YOLOv8-EMSC: A lightweight fire recognition algorithm for large spaces
Stringent fire prevention requirements are imperative in expansive environments. Fire detection in diverse large-scale settings typically relies on sensor-based or AI-driven target detection methods. Traditional fire detectors often suffer from false alarms and missed detections, failing to meet the...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2024-12-01
|
| Series: | Journal of Safety Science and Resilience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666449624000458 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846137666999943168 |
|---|---|
| author | Deng Li Tan Yang Zhou Jin Wu Si-qi Liu Quan-yi |
| author_facet | Deng Li Tan Yang Zhou Jin Wu Si-qi Liu Quan-yi |
| author_sort | Deng Li |
| collection | DOAJ |
| description | Stringent fire prevention requirements are imperative in expansive environments. Fire detection in diverse large-scale settings typically relies on sensor-based or AI-driven target detection methods. Traditional fire detectors often suffer from false alarms and missed detections, failing to meet the fire safety requirements of large-scale structures. Many existing target detection algorithms are characterized by substantial model sizes. Some detection terminals in large structures face challenges deploying these models due to constrained computational resources. To address this issue, we propose a lightweight model, YOLOv8-EMSC, derived from YOLOv8n. The incorporation of C2f_EMSC, replacing the C2f module, significantly reduces the model parameters in the enhanced YOLOv8-EMSC model compared to YOLOv8n, thereby enhancing model inference speed. Extensive testing and validation using a custom-built large-scale infrared fire dataset demonstrates a 9.6 % reduction in parameters compared to the baseline model for YOLOv8-EMSC, achieving an average precision of 95.6 %, surpassing both the baseline and mainstream models and significantly enhancing fire detection accuracy in expansive environments. |
| format | Article |
| id | doaj-art-8c1669dc18e3494e98f86131b7ddc38c |
| institution | Kabale University |
| issn | 2666-4496 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Safety Science and Resilience |
| spelling | doaj-art-8c1669dc18e3494e98f86131b7ddc38c2024-12-08T06:12:42ZengKeAi Communications Co., Ltd.Journal of Safety Science and Resilience2666-44962024-12-0154422431YOLOv8-EMSC: A lightweight fire recognition algorithm for large spacesDeng Li0Tan Yang1Zhou Jin2Wu Si-qi3Liu Quan-yi4College of Civil Aviation Safety Engineering, Civil Aviation Flight University of China, Guanghan, 618307, China; Civil Aircraft Fire Science and Safety Engineering Key Laboratory of Sichuan Province, Guanghan 618307, China; Sichuan Key Technology Engineering Research Center for All-electric Navigable Aircraft, Guanghan, 618307, ChinaCollege of Civil Aviation Safety Engineering, Civil Aviation Flight University of China, Guanghan, 618307, China; Civil Aircraft Fire Science and Safety Engineering Key Laboratory of Sichuan Province, Guanghan 618307, ChinaCollege of Civil Aviation Safety Engineering, Civil Aviation Flight University of China, Guanghan, 618307, China; Civil Aircraft Fire Science and Safety Engineering Key Laboratory of Sichuan Province, Guanghan 618307, ChinaCollege of Civil Aviation Safety Engineering, Civil Aviation Flight University of China, Guanghan, 618307, China; Civil Aircraft Fire Science and Safety Engineering Key Laboratory of Sichuan Province, Guanghan 618307, ChinaCollege of Civil Aviation Safety Engineering, Civil Aviation Flight University of China, Guanghan, 618307, China; Civil Aircraft Fire Science and Safety Engineering Key Laboratory of Sichuan Province, Guanghan 618307, China; Sichuan Key Technology Engineering Research Center for All-electric Navigable Aircraft, Guanghan, 618307, China; Corresponding author.Stringent fire prevention requirements are imperative in expansive environments. Fire detection in diverse large-scale settings typically relies on sensor-based or AI-driven target detection methods. Traditional fire detectors often suffer from false alarms and missed detections, failing to meet the fire safety requirements of large-scale structures. Many existing target detection algorithms are characterized by substantial model sizes. Some detection terminals in large structures face challenges deploying these models due to constrained computational resources. To address this issue, we propose a lightweight model, YOLOv8-EMSC, derived from YOLOv8n. The incorporation of C2f_EMSC, replacing the C2f module, significantly reduces the model parameters in the enhanced YOLOv8-EMSC model compared to YOLOv8n, thereby enhancing model inference speed. Extensive testing and validation using a custom-built large-scale infrared fire dataset demonstrates a 9.6 % reduction in parameters compared to the baseline model for YOLOv8-EMSC, achieving an average precision of 95.6 %, surpassing both the baseline and mainstream models and significantly enhancing fire detection accuracy in expansive environments.http://www.sciencedirect.com/science/article/pii/S2666449624000458Fire detectionLarge spaceLightweightYOLOv8YOLOv8-EMSC |
| spellingShingle | Deng Li Tan Yang Zhou Jin Wu Si-qi Liu Quan-yi YOLOv8-EMSC: A lightweight fire recognition algorithm for large spaces Journal of Safety Science and Resilience Fire detection Large space Lightweight YOLOv8 YOLOv8-EMSC |
| title | YOLOv8-EMSC: A lightweight fire recognition algorithm for large spaces |
| title_full | YOLOv8-EMSC: A lightweight fire recognition algorithm for large spaces |
| title_fullStr | YOLOv8-EMSC: A lightweight fire recognition algorithm for large spaces |
| title_full_unstemmed | YOLOv8-EMSC: A lightweight fire recognition algorithm for large spaces |
| title_short | YOLOv8-EMSC: A lightweight fire recognition algorithm for large spaces |
| title_sort | yolov8 emsc a lightweight fire recognition algorithm for large spaces |
| topic | Fire detection Large space Lightweight YOLOv8 YOLOv8-EMSC |
| url | http://www.sciencedirect.com/science/article/pii/S2666449624000458 |
| work_keys_str_mv | AT dengli yolov8emscalightweightfirerecognitionalgorithmforlargespaces AT tanyang yolov8emscalightweightfirerecognitionalgorithmforlargespaces AT zhoujin yolov8emscalightweightfirerecognitionalgorithmforlargespaces AT wusiqi yolov8emscalightweightfirerecognitionalgorithmforlargespaces AT liuquanyi yolov8emscalightweightfirerecognitionalgorithmforlargespaces |