Joint Superresolution And Rectification For Solar Cell Inspection

• doi: 10.1109/JPHOTOV.2021.3072229
• title: Joint Superresolution and Rectification for Solar Cell Inspection
• publisher: IEEE
• isbn:
• issn: 2156-3403
• rank: 2841
• access_type: LOCKED
• content_type: Journals
• abstract: Visual inspection of solar modules is an important monitoring facility in photovoltaic power plants. Since a single measurement of fast CMOS sensors is limited in spatial resolution and often not sufficient to reliably detect small defects, we apply multiframe superresolution (MFSR) to a sequence of low-resolution measurements. In addition, the rectification and removal of lens distortion simplifies subsequent analysis. Therefore, we propose to fuse this preprocessing with standard MFSR algorithms. This is advantageous, because we omit a separate processing step, the motion estimation becomes more stable and the spacing of high-resolution pixels on the rectified module image becomes uniform w.r.t. the module plane, regardless of perspective distortion. We present a comprehensive user study showing that MFSR is beneficial for defect recognition by human experts and that the proposed method performs better than the state-of-the-art. Furthermore, we apply automated crack segmentation and show that the proposed method performs 3× better than bicubic upsampling and 2× better than the state-of-the-art for automated inspection.
• article_number: 9422363
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9422363
• html_url: https://ieeexplore.ieee.org/document/9422363/
• abstract_url: https://ieeexplore.ieee.org/document/9422363/
• publication_title: IEEE Journal of Photovoltaics
• conference_location:
• conference_dates:
• publication_number: 5503869
• is_number: 9461202
• publication_year: 2021
• publication_date: July 2021
• start_page: 1051
• end_page: 1058
• citing_paper_count: 0
• citing_patent_count: 0
• download_count: 196
• insert_date: 20210503
• index_terms:
  • ieee_terms:
    • Photovoltaic cells
    • Image reconstruction
    • Cameras
    • Nonlinear distortion
    • Computational modeling
    • Superresolution
    • Lenses
  • author_terms:
    • Automated inspection
    • solar cell
    • superresolution (SR)
  • dynamic_index_terms:
    • Solar Cells
    • Joint Super-resolution
    • Spatial Resolution
    • User Study
    • Image Distortion
    • Lens Distortion
    • Radial Distortion
    • Image Deformation
    • Human Experts
    • Motion Estimation
    • Solar Power Plants
    • Solar Farms
    • Photovoltaic Farm
    • Photovoltaic Power Stations
    • Photovoltaic Power Plants
    • Automatic Inspection
    • Perspective Distortion
    • Deep Learning
    • Image Processing
    • High-resolution Images
    • Motion Model
    • Point Spread Function
    • Model Projections
    • Depth Camera
    • RGB-D Camera
    • Depth Sensor
    • 3D Camera
    • Low-resolution Images
    • Reconstruction Approach
    • Motion Blur
    • Crack Detection
    • Camera Intrinsic Parameters
    • Crucial Details
    • Coefficient Of Concordance
    • Kendall’s W
    • Kendall’s Coefficient Of Concordance
    • Camera Pose
    • Motion Vector
    • Magnification Factor
• authors:
  • Author Name: Mathis Hoffmann
    Affiliation: Pattern Recognition Lab and the Institute Materials for Electronics and Energy Technology, University of Erlangen–Nürnberg, Erlangen, Germany
    Author URL: https://ieeexplore.ieee.org/author/37086382480
    ID: 37086382480
    Order: 1
    Author Affiliations:
    • Pattern Recognition Lab and the Institute Materials for Electronics and Energy Technology, University of Erlangen–Nürnberg, Erlangen, Germany
  • Author Name: Thomas Köhler
    Affiliation: e.solutions GmbH, Erlangen, Germany
    Author URL: https://ieeexplore.ieee.org/author/37268046800
