Photovoltaic cell anomaly detection dataset

The anomaly detection in photovoltaic (PV) cell electroluminescence (EL) image is of great significance for the vision-based fault diagnosis. Many researchers are committed to solving this problem, but a large-scale open-world dataset is required to validate their novel ideas. We build a PV EL Anomaly Detection (PVEL-AD) dataset for polycrystalline solar cell, which contains 36,543 near-infrared images with various internal defects and heterogeneous background. This dataset contains anomaly-free images and anomalous images with 10 different categories. Moreover, 37,380 ground truth bounding boxes are provided for 8 types of defects. We also carry out a comprehensive evaluation of the state-of-the-art object detection methods based on deep learning. The evaluation results on this dataset provide the initial benchmark, which is convenient for follow-up researchers to conduct experimental comparisons. To the best of our knowledge, this is the first public dataset for PV solar cell anomaly detection that provides box-wise ground truth and focuses on industrial application. Furthermore, this dataset can also be used for the evaluation of many computer vision tasks such as few-shot detection, one-class classification and anomaly generation. More details are presented in https://github.com/binyisu/PVEL-AD

光伏（Photovoltaic，PV）电池电致发光（Electroluminescence，EL）图像异常检测对于基于视觉的故障诊断具有重要意义。诸多研究者致力于攻克该问题，但现有研究仍需大规模开放世界数据集以验证其创新思路。我们构建了面向多晶太阳能电池的光伏电致发光异常检测（PV EL Anomaly Detection，PVEL-AD）数据集，该数据集包含36543幅带有各类内部缺陷与异质背景的近红外图像。该数据集涵盖无异常样本图像与10类不同的异常样本图像。此外，针对8类缺陷，我们还提供了37380个真值边界框（ground truth bounding boxes）。我们还基于深度学习技术，对当前前沿的目标检测方法开展了全面评估。本数据集上的评估结果可作为初始基准，便于后续研究人员开展实验对比。据我们所知，这是首个公开的、提供逐框真值标注（box-wise ground truth）且聚焦工业应用场景的光伏太阳能电池异常检测数据集。此外，该数据集还可用于少样本（few-shot）检测、单类分类、异常生成等诸多计算机视觉任务的评估。更多详细信息请参见https://github.com/binyisu/PVEL-AD