Fusion of Spatial Depth Information for Defect Detection in Photovoltaic Panels
The conversion efficiency of photovoltaic panels is usually limited by defects,which can reduce their performance and lifespan.High precision photovoltaic panel defect detection algorithms play an important role in ensuring their performance and reliability.The article proposes a photovoltaic panel defect detection model(FSDNet)that integrates spatial depth information to address the issues of insufficient feature extraction capability and low detection accuracy in photovoltaic panel defect detection technology in industrial scenarios.FSDNet uses YOLOv5 as the basic model and designs a spatial depth information fusion module to effectively fuse feature map spatial information and depth information,enhancing the encoding ability of the model's global semantic information.The experimental results indicate that,The average detection accuracy of FSDNet compared to the YOLOv5 s basic model has increased by 6.00%,reaching 86.70%,and the average detection speed of a single image has reached 209.49 FPS.
photovoltaic panelsspatial deep fusiondefect detection