Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Fire Detection Based on YOLOv4 Baseline
Identifying a fire in its early stages is essential for minimizing fire incidents by solving it. To prevent from the extent of the fire area, we need effective technology to detect the fire. In this paper, the network structure is slightly improved and compared with the original yolov4 algorithm to explore the features of fire in images to accurately detect fire and realize the fire detection in different scenes. The paper first prepares a variety of fire datasets in complex scenes and divide them into two categories, regular fire and irregular fire, and then label them with labeling software; The labeled datasets are divided into training set and testing set according to 8:2; And then, k-means clustering algorithm is used to initialize the region proposal of the datasets; After that, the origin YOLOv4 and improved model are used to train the training set images respectively under Win10 system; Finally, the trained model is used for the evaluation of testing set and tested on fires in real environment. The experimental results show that the model is effective in detecting fires for various scenes.
Fire Detection Based on YOLOv4 Baseline
Identifying a fire in its early stages is essential for minimizing fire incidents by solving it. To prevent from the extent of the fire area, we need effective technology to detect the fire. In this paper, the network structure is slightly improved and compared with the original yolov4 algorithm to explore the features of fire in images to accurately detect fire and realize the fire detection in different scenes. The paper first prepares a variety of fire datasets in complex scenes and divide them into two categories, regular fire and irregular fire, and then label them with labeling software; The labeled datasets are divided into training set and testing set according to 8:2; And then, k-means clustering algorithm is used to initialize the region proposal of the datasets; After that, the origin YOLOv4 and improved model are used to train the training set images respectively under Win10 system; Finally, the trained model is used for the evaluation of testing set and tested on fires in real environment. The experimental results show that the model is effective in detecting fires for various scenes.
Fire Detection Based on YOLOv4 Baseline
Lect. Notes Electrical Eng.
Zhao, Pengfei (Herausgeber:in) / Ye, Zhuangzhi (Herausgeber:in) / Xu, Min (Herausgeber:in) / Yang, Li (Herausgeber:in) / Zhang, Linghao (Herausgeber:in) / Yan, Shu (Herausgeber:in) / Wang, Wanting (Autor:in) / Wang, Qing (Autor:in) / Chen, Yehong (Autor:in)
17.04.2022
6 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Fire detection in industrial environments with YOLOv4
| DataCite | 2024
Detection of Potholes in Asphalt Pavements Using YOLOv4 Architecture
| Springer Verlag | 2024
Water Column Detection Method at Impact Point Based on Improved YOLOv4 Algorithm
| DOAJ | 2022
Fire engineering, setting the baseline
| British Library Conference Proceedings | 2004