Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 60, Issue 20, 2011003(2023)

Poisson Noise Suppression for Single-Photon Non-Line-of-Sight Imaging Based on Deep Learning

Min Tu1, Qiurong Yan1、*, Yongjian Zheng1, Xiancheng Xiong1, Quan Zou1, Qianling Dai1, and Xiaoqiang Lu2
Author Affiliations
  • 1School of Information Engineering, Nanchang University, Nanchang 330031, Jiangxi , China
  • 2Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710119, Shaanxi , China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (8)
    Equations (15)
    References (20)
    Cited By (4)
    Tools
    Paper Information
    Topics
    Figures & Tables(8)
    Experimental setup of the non-line-of-sight imaging system

    Fig. 1. Experimental setup of the non-line-of-sight imaging system

    Download full size
    Network structures. (a) Structure of AEF-Net; (b) sparse block; (c) feature enhancement block; (d) RNN block; (e) ConvRNNcell

    Fig. 2. Network structures. (a) Structure of AEF-Net; (b) sparse block; (c) feature enhancement block; (d) RNN block; (e) ConvRNNcell

    Download full size
    Reconstruction results of non-line-of-sight simulation at different photons.(a) Number of photons is 1×104; (b) number of photons is 5×104; (c) number of photons is 1×105; (d) number of photons is 5×105

    Fig. 3. Reconstruction results of non-line-of-sight simulation at different photons.(a) Number of photons is 1×104; (b) number of photons is 5×104; (c) number of photons is 1×105; (d) number of photons is 5×105

    Download full size
    Reconstruction results of non-line-of-sight simulation at different distances. (a) 0.5 m; (b) 1 m; (c) 2 m; (d) 4 m

    Fig. 4. Reconstruction results of non-line-of-sight simulation at different distances. (a) 0.5 m; (b) 1 m; (c) 2 m; (d) 4 m

    Download full size
    Comparison of average PSNR of networks trained by dataset with different noises

    Fig. 5. Comparison of average PSNR of networks trained by dataset with different noises

    Download full size
    Noise suppression results obtained by different AEF-Net; (a) Scan time of 512 s; (b) scan time of 1024 s; (c) scan time of 2048 s

    Fig. 6. Noise suppression results obtained by different AEF-Net; (a) Scan time of 512 s; (b) scan time of 1024 s; (c) scan time of 2048 s

    Download full size
    Comparison of average PSNR for different noise suppression algorithms

    Fig. 7. Comparison of average PSNR for different noise suppression algorithms

    Download full size
    Noise suppression results of different algorithms. (a) Scan time of 512 s; (b) scan time of 1024 s; (c) scan time of 2048 s

    Fig. 8. Noise suppression results of different algorithms. (a) Scan time of 512 s; (b) scan time of 1024 s; (c) scan time of 2048 s

    Download full size
    Tools

    Get Citation

    Copy Citation Text

    Min Tu, Qiurong Yan, Yongjian Zheng, Xiancheng Xiong, Quan Zou, Qianling Dai, Xiaoqiang Lu. Poisson Noise Suppression for Single-Photon Non-Line-of-Sight Imaging Based on Deep Learning[J]. Laser & Optoelectronics Progress, 2023, 60(20): 2011003

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Imaging Systems

    Received: Nov. 4, 2022

    Accepted: Dec. 28, 2022

    Published Online: Sep. 28, 2023

    The Author Email: Qiurong Yan (yanqiurong@ncu.edu.cn)

    DOI:10.3788/LOP222969

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology