SPGrowing: an unsupervised individual plant segmentation pipeline from UAV-derived point clouds for high-throughput in-field maize phenotyping

点云 分割 天蓬 交叉口(航空) 管道(软件) 人工智能 分拆(数论) 摄影测量学 计算机科学 图像分割 模式识别(心理学) 数据挖掘 领域(数学) 遥感 数学 可扩展性 目标检测 聚类分析 抽象 马尔可夫随机场 植物冠层 点(几何) 对象(语法)
作者
Ziang Niu,Ting Huang,Chen Yang,Xinyue Sun,Yong He,Zhengjun Qiu
出处
期刊:Artificial intelligence in agriculture [Elsevier BV]
标识
DOI:10.1016/j.aiia.2026.10.007
摘要

In-field plant phenotyping is essential for understanding gene–environment interactions and supporting crop breeding. While unmanned aerial vehicle (UAV)-based photogrammetry enables high-throughput three-dimensional (3D) sensing, accurate plant-level analysis of densely planted crops like maize remains challenging due to morphological complexity, leaf occlusion, and dynamic canopy structures. To address these issues, this study develops an end-to-end phenotyping pipeline based on UAV-derived point clouds, incorporating cross-circling oblique (CCO) flight sampling, point cloud reconstruction and preprocessing, individual plant segmentation, and trait extraction, which is applied to multiple maize varieties (ZD 958, SKT 1506, SBR), growth stages (V3–R2), and planting spacings (0.4–0.8 m). At the core of the pipeline, an unsupervised individual plant segmentation algorithm (SPGrowing) is proposed, which integrates stem core detection via ground-projected density analysis, superpoint-based structural abstraction for efficient homogeneous partition representation, and multi-source shortest-path optimization incorporating stem-centered growth patterns as topological constraints. Validation results showed that SPGrowing consistently outperformed existing segmentation benchmarks, achieving an overall accuracy (OA) of 0.950 and a mean intersection over union (mIoU) of 0.898 at the point level, and an AP 50 of 0.949 at the object level. The extracted plant-level traits closely matched manual measurements, with a mean absolute error (MAE) of 0.068 m and a coefficient of determination ( R 2 ) of 0.975 for plant height. Multi-dimensional architectural traits, including plant height, canopy volume, and height-to-width ratio, were further analyzed across varieties and growth stages, revealing distinct architectural profiles among cultivars. This study provides a scalable tool for acquiring fine-grained phenotypic data under field conditions, supplying valuable data support for precision field management and breeding. The source code and dataset are available at https://github.com/Joyar546/SPGrowing.git .

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
2秒前
呼呼夫人完成签到,获得积分10
2秒前
4秒前
5秒前
5秒前
weitao0916完成签到,获得积分10
5秒前
冬冬完成签到,获得积分10
6秒前
小蘑菇的应助被杨淼采纳,获得10
6秒前
爱听歌的沛儿完成签到 ,获得积分20
6秒前
6秒前
7秒前
8秒前
李健的小迷弟的应助被晓天采纳,获得10
8秒前
张伟的应助被钱罐罐采纳,获得10
8秒前
Zzha10发布了新的文献求助10
8秒前
8秒前
是我呀吼发布了新的文献求助20
9秒前
Orange的应助被土豪的城采纳,获得30
11秒前
XS_QI发布了新的文献求助10
11秒前
还有早安完成签到,获得积分10
11秒前
安详的夜春完成签到,获得积分10
11秒前
小鱼干完成签到,获得积分10
11秒前
自由的王发布了新的文献求助10
12秒前
开朗紫发布了新的文献求助10
12秒前
叶95完成签到,获得积分10
13秒前
13秒前
14秒前
14秒前
Maestro_S的应助被小鱼干采纳,获得10
15秒前
15秒前
吕锴岐完成签到 ,获得积分10
16秒前
huang完成签到 ,获得积分10
16秒前
16秒前
zjjcug完成签到,获得积分10
16秒前
苦昼短完成签到 ,获得积分10
16秒前
zzl完成签到,获得积分10
16秒前
大个的应助被小青采纳,获得10
17秒前
anqi6688完成签到,获得积分10
17秒前
Zzha10完成签到,获得积分10
17秒前
CarryLJR发布了新的文献求助10
17秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8181658
求助须知:如何正确求助?哪些是违规求助? 9571454
关于积分的说明 21818081
捐赠科研通 7777987
什么是DOI,文献DOI怎么找? 3433508
关于科研通互助平台的介绍 2557696
邀请新用户注册赠送积分活动 2479568