An Edge-Guided Deep Learning Solar Panel Hotspot Thermal Image Segmentation Algorithm
Source abstract
Abstract
To overcome the deficiencies in segmenting hot spots from thermal infrared images, such as difficulty extracting the edge features, low accuracy, and a high missed detection rate, an improved Mask R-CNN photovoltaic hot spot thermal image segmentation algorithm has been proposed in this paper. Firstly, the edge image features of hot spots were extracted based on residual neural networks. Secondly, by combining the feature pyramid structure, an edge-guided feature pyramid structure was designed, and the hot spot edge features were injected into a Mask R-CNN network. Thirdly, an infrared spatial attention module was introduced into the Mask R-CNN network when feature extraction and the infrared features of the detected hot spots were enhanced. Fourthly, the size ratio of the candidate frames was adjusted self-adaptively according to the structural characteristics of the aspect ratio of the hot spots. Finally, the validation experiments were conducted, and the results demonstrated that the hot spot contours of thermal infrared images were enhanced through the algorithm proposed in this paper, and the segmentation accuracy was significantly improved.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Photovoltaic System Optimization Techniques · Solar Radiation and Photovoltaics · Solar Thermal and Photovoltaic Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical and Electrical Engineering, Anhui Jianzhu University, Hefei 230601, China
Key Laboratory of Construction Machinery Fault Diagnosis and Early Warning Technology of Anhui Jianzhu University, Hefei 230601, China
Ultra High Voltage Branch, State Grid Anhui Electric Power Co., Hefei Anhui Ltd., Hefei 230041, China
Funding
Anhui Natural Science Foundation · Anhui University Collaborative Innovation Project · Anhui Construction Plan Project · Anhui Simulation Design and Modern Manufacture Engineering Technology Research Center
References (26)
Show source-provided references
1. Driving force model to evaluate China’s photovoltaic industry: Historical and future trends10.1016/j.jclepro.2021.127637 ↗
2. Early degradation of silicon PV modules and guaranty conditions10.1016/j.solener.2011.06.011 ↗
3. Research on Hot Spots in System Side Photovoltaic Modules and Causes Analysis
4. Hot-spot generation model using electrical and thermal equivalent circuits for a copper indium gallium selenide photovoltaic module10.1016/j.solener.2021.01.042 ↗
5. Influence of Hot Spot on Power Generation Performance of Photovoltaic Module
6. Fault diagnosis of photovoltaic modules through image processing and Canny edge detection on field thermographic measurements10.1080/14786451.2013.826223 ↗
7. Alsafasfeh, M., Abdel-Qader, I., Bazuin, B., Alsafasfeh, Q., and Su, W. (2018). Unsupervised Fault Detection and Analysis for Large Photovoltaic Systems Using Drones and Machine Vision. Energies, 11.10.3390/en11092252 ↗
8. Vidal de Oliveira, A.K., Aghaei, M., and Rüther, R. (2019, January 9–13). Automatic fault Detection of photovoltaic Arrays by convolutional neural networks during aerial infrared thermography. Proceedings of the 36th European Photovoltaic Solar Energy Conference and Exhibition, Marseille, France.
9. Hot Spots Detection of Operating PV Arrays through IR Thermal Image Using Method Based on Curve Fitting of Gray Histogram10.1051/matecconf/20166106017 ↗
10. Efficient Thermal Image Segmentation for Heat Visualization in Solar Panels and Batteries using Watershed Transform10.5815/ijigsp.2017.11.02 ↗
11. Ngo, G.C., and Macabebe, E.Q.B. (2016, January 22–26). Image segmentation using K-means color quantization and density-based spatial clustering of applications with noise (DBSCAN) for hotspot detection in photovoltaic modules. Proceedings of the 2016 IEEE Region 10 Conference (TENCON), Singapore.10.1109/TENCON.2016.7848290 ↗
12. Intelligent monitoring of photovoltaic panels based on infrared detection10.1016/j.egyr.2022.03.173 ↗
13. Pierdicca, R., Paolanti, M., Felicetti, A., Piccinini, F., and Zingaretti, P. (2020). Automatic Faults Detection of Photovoltaic Farms: solAIr, a Deep Learning-Based System for Thermal Images. Energies, 13.10.3390/en13246496 ↗
14. He, K., Gkioxari, G., Dollár, P., and Girshick, R.B. (2017, January 22–29). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.322 ↗
15. A novel detection method for hot spots of photovoltaic (PV) panels using improved anchors and prediction heads of YOLOv5 network10.1016/j.egyr.2022.08.130 ↗
16. Vlaminck, M., Heidbuchel, R., Philips, W., and Luong, H. (2022). Region-Based CNN for Anomaly Detection in PV Power Plants Using Aerial Imagery. Sensors, 22.10.3390/s22031244 ↗
17. Improved Mask-RCNN based semantic segmentation for distribution power lines
18. Infrared Image Segmentation and Temperature Reading of Composite Insulator Strings Based on Mask-RCNN Algorithm
19. Prostate cancer of magnetic resonance imaging automatic segmentation and detection of based on 3D-Mask RCNN
20. Instance segmentation scheme for roofs in rural areas based on Mask R-CNN
21. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
22. Sun, Y., Wang, S., Chen, C., and Xiang, T.Z. (2022). Boundary-Guided Camouflaged Object Detection. arXiv.10.24963/ijcai.2022/186 ↗
23. Chen, S., Qiu, C., Yang, W., and Zhang, Z. (2022). Combining edge guidance and feature pyramid for medical image segmentation. Biomed. Signal Process. Control, 78.10.1016/j.bspc.2022.103960 ↗
24. Attention Enhancement Mechanism Instance Segmentation of Thermal Imaging Temperature Measurement Region Based on Infrared
25. Research on infrared small target segmentation algorithm based on improved mask R-CNN10.1016/j.ijleo.2022.170334 ↗
26. Building Extraction from Remote Sensing Image Based on Improved Mask R-CNN