    ID: 37268046800
    Order: 2
    Author Affiliations:
    • e.solutions GmbH, Erlangen, Germany
  • Author Name: Bernd Doll
    Affiliation: Institute Materials for Electronics and Energy Technology, University of Erlangen–Nürnberg, Erlangen, Germany
    Author URL: https://ieeexplore.ieee.org/author/37086524537
    ID: 37086524537
    Order: 3
    Author Affiliations:
    • Institute Materials for Electronics and Energy Technology, University of Erlangen–Nürnberg, Erlangen, Germany
    • Forschungszentrum Jülich GmbH, Helmholtz Institut Erlangen-Nürnberg, Erlangen, Germany
    • Graduate School in Advanced Optical Technologies, Erlangen, Germany
  • Author Name: Frank Schebesch
    Affiliation: Pattern Recognition Lab, University of Erlangen–Nürnberg, Erlangen, Germany
    Author URL: https://ieeexplore.ieee.org/author/37085660658
    ID: 37085660658
    Order: 4
    Author Affiliations:
    • Pattern Recognition Lab, University of Erlangen–Nürnberg, Erlangen, Germany
  • Author Name: Florian Talkenberg
    Affiliation: Greateyes GmbH, Berlin, Germany
    Author URL: https://ieeexplore.ieee.org/author/37088893737
    ID: 37088893737
    Order: 5
    Author Affiliations:
    • Greateyes GmbH, Berlin, Germany
  • Author Name: Ian Marius Peters
    Affiliation: Forschungszentrum Jülich GmbH, Helmholtz Institut Erlangen-Nürnberg, Erlangen, Germany
    Author URL: https://ieeexplore.ieee.org/author/37085374385
    ID: 37085374385
    Order: 6
    Author Affiliations:
    • Forschungszentrum Jülich GmbH, Helmholtz Institut Erlangen-Nürnberg, Erlangen, Germany
  • Author Name: Christoph J. Brabec
    Affiliation: Institute Materials for Electronics and Energy Technology, University of Erlangen–Nürnberg, Erlangen, Germany
    Author URL: https://ieeexplore.ieee.org/author/37314031100
    ID: 37314031100
    Order: 7
    Author Affiliations:
    • Institute Materials for Electronics and Energy Technology, University of Erlangen–Nürnberg, Erlangen, Germany
    • Graduate School in Advanced Optical Technologies, Erlangen, Germany
  • Author Name: Andreas Maier
    Affiliation: Pattern Recognition Lab, University of Erlangen–Nürnberg, Erlangen, Germany
    Author URL: https://ieeexplore.ieee.org/author/37703448300
    ID: 37703448300
    Order: 8
    Author Affiliations:
    • Pattern Recognition Lab, University of Erlangen–Nürnberg, Erlangen, Germany
    • Graduate School in Advanced Optical Technologies, Erlangen, Germany
  • Author Name: Vincent Christlein
    Affiliation: Pattern Recognition Lab, University of Erlangen–Nürnberg, Erlangen, Germany
    Author URL: https://ieeexplore.ieee.org/author/37845711100
    ID: 37845711100
    Order: 9
    Author Affiliations:
    • Pattern Recognition Lab, University of Erlangen–Nürnberg, Erlangen, Germany

Image Sensor

• sensor_type: CMOS
• resolution: 640x512
• dynamic_range: not specified
• pixel_size: not specified
• dark_current: not specified

Optical Data

• focal_length: not specified
• aperture: not specified
• field_of_view: not specified
• distortion: not specified

Performance Metrics

Applications & Benefits

• cell_imaging: Electroluminescence imaging for defect detection in solar cells.
• benefits: Enhanced defect recognition and automated inspection performance.

Supporting Organizations

• supported_by: Federal Ministry for Economic Affairs and Energy (BMWi)

Manuscript Details

• publication_date: July 2021

Relevancy Score

• score: 8
• missing_fields:
  • dynamic_range
  • pixel_size
  • dark_current
  • focal_length
  • aperture
  • field_of_view
  • distortion
  • frame_rate
  • signal_to_noise_ratio
  • sensitivity
  • shutter_speed
  • power_consumption
  • noise

Processed JSON Filename

request_a35529e9-6307-49ef-8535-d8d386462637-joint_superresolution_and_rectification_for_solar_cell_inspection.json