A real-time detection model for smoke in grain bins with edge devices
Hang Yin,
Mingxuan Chen,
Yinqi Lin,
Shixuan Luo,
Yalin Chen,
Song Yang,
Lijun Gao
Affiliations
Hang Yin
College of Big Data and Internet, Shenzhen Technology University, Shenzhen, 518118, China; College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China; Corresponding author. College of Big Data and Internet, Shenzhen Technology University, Shenzhen, 518118, China.
Mingxuan Chen
College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China
Yinqi Lin
College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China
Shixuan Luo
College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China
Yalin Chen
College of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, 510225, China
Song Yang
College of Software, Dalian University of Foreign Languages, Dalian, 116044, China
Lijun Gao
College of Computer Science, Shenyang Aerospace University, Shenyang, 110136, China; Corresponding author.
The global food crisis is becoming increasingly severe, and frequent grain bins fires can also lead to significant food losses at the same time. Accordingly, this paper proposes a model-compressed technique for promptly detecting small and thin smoke at the early stages of fire in grain bins. The proposed technique involves three key stages: (1) conducting smoke experiments in a back-up bin to acquire a dataset; (2) proposing a real-time detection model based on YOLO v5s with sparse training, channel pruning and model fine-tuning, and (3) the proposed model is subsequently deployed on different current edge devices. The experimental results indicate the proposed model can detect the smoke in grain bins effectively, with mAP and detection speed are 94.90% and 109.89 FPS respectively, and model size reduced by 5.11 MB. Furthermore, the proposed model is deployed on the edge device and achieved the detection speed of 49.26 FPS, thus allowing for real-time detection.
