2020/01/30 by Martin Mayr, Mathis Hoffmann, Mayr, Martin +5
Computer Science · Energy · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Industrial Vision Systems and Defect Detection #Integrated Circuits and Semiconductor Failure Analysis #Photovoltaic System Optimization Techniques #cs.CV
paper · pdf · doi:10.48550/arxiv.2001.11248
ICIP'2019
arxiv created 2020/01/30 · openalex publication_date 2020/01/30 · arxiv updated 2020/01/31 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Photovoltaic is one of the most important renewable energy sources for dealing with world-wide steadily increasing energy consumption. This raises the demand for fast and scalable automatic quality management during production and operation. However, the detection and segmentation of cracks on electroluminescence (EL) images of mono- or polycrystalline solar modules is a challenging task. In this work, we propose a weakly supervised learning strategy that only uses image-level annotations to obtain a method that is capable of segmenting cracks on EL images of solar cells. We use a modified ResNet-50 to derive a segmentation from network activation maps. We use defect classification as a surrogate task to train the network. To this end, we apply normalized Lp normalization to aggregate the activation maps into single scores for classification. In addition, we provide a study how different parameterizations of the normalized Lp layer affect the segmentation performance. This approach shows promising results for the given task. However, we think that the method has the potential to solve other weakly supervised segmentation problems as well.