湖北农业科学 ›› 2024, Vol. 63 ›› Issue (8): 262-266.doi: 10.14088/j.cnki.issn0439-8114.2024.08.044

• 智能监测 • 上一篇    下一篇

基于无人机图像检测的林业虫害监控预防

邱雅林1a, 刘向龙2, 何小军3, 赵庆龙1b, 贾存芳1c   

  1. 1.庆阳市林业和草原科学技术推广站,甘肃 庆阳 745000;
    2.庆阳市林业科学研究所,甘肃 庆阳 745099;
    3.子午岭林管局合水分局北川林场,甘肃 庆阳 745400
  • 收稿日期:2024-06-05 出版日期:2024-08-25 发布日期:2024-09-05
  • 作者简介:邱雅林(1969-),女,甘肃宁县人,高级工程师,主要从事林业和草原有害生物防控的研究工作,(电话)13919600088(电子信箱)13919600088@163.com。
  • 基金资助:
    中央财政林业科技推广示范项目(甘[2023]ZYTG 007号); 庆阳市科技计划项目(QY-STK-2022A-042)

Forest pest monitoring and prevention based on UAV image detection

QIU Ya-lin1a, LIU Xiang-long2, HE Xiao-jun3, ZHAO Qing-long1b, JIA Cun-fang1c   

  1. 1. Qingyang Foresty and Grassland Science and Technology Promotion Station, Qingyang 745000, Gansu, China;
    2. Qingyang Forestry Research Institute, Qingyang 745099, Gansu, China;
    3. Beichuan Forest Farm of Ziwuling Forestry Bureau Hexui Branch, Qingyang 745400, Gansu, China
  • Received:2024-06-05 Published:2024-08-25 Online:2024-09-05

摘要: 为解决现有基于无人机图像的虫害监控方法效率低效果差,且需要耗费大量人力物力的问题,研究基于深度学习构建了基于无人机的林业虫害检测框架,将浅层网络提取的特征信息传递到深层网络,并通过剪枝和批量归一化折叠对模型进行了轻量化改进。结果表明,训练过程中各模型趋于稳定时,改进后的YOLOv4模型平均准确率达97.38%,计算成本和存储需求较原始的YOLOv4已分别降低17.81个百分点和23.38%;平均检测正确率比改进前高12.75个百分点。

关键词: 无人机, 虫害监控, 图像检测, YOLOv4模型

Abstract: In order to solve the problem of low efficiency and poor effect of existing pest control methods, which required a lot of manpower and material resources, the research built a forest pest detection framework based on deep learning, which transferred the feature information extracted from the shallow network to the deep network, and made lightweight improvements to the model through pruning and batch normalization folding. The results showed that, when each model tended to be stable during training, the average accuracy of the improved YOLOv4 model reached 97.38%, and compared with the original YOLOv4 model, the computing cost and storage requirements were reduced by 17.81 percent points and 23.38%, respectively. The average detection accuracy was 12.75 percent points higher than before.

Key words: unmanned aerial vehicle(UAV), pest control, image detection, YOLOv4 model

中图分类号: