GGSYOLOv5: Flame recognition method in complex scenes based on deep learning.
The continuous development of the field of artificial intelligence, not only makes people's lives more convenient but also plays a role in the supervision and protection of people's lives and property safety. News of the fire is not uncommon, and fire has become the biggest hidden danger t...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0317990 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206785535901696 |
|---|---|
| author | Fucai Sun Liping Du Yantao Dai |
| author_facet | Fucai Sun Liping Du Yantao Dai |
| author_sort | Fucai Sun |
| collection | DOAJ |
| description | The continuous development of the field of artificial intelligence, not only makes people's lives more convenient but also plays a role in the supervision and protection of people's lives and property safety. News of the fire is not uncommon, and fire has become the biggest hidden danger threatening the safety of public life and property. In this paper, a deep learning-based flame recognition method for complex scenes, GGSYOLOv5, is proposed. Firstly, a global attention mechanism (GAM) was added to the CSP1 module in the backbone part of the YOLOv5 network, and then a parameterless attention mechanism was added to the feature fusion part. Finally, packet random convolution (GSConv) was used to replace the original convolution at the output end. A large number of experiments show that the detection accuracy rate is 4.46% higher than the original algorithm, and the FPS is as high as 64.3, which can meet the real-time requirements. Moreover, the algorithm is deployed in the Jetson Nano embedded development board to build the flame detection system. |
| format | Article |
| id | doaj-art-541c7067a6124e7c805edc7da2c7edcc |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-541c7067a6124e7c805edc7da2c7edcc2025-02-07T05:30:37ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01201e031799010.1371/journal.pone.0317990GGSYOLOv5: Flame recognition method in complex scenes based on deep learning.Fucai SunLiping DuYantao DaiThe continuous development of the field of artificial intelligence, not only makes people's lives more convenient but also plays a role in the supervision and protection of people's lives and property safety. News of the fire is not uncommon, and fire has become the biggest hidden danger threatening the safety of public life and property. In this paper, a deep learning-based flame recognition method for complex scenes, GGSYOLOv5, is proposed. Firstly, a global attention mechanism (GAM) was added to the CSP1 module in the backbone part of the YOLOv5 network, and then a parameterless attention mechanism was added to the feature fusion part. Finally, packet random convolution (GSConv) was used to replace the original convolution at the output end. A large number of experiments show that the detection accuracy rate is 4.46% higher than the original algorithm, and the FPS is as high as 64.3, which can meet the real-time requirements. Moreover, the algorithm is deployed in the Jetson Nano embedded development board to build the flame detection system.https://doi.org/10.1371/journal.pone.0317990 |
| spellingShingle | Fucai Sun Liping Du Yantao Dai GGSYOLOv5: Flame recognition method in complex scenes based on deep learning. PLoS ONE |
| title | GGSYOLOv5: Flame recognition method in complex scenes based on deep learning. |
| title_full | GGSYOLOv5: Flame recognition method in complex scenes based on deep learning. |
| title_fullStr | GGSYOLOv5: Flame recognition method in complex scenes based on deep learning. |
| title_full_unstemmed | GGSYOLOv5: Flame recognition method in complex scenes based on deep learning. |
| title_short | GGSYOLOv5: Flame recognition method in complex scenes based on deep learning. |
| title_sort | ggsyolov5 flame recognition method in complex scenes based on deep learning |
| url | https://doi.org/10.1371/journal.pone.0317990 |
| work_keys_str_mv | AT fucaisun ggsyolov5flamerecognitionmethodincomplexscenesbasedondeeplearning AT lipingdu ggsyolov5flamerecognitionmethodincomplexscenesbasedondeeplearning AT yantaodai ggsyolov5flamerecognitionmethodincomplexscenesbasedondeeplearning |