PVEL-AD工业检测数据集 ● We build a Photovoltaic Electroluminescence Anomaly Detection dataset (PVEL-AD ) for 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 such as crack (line and star), finger interruption, black core, misalignment, thick line, scratch, fragment, corner, and material defect. Moreover, 37,380 ground truth bounding boxes are provided for 8 types of defects. The PVELAD-2021 Datasets Request Form is available here. ○ All researchers need to follow the instructions below to access the datasets. ○ Download and fill the Datasets Request Form (MUST be hand signed with date). Please use institutional email address(es). Commercial emails such as Gmail and QQmail are NOT allowed. ○ Email the signed Datasets Request Form to haiyong.chen@hebut.edu.cn or Subinyi@buaa.edu.cn |