Unsupervised Semantic Segmenting TLS Data of Individual Tree Based on Smoothness Constraint Using Open-Source Datasets

点云 分割 计算机科学 树(集合论) 图像分割 人工智能 模式识别(心理学) 遥感 数学 地质学 数学分析
作者
Yanqi Dong,Zhibin Ma,Fang Xu,Feixiang Chen
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:60: 1-15 被引量:1
标识
DOI:10.1109/tgrs.2022.3218442
摘要

Unsupervised segmentation of Terrestrial Laser Scanning (TLS) data into wood and leaf is the key for studying forest carbon storage, photosynthesis, canopy radiation. Further segmentation of wood data into trunk and larger branch (TLB), remaining branch (RB) is of great significance and challenge for dust retention, soil heavy metal enrichment. We proposed an unsupervised, automatic semantic segmentation method based on TLS data of individual tree. The method firstly performs initial segmentation based on plane fitting residuals and neighborhood normal angle, which can extract smooth and connected regions in point cloud. Then, the geometric features of segmented clusters are quantified to approximate RB or leaf features. Finally, the segmentation of TLB, RB, and leaf is realized by combining different clusters from bottom to top with geometric features and neighborhood relations. The segmentation performance of our method was evaluated with 104 tree samples from 23 tree species in two open-source datasets from Indonesia, Peru, Guyana and from Canada and Finland. The micro-average precision of our method is 93.61%. The micro-average recalls of TLB, RB, and leaf are 97.08%, 86.44%, and 89.62%. Compared with the well-known method of separating wood and leaf, our method has 33.56% higher sensitivity, 1.82% higher specificity, 20.52% higher precision, and 0.217 higher F1-score. Besides, we estimated the surface area and volume of TLB, the surface area and volume of RB based on the segmented data. The above parameters have good consistency compared to those calculated based on manually separated point clouds (Pearson correlation coefficient (PCC) of 0.55-0.93).
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
Hello应助科研通管家采纳,获得10
1秒前
yydragen应助科研通管家采纳,获得50
1秒前
ll应助科研通管家采纳,获得10
1秒前
1秒前
赘婿应助科研通管家采纳,获得10
1秒前
隐形曼青应助科研通管家采纳,获得10
1秒前
FashionBoy应助科研通管家采纳,获得10
1秒前
yydragen应助科研通管家采纳,获得50
1秒前
赘婿应助科研通管家采纳,获得10
1秒前
lu777完成签到,获得积分10
1秒前
NexusExplorer应助科研通管家采纳,获得10
1秒前
桐桐应助科研通管家采纳,获得10
1秒前
seven_yao完成签到,获得积分10
1秒前
1秒前
彭于晏应助科研通管家采纳,获得10
1秒前
2秒前
2秒前
2秒前
2秒前
2秒前
2秒前
wanci应助满意芯采纳,获得10
2秒前
2秒前
LLL完成签到,获得积分10
3秒前
陈pc发布了新的文献求助10
3秒前
Ava应助YIZEXIN采纳,获得10
4秒前
莹崽无敌完成签到,获得积分10
4秒前
hjz完成签到,获得积分10
5秒前
5秒前
6秒前
七仔完成签到,获得积分10
6秒前
自觉的傲薇应助下周末采纳,获得10
6秒前
wenbo发布了新的文献求助30
7秒前
小乐应助啦啦啦啦啦采纳,获得10
7秒前
怕黑向日葵完成签到,获得积分10
7秒前
7秒前
curry发布了新的文献求助20
8秒前
tianhaizhi完成签到,获得积分20
8秒前
学术小白完成签到,获得积分10
9秒前
迷人依白完成签到,获得积分10
9秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3969222
求助须知:如何正确求助?哪些是违规求助? 3514124
关于积分的说明 11171948
捐赠科研通 3249361
什么是DOI,文献DOI怎么找? 1794799
邀请新用户注册赠送积分活动 875431
科研通“疑难数据库(出版商)”最低求助积分说明 804779