A Benchmark for Crack Segmentation in Electroluminescence Images

Dataset · Mon May 30 00:00:00 EDT 2022

DOI:https://doi.org/10.21948/1871275· OSTI ID:1871275

Chen, Xin ^[1]; Karin, Todd ^[2]; Libby, Cara ^[3]; Deceglie, Michael ^[4]; Hacke, Peter ^[4]; Silverman, Timothy ^[4]; Gabor, Andrew ^[5]; Jain, Anubhav ^[2]

---

1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); National Renewable Energy Laboratory
2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
3. Electric Power Research Inst. (EPRI), Palo Alto, CA (United States)
4. National Renewable Energy Lab. (NREL), Golden, CO (United States)
5. BrightSpot Automation

This public dataset contains electroluminescence images of solar cells and crack annotations, which can be used for developing semantic segmentation model to detect cracks in solar modules.

• Research Organization: EMN-HYMARC (EMN-HyMARC); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); National Renewable Energy Laboratory (NREL), Golden, CO (United States); East Tennessee Technology Park (ETTP), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office
• Contributing Organization: Lawrence Berkeley National Laboratory, National Renewable Energy Laboratory, Electric Power Research Institute, BrightSpot Automation
• DOE Contract Number: AC36-08GO28308
• OSTI ID: 1871275
• Availability: Public
• Country of Publication: United States
• Language: English

Related Subjects

14 SOLAR ENERGY
computer vision
crack segmentation
deep learning
solar module characterization