| Issue |
MATEC Web Conf.
Volume 417, 2025
2025 RAPDASA-RobMech-PRASA-AMI Conference: Bridging the Gap between Industry & Academia - The 26th Annual International RAPDASA Conference, joined by RobMech, PRASA and AMI, co-hosted by CSIR and Tshwane University of Technology, Pretoria
|
|
|---|---|---|
| Article Number | 04013 | |
| Number of page(s) | 14 | |
| Section | Robotics and Mechatronics | |
| DOI | https://doi.org/10.1051/matecconf/202541704013 | |
| Published online | 25 November 2025 | |
Comparative analysis of Yolo based algorithms in solar panel detection using resource-constrained hardware
1 Department of Mechatronics, Nelson Mandela University, South Africa,
2 Department of Marine Engineering, Nelson Mandela University, South Africa,
* Corresponding author: s229701698@mandela.ac.za
This study presents a comparative analysis of YOLO models for solar panel detection with the implementation on edge devices. With the rapid adoption of renewable energy, the need for monitoring and inspecting solar panel structures is also increasing. This study dives into different YOLO models for solar panel detection. It also compares the use of CLAHE and Histogram Equalization as preprocessing techniques and investigates dataset augmentation to increase its robustness. During training, YOLOv8 emerged as the strongest model with a higher F1 Score of above 96% and accuracy, also proving to have the better inference rate on both the Raspberry Pi and Google Coral Accelerator.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.