Aiming at the problem of fire detection, this paper proposes a detection method based on YOLOv5. This paper introduces in detail the deep learning techniques, such as convolutional neural networks, which are mainly used in the field of fire detection, and mentions some typical models and their characteristics. On the basis of introducing the existing technology, this paper puts forward the solution of fire detection problem using YOLOv5. As an efficient and accurate object detection algorithm, YOLOv5 has the advantages of fast speed, high accuracy, lightweight network structure, etc., which is suitable for practical application scenarios. The key parts of YOLOv5, such asnetwork model, input, backbone network, Neck and detection layer, as well as experimental design, experimental environment and analysis of experimental results, are also introduced in detail. The experimental results show that the fire detection model based on YOLOv5 has achieved good results in the training process, and can accurately identify the flame in different scenes, with a high accuracy rate and recall rate. Finally, the paper summarizes the experimental results, and looks forward to the future development direction of fire detection technology, in order to bring more guarantess and possibilities for urban safety, traffic safety and other fields.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Research on fire detection based on object detection algorithm-YOLOv5


    Beteiligte:
    Guo, Jiangshuo (Autor:in) / Yan, Jingwen (Autor:in)


    Erscheinungsdatum :

    23.10.2024


    Format / Umfang :

    1055859 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Research on UAV Object Detection Algorithm Based on CSPCM-YOLOv5

    Xiong, Qiaohui / Shan, Liang / Ma, Qiang et al. | Springer Verlag | 2024



    Remote sensing aircraft small object detection algorithm based on YOLOv5

    Qiu, Yijuan / Xue, Jiefeng / Zhang, Jie et al. | SPIE | 2024


    Lightweight pear detection algorithm based on improved YOLOv5

    Hu, Xiaomei / Zhang, Yunyou / Chen, Yi et al. | SPIE | 2023