相关实验视频

Updated: Jul 8, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

通过改进的深度学习方法探索基于无人机的近距离检测松病的UAV图像

Xinquan Ye¹, Jie Pan^1,2, Gaosheng Liu¹

¹College of Forestry, Nanjing Forestry University, Nanjing 210037, China.

Plant phenomics (Washington, D.C.)

|December 18, 2023

概括

一个新的PWD-YOLO模型可以实时检测树木中的松病 (PWD). 这种高效,轻量级的人工智能模型可以提高复杂森林的准确性,帮助疾病管理.

科学领域:

林业科学林业科学
计算机科学计算机科学
人工智能的人工智能

背景情况:

松病 (PWD) 对森林生态系统构成重大威胁.
目前用于检测PWD感染树木的方法缺乏实时效率和准确性,特别是在混合森林中.
现有的物体检测模型难以平衡轻量设计和高性能.

研究的目的:

开发一个实时和高效的物体检测模型来识别受PWD感染的树木.
改进现有的YOLOv5s (你只看一次5s版本) 算法,以提高PWD检测.
为林业管理提供可靠的工具,监测和控制PWD的传播.

主要方法:

开发了一个改进的YOLOv5s算法,命名为PWD-YOLO.
使用RepVGG块和GSConv网络实施了一种轻量级的骨干,以增加推断速度和减少复杂性.
一个C2fCA模块和双向特征金字塔网络被纳入,以增强特征提取和多尺度信息传播.

主要成果:

PWD-YOLO实现了2.7 MB的模型大小,3.5 GFLOP的计算复杂性和1.09 MB的参数体积.
该模型显示了98.0/秒的高推断速度.
在自己构建的数据集上,PWD-YOLO实现了92.5%的精度,95.3%的回忆率和93.9%的F1得分.

结论:

与PWD检测的现有物体检测模型相比,PWD-YOLO模型提供了更高的性能.
开发的模型为实时监测和管理松病提供了有效和高效的解决方案.
这项技术为林业部门在打击PWD方面提供了至关重要的技术支持.

更多相关视频

Leaf Area Index Estimation Using Three Distinct Methods in Pure Deciduous Stands

Leaf Area Index Estimation Using Three Distinct Methods in Pure Deciduous Stands

Published on: August 29, 2019

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

相关概念视频

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.