Hoffmann, Mathis
[Author];
Kohler, Thomas
[Author];
Doll, Bernd
[Author];
Schebesch, Frank
[Author];
Talkenberg, Florian
[Author];
Peters, Ian Marius
[Author];
Brabec, Christoph
[Author];
Maier, Andreas
[Author];
Christlein, Vincent
[Author]
Joint Superresolution and Rectification for Solar Cell Inspection
You can manage bookmarks using lists, please log in to your user account for this.
Media type:
E-Article
Title:
Joint Superresolution and Rectification for Solar Cell Inspection
Contributor:
Hoffmann, Mathis
[Author];
Kohler, Thomas
[Author];
Doll, Bernd
[Author];
Schebesch, Frank
[Author];
Talkenberg, Florian
[Author];
Peters, Ian Marius
[Author];
Brabec, Christoph
[Author];
Maier, Andreas
[Author];
Christlein, Vincent
[Author]
Published:
IEEE, 2021
Published in:IEEE journal of photovoltaics 11(4), 1051 - 1058 (2021). doi:10.1109/JPHOTOV.2021.3072229
Language:
English
DOI:
https://doi.org/10.1109/JPHOTOV.2021.3072229
ISSN:
2156-3381;
2156-3403
Origination:
Footnote:
Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
Description:
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.