze-and-excitation blocks and residual blocks to better learn target information in the scattering environment. The total loss functions of least-square loss, content loss, and mean structural similarity loss are used for the first time to stabilize the training process and improve image reconstruction quality under strong scattering conditions at low sampling rates. This method promotes the development of SPI technology and has important applications in optical scattering medium imaging.

JOURNAL OF OPTICS-INDIA (2023)

添加到收藏夹

Article Optics

Fourier single pixel imaging reconstruction method based on the U-net and attention mechanism at a low sampling rate

Pengfei Jiang et al.

Summary: This paper proposes a method to improve the quality of FSI reconstruction at low sampling rates by parallel fusing the U-net and attention mechanism. A generative adversarial network structure is built to recover high-resolution target images from low-resolution FSI reconstruction results under low sampling rate conditions. Experimental results demonstrate that the proposed method achieves better quality and higher resolution results at low sampling rates.

OPTICS EXPRESS (2022)

添加到收藏夹

Article Optics

Imaging in turbid water based on a Hadamard single-pixel imaging system

Xin Yang et al.

Summary: Underwater imaging is challenging due to noise and scattering in water. Conventional optical methods struggle with low sensitivity, geometric aberrations, and narrow detector spectra. Single-pixel imaging offers promise in poor visibility, but faces challenges in highly turbid water. The proposed Hadamard single-pixel imaging system shows superior performance in turbid water, with higher resolution and anti-scattering capabilities compared to existing SPI techniques.

OPTICS EXPRESS (2021)

添加到收藏夹

Article Optics

Sub-Nyquist computational ghost imaging with deep learning

Heng Wu et al.

OPTICS EXPRESS (2020)

添加到收藏夹

Article Optics

Optimal compressive multiphoton imaging at depth using single-pixel detection

Philip Wijesinghe et al.

OPTICS LETTERS (2019)

添加到收藏夹

Article Multidisciplinary Sciences

Ghost Imaging Based on Deep Learning

Yuchen He et al.

SCIENTIFIC REPORTS (2018)

添加到收藏夹

Article Optics

Underwater computational ghost imaging

Mingnan Le et al.

OPTICS EXPRESS (2017)

添加到收藏夹

Article Optics

Hadamard single-pixel imaging versus Fourier single-pixel imaging

Zibang Zhang et al.

OPTICS EXPRESS (2017)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Massively parallel simulator of optical coherence tomography of inhomogeneous turbid media

Siavash Malektaji et al.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2017)

添加到收藏夹

Article Optics

Single-pixel compressive diffractive imaging

Ryoichi Horisaki et al.

APPLIED OPTICS (2017)

添加到收藏夹

Article Physics, Multidisciplinary

Spatiotemporal Coherent Control of Light through a Multiple Scattering Medium with the Multispectral Transmission Matrix

Mickael Mounaix et al.

PHYSICAL REVIEW LETTERS (2016)

添加到收藏夹

Article Optics

Fast reconstructed and high-quality ghost imaging with fast Walsh-Hadamard transform

Le Wang et al.

PHOTONICS RESEARCH (2016)

添加到收藏夹

Article Multidisciplinary Sciences

Smart optical coherence tomography for ultra-deep imaging through highly scattering media

Amaury Badon et al.

SCIENCE ADVANCES (2016)

添加到收藏夹

Article Optics

Feedback-based wavefront shaping

Ivo M. Vellekoop

OPTICS EXPRESS (2015)

添加到收藏夹

Article Multidisciplinary Sciences

Imaging with a small number of photons

Peter A. Morris et al.

NATURE COMMUNICATIONS (2015)

添加到收藏夹

Article Optics

Non-invasive single-shot imaging through scattering layers and around corners via speckle correlations

Ori Katz et al.

NATURE PHOTONICS (2014)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.