MFPN-ASPP: MobileNet feature pyramid with ASPP for photovoltaic panel defect segmentation
Abstract
Photovoltaic (PV) fault detection through thermal infrared imaging is a crucial step for efficient operation and maintenance of large-scale solar plants. Although current deep learning methodologies demonstrate potential, their efficacy is limited by inadequate feature extraction on various scales. This research presents an enhanced semantic segmentation model that combines a feature pyramid network (FPN) with a lightweight MobileNetV2 backbone and an atrous spatial pyramid pooling (ASPP) module. The model is trained, evaluated, and tested on the Photovoltaic Thermal Images dataset. The suggested method achieved competitive performance, with a mean Dice coefficient of 0.8440 and an average IoU of 0.7564, surpassing U-Net, LinkNet, FPN, and Mask-RCNN. The results highlight the efficacy of lightweight encoder–decoder frameworks that incorporate atrous spatial pyramid pooling, enabling accurate and computationally efficient fault detection in photovoltaic installations.
Related
- Hybrid feature pyramid attention and capsule network (FpaNet+CapsNet) for enhanced spatial and contextual feature extraction for improved brain tumor segmentation
- Solar photovoltaic module multi-class anomaly detection using MobileNet architecture with skip connections
- A deep hybrid feature extraction model based on MobileNet and vision transformer for acute lymphoblastic leukemia prediction
- A lightweight photovoltaic panel defect detection model based on YOLO
- ACFNet: Asymmetric Cross-Layer Fusion Network with Semantic Context Enhancement for Photovoltaic Defect Detection
BibTeX
@article{galal2026mfpnaspp,
title = {{MFPN-ASPP: MobileNet feature pyramid with ASPP for photovoltaic panel defect segmentation}},
author = {Nivin Galal and El Said A. Marzouk and Hossam EL-Din Moustafa and Hala B. Nafea and Asmaa A. Hekal},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-71340-5},
url = {https://www.nature.com/articles/s41598-026-71340-5},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - MFPN-ASPP: MobileNet feature pyramid with ASPP for photovoltaic panel defect segmentation
AU - Nivin Galal
AU - El Said A. Marzouk
AU - Hossam EL-Din Moustafa
AU - Hala B. Nafea
AU - Asmaa A. Hekal
PY - 2026
DA - 2026/10/08
JO - Scientific Reports
DO - 10.1038/s41598-026-71340-5
UR - https://www.nature.com/articles/s41598-026-71340-5
AB - Photovoltaic (PV) fault detection through thermal infrared imaging is a crucial step for efficient operation and maintenance of large-scale solar plants. Although current deep learning methodologies demonstrate potential, their efficacy is limited by inadequate feature extraction on various scales. This research presents an enhanced semantic segmentation model that combines a feature pyramid network (FPN) with a lightweight MobileNetV2 backbone and an atrous spatial pyramid pooling (ASPP) module. The model is trained, evaluated, and tested on the Photovoltaic Thermal Images dataset. The suggested method achieved competitive performance, with a mean Dice coefficient of 0.8440 and an average IoU of 0.7564, surpassing U-Net, LinkNet, FPN, and Mask-RCNN. The results highlight the efficacy of lightweight encoder–decoder frameworks that incorporate atrous spatial pyramid pooling, enabling accurate and computationally efficient fault detection in photovoltaic installations.
SN - 2045-2322
ER -