使用无人机3D点云和改进的PointNet+进行田间作物表型特征的自动测量
Jiatong Yao1, Wei Wang2, Hongyu Fu3
1College of Information and Intelligence, Hunan Agricultural University, Changsha, China.
Frontiers in plant science
|September 29, 2025
概括
本研究介绍了一种改进的PointNet++模型,用于使用无人机图像进行高通量烟草表型化. 该方法准确地测量了植物特征,为先进的作物分析提供了基础.
科学领域:
- 农业科学 农业科学
- 计算机视觉 计算机视觉
- 遥感 遥感 遥感 遥感
背景情况:
- 准确的烟草表型特征获取对于作物管理和研究至关重要.
- 传统的手动测量对于大规模,高通量现场表型化是低效的.
- 3D重建和茎叶细分为自动化表型化提供了一个有希望的替代方案.
研究的目的:
- 开发一种使用无人机 (UAV) 遥感和改进的PointNet++模型的自动烟草表型化方法.
- 增强PointNet++架构,以便在3D点云中准确地对树干和树叶进行细分.
- 建立一个自动化管道来计算烟草的关键表型特征.
主要方法:
- 使用多视图无人机图像生成了田间种植的烟草的3D点云数据集.
- 通过本地空间编码 (LSE) 和密度意识聚合 (DAP) 模块增强了PointNet++模型.
- 开发了一个自动化管道,从细分数据计算植物高度,叶子尺寸,叶子数和内部节点长度.
主要成果:
- 改进的PointNet++模型实现了95.25%的整体准确度和93.97%的烟草植物细分量.
- 与最初的PointNet++相比,观察到5.12% (OA) 和5.55% (mIoU) 的显著改善.
- 现型特征预测与基本真相数据有很强的一致性 (R2:0.860.95,RMSE:0.312.27厘米).
结论:
- 拟议的基于无人机的表型化方法与改进的PointNet++提供了准确和高效的烟草特征获取.
- 这种方法为各种作物的高通量表型化提供了一个可转移的框架.
- 该研究为推进自动化作物分析和管理实践奠定了技术基础.
相关概念视频
02:16Light Acquisition
9.4K
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.
9.4K
02:35Key Elements for Plant Nutrition
23.9K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
23.9K