Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Wavefront Line-Scan Imaging Via a Single-Pixel Detector.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Non-Invasively Tracking an Arbitrary Deformable Object Through Scattering Media and Around Corners via Speckle Correlations.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Single-pixel phase imaging via a complex-valued Zernike basis.

Optics letters·2024
Same author

Tight focusing through scattering media via a Bessel-basis transmission matrix.

Optics letters·2024
Same author

Efficiently scanning a focus behind scattering media beyond memory effect by wavefront tilting and re-optimization.

Optics express·2023
Same author

Comparison of Common Algorithms for Single-Pixel Imaging via Compressed Sensing.

Sensors (Basel, Switzerland)·2023
Same journal

Denoising algorithm of Φ-OTDR systems based on adaptive fractional wavelet transform denoising.

Optics express·2026
Same journal

Millisecond photon-to-photon latency and high-speed volumetric projection system for optogenetics.

Optics express·2026
Same journal

Polarization-encoded coaxial structured light for high-precision 3D surface profilometry.

Optics express·2026
Same journal

Discrete freeform optical design based on collaborative optimization of point cloud and local normals.

Optics express·2026
Same journal

Ultrafast ghost imaging with 25 GHz speckle switching and wavelength-division multiplexing.

Optics express·2026
Same journal

Atomic vapor cells fabricated by femtosecond laser welding of standard-optical-quality glass.

Optics express·2026
See all related articles

Related Experiment Video

Updated: Nov 5, 2025

Quantitative Optical Microscopy: Measurement of Cellular Biophysical Features with a Standard Optical Microscope
14:09

Quantitative Optical Microscopy: Measurement of Cellular Biophysical Features with a Standard Optical Microscope

Published on: April 7, 2014

15.9K

DQN based single-pixel imaging.

Zhirun Wang, Wenjing Zhao, Aiping Zhai

    Optics Express
    |May 14, 2021
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a Deep Q-learning Network (DQN) to optimize sampling strategies for orthogonal transform based single-pixel imaging (OT-SPI). This AI-driven approach enhances imaging speed and quality without manual path planning.

    More Related Videos

    Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates
    10:18

    Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

    Published on: July 9, 2020

    3.1K
    Compact Quantum Dots for Single-molecule Imaging
    17:14

    Compact Quantum Dots for Single-molecule Imaging

    Published on: October 9, 2012

    18.4K

    Related Experiment Videos

    Last Updated: Nov 5, 2025

    Quantitative Optical Microscopy: Measurement of Cellular Biophysical Features with a Standard Optical Microscope
    14:09

    Quantitative Optical Microscopy: Measurement of Cellular Biophysical Features with a Standard Optical Microscope

    Published on: April 7, 2014

    15.9K
    Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates
    10:18

    Photodiode-Based Optical Imaging for Recording Network Dynamics with Single-Neuron Resolution in Non-Transgenic Invertebrates

    Published on: July 9, 2020

    3.1K
    Compact Quantum Dots for Single-molecule Imaging
    17:14

    Compact Quantum Dots for Single-molecule Imaging

    Published on: October 9, 2012

    18.4K

    Area of Science:

    • Computational imaging
    • Machine learning applications
    • Optical sensing technologies

    Background:

    • Orthogonal transform based single-pixel imaging (OT-SPI) traditionally relies on manually planned sampling paths.
    • Optimizing these paths is crucial for accelerating imaging speed and maintaining image quality.
    • Existing methods often face limitations due to the complexity of artificial path planning.

    Purpose of the Study:

    • To develop an optimized sampling strategy for OT-SPI using artificial intelligence.
    • To improve imaging speed and quality by automating the sampling path planning process.
    • To overcome the limitations of manual sampling path design in OT-SPI.

    Main Methods:

    • A Deep Q-learning Network (DQN) was employed to treat the sampling process as a sequential decision-making problem.
    • The network learns an optimal sampling strategy by receiving feedback on reconstructed image quality.
    • Simulations and experimental validations were conducted to verify the proposed method.

    Main Results:

    • The DQN successfully generated a near-optimal sampling strategy for OT-SPI.
    • The proposed method demonstrated significant improvements in imaging speed without substantial degradation in image quality.
    • Eliminated the need for manual intervention in sampling path planning.

    Conclusions:

    • The AI-driven sampling strategy using DQN offers an effective solution for enhancing OT-SPI performance.
    • This approach provides a direct and automated way to achieve optimal sampling, improving efficiency and reducing artifacts.
    • The findings pave the way for more advanced and efficient single-pixel imaging systems.