Fire Recognition for Photovoltaic Panel Fire Fighting UAV Based on Machine Vision

DOI

10.2991/978-94-6463-821-9_103How to use a DOI?

Keywords

Flame Recognition; Machine Vision; Neural Networks; UAV

Abstract

Photovoltaic (PV) power generation has been widely promoted due to the increased demand for clean energy in recent years, but the fires it generates are often prone to cause large negative impacts. Therefore, a machine vision-based fire recognition algorithm for PV panel fire-fighting UAVs is proposed in this research. The algorithm consists of image preprocessing, feature extraction and CNN-based recognition in three parts. Firstly, the image preprocessing stages are innovatively designed, including RGB operation, filtering operation and morphological processing. Then the feature extraction of the connectivity characteristics and the number of sharp corners of the suspected flame region after processing is carried out. Through a number of image preprocessing sessions and feature extraction sessions on the processed image information, the information of the ingested range with the dataset that combines the image information and feature information are represented. Finally, the data set of the photographed area is put into a well-trained neural network to determine. The improved CNN neural network makes the overall photovoltaic panel fire fighting UAV fire recognition algorithm reach 96.67% accuracy and more than 96.25% anti-jamming accuracy, which can complete the photovoltaic fire recognition task in an excellent way.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xuran Gong
PY  - 2025
DA  - 2025/08/31
TI  - Fire Recognition for Photovoltaic Panel Fire Fighting UAV Based on Machine Vision
BT  - Proceedings of the 2025 2nd International Conference on Mechanics, Electronics Engineering and Automation (ICMEEA 2025)
PB  - Atlantis Press
SP  - 1063
EP  - 1077
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-821-9_103
DO  - 10.2991/978-94-6463-821-9_103
ID  - Gong2025
ER  -