A High-Precision Ensemble Model for Forest Fire Detection in Large and Small Targets

被引:3
|
作者
Qian, Jiachen [1 ]
Bai, Di [2 ]
Jiao, Wanguo [1 ]
Jiang, Ling [1 ]
Xu, Renjie [3 ]
Lin, Haifeng [1 ]
Wang, Tian [1 ]
机构
[1] Nanjing Forestry Univ, Coll Informat Sci & Technol, Nanjing 210037, Peoples R China
[2] Nanjing Agr Univ, Coll Informat Management, Nanjing 210095, Peoples R China
[3] McMaster Univ, Dept Comp & Software, Hamilton, ON L8S 4L8, Canada
来源
FORESTS | 2023年 / 14卷 / 10期
关键词
forest fire; integrated learning; target detection;
D O I
10.3390/f14102089
中图分类号
S7 [林业];
学科分类号
0829 ; 0907 ;
摘要
Forest fires are major forestry disasters that cause loss of forest resources, forest ecosystem safety, and personal injury. It is often difficult for current forest fire detection models to achieve high detection accuracy on both large and small targets at the same time. In addition, most of the existing forest fire detection models are single detection models, and using only a single model for fire detection in a complex forest environment has a high misclassification rate, and the accuracy rate needs to be improved. Aiming at the above problems, this paper designs two forest fire detection models (named WSB and WSS) and proposes an integrated learning-based forest fire detection model (named WSB_WSS), which also obtains high accuracy in the detection of forest fires with large and small targets. In order to help the model predict the location and size of forest fire targets more accurately, a new edge loss function, Wise-Faster Intersection over Union (WFIoU), is designed in this paper, which effectively improves the performance of the forest fire detection algorithm. The WSB model introduces the Simple-Attention-Module (SimAM) attention mechanism to make the image feature extraction more accurate and introduces the bi-directional connectivity and cross-layer feature fusion to enhance the information mobility and feature expression ability of the feature pyramid network. The WSS model introduces the Squeeze-and-Excitation Networks (SE) attention mechanism so that the model can pay more attention to the most informative forest fire features and suppress unimportant features, and proposes Spatial Pyramid Pooling-Fast Cross Stage Partial Networks (SPPFCSPC) to enable the network to extract features better and speed up the operation of the model. The experimental findings demonstrate that the WSB model outperforms other approaches in the context of identifying forest fires characterized by small-scale targets, achieving a commendable accuracy rate of 82.4%, while the WSS model obtains a higher accuracy of 92.8% in the identification of large target forest fires. Therefore, in this paper, a more efficient forest fire detection model, WSB_WSS, is proposed by integrating the two models through the method of Weighted Boxes Fusion (WBF), and the accuracy of detecting forest fires characterized by small-scale targets attains 83.3%, while for forest fires with larger dimensions, the accuracy reaches an impressive 93.5%. This outcome effectively leverages the strengths inherent in both models, consequently achieving the dual objective of high-precision detection for both small and large target forest fires concurrently.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] A high-precision forest fire smoke detection approach based on ARGNet
    Zhan, Jialei
    Hu, Yaowen
    Zhou, Guoxiong
    Wang, Yanfeng
    Cai, Weiwei
    Li, Liujun
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2022, 196
  • [2] SMWE-GFPNNet: A high-precision and robust method for forest fire smoke detection
    Li, Rui
    Hu, Yaowen
    Li, Lin
    Guan, Renxiang
    Yang, Ruoli
    Zhan, Jialei
    Cai, Weiwei
    Wang, Yanfeng
    Xu, Haiwen
    Li, Liujun
    [J]. KNOWLEDGE-BASED SYSTEMS, 2024, 289
  • [3] High-Precision Real-Time Forest Fire Video Detection Using One-Class Model
    Yang, Xubing
    Wang, Yang
    Liu, Xudong
    Liu, Yunfei
    [J]. FORESTS, 2022, 13 (11):
  • [4] SOD-YOLO: A High-Precision Detection of Small Targets on High-Voltage Transmission Lines
    Wu, Kaijun
    Chen, Yifu
    Lu, Yaolin
    Yang, Zhonghao
    Yuan, Jiayu
    Zheng, Enhui
    [J]. ELECTRONICS, 2024, 13 (07)
  • [5] High-Precision Calibration Method of Binocular Cameras for Large Inclination Targets
    Lu Junhao
    Lou Qun
    Xiao Jinyou
    Wen Lihua
    Hou Xiao
    [J]. ACTA OPTICA SINICA, 2022, 42 (23)
  • [6] SMALL HIGH-PRECISION THERMOSTAT
    CHYLEWSK.C
    TOMLINSON, C
    SAUTER, W
    SIMON, W
    [J]. MICROCHEMICAL JOURNAL, 1963, 7 (03) : 263 - &
  • [7] SMALL RACES - HIGH-PRECISION
    BEELER, J
    [J]. F&M-FEINWERKTECHNIK & MESSTECHNIK, 1991, 99 (06): : S18 - &
  • [8] SMALL COMPONENTS - HIGH-PRECISION
    SCHNEIDER, M
    [J]. F&M-FEINWERKTECHNIK & MESSTECHNIK, 1991, 99 (04): : 165 - 167
  • [9] Dielectric metasurface for high-precision detection of large unilamellar vesicles
    Conteduca, D.
    Quinn, S. D.
    Krauss, T. F.
    [J]. JOURNAL OF OPTICS, 2021, 23 (11)
  • [10] High-precision comb targets and manufacture process
    王林
    高秀娟
    宫小泽
    李晓辉
    [J]. Journal of Measurement Science and Instrumentation, 2013, 4 (02) : 136 - 138