Cucumber seedlings segmentation network based on multi-view geometric graph encoder from 3D point clouds DOI Creative Commons
Yonglong Zhang,

Yaling Xie,

Jialuo Zhou

et al.

Plant Phenomics, Journal Year: 2024, Volume and Issue: 6

Published: Jan. 1, 2024

Plant phenotyping plays a pivotal role in observing and comprehending the growth development of plants. In phenotyping, plant organ segmentation based on 3D point clouds has garnered increasing attention recent years. However, using only geometric relationship features Euclidean space still cannot accurately segment measure To this end, we mine more propose network multiview graph encoder, called SN-MGGE. First, construct cloud acquisition platform to obtain cucumber seedling dataset, employ CloudCompare software annotate data. The GGE module is then designed generate features, including relationships shape structure, via encoder over hyperbolic spaces. Finally, semantic results are obtained downsampling operation multilayer perceptron. Extensive experiments dataset clearly show that our proposed SN-MGGE outperforms several mainstream networks (e.g., PointNet++, AGConv, PointMLP), achieving mIoU OA values 94.90% 97.43%, respectively. On basis results, 4 phenotypic parameters (i.e., height, leaf length, width, area) extracted through K-means clustering method; these very close ground truth,

Language: Английский

A simple oriented search and clustering method for extracting individual forest trees from ALS point clouds DOI Creative Commons

Wenhui Ding,

Rong Huang, Wei Yao

et al.

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 102978 - 102978

Published: Jan. 1, 2025

Language: Английский

Citations

1
A new unified framework for supervised 3D crown segmentation (TreeisoNet) using deep neural networks across airborne, UAV-borne, and terrestrial laser scans DOI Creative Commons
Zhouxin Xi, Dani Degenhardt

ISPRS Open Journal of Photogrammetry and Remote Sensing, Journal Year: 2025, Volume and Issue: unknown, P. 100083 - 100083

Published: Jan. 1, 2025

Language: Английский

Citations

1
STFCropNet: A Spatio-Temporal Fusion Network for Crop Classification in Multi-Resolution Remote Sensing Images DOI Creative Commons
Wei Wu,

Yapeng Liu,

Kun Li

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2025, Volume and Issue: 18, P. 4736 - 4750

Published: Jan. 1, 2025

Language: Английский

Citations

1
Low-cost phone-based LiDAR scanning technology provides sub-centimeter accuracy when measuring the main dimensions of motor-manual tree felling cuts DOI Creative Commons
Stelian Alexandru Borz, Andrea Rosario Proto

Ecological Informatics, Journal Year: 2025, Volume and Issue: 85, P. 102999 - 102999

Published: Jan. 8, 2025

Language: Английский

Citations

0
TLSLeaf: Unsupervised Instance Segmentation of Broadleaf Leaf Count and Area from TLS Point Clouds DOI
Guangpeng Fan,

Ruoyoulan Wang,

Cheng‐Ye Wang

et al.

IEEE Transactions on Geoscience and Remote Sensing, Journal Year: 2025, Volume and Issue: 63, P. 1 - 15

Published: Jan. 1, 2025

Language: Английский

Citations

0
Estimating Olive Tree Density in Delimited Areas Using Sentinel-2 Images DOI Creative Commons
Adolfo Lozano-Tello,

Jorge Luceño,

Andrés Caballero-Mancera

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(3), P. 508 - 508

Published: Jan. 31, 2025

The objective of this study is to develop a method for estimating the density olive trees in delimited plots using low-resolution images from Sentinel-2 satellite. This approach particularly relevant certain regions where high-resolution orthophotos, which are often costly and not always available, cannot be accessed. focuses on Extremadura region Spain, 48,530 were analysed. Data Sentinel-2’s multispectral bands obtained each plot, Random Forest Regression (RFR) model was used correlate these values with number trees, previously counted orthophotos machine learning object detection techniques. results show that proposed can predict tree within an acceptable error margin, especially useful distinguishing greater than 300 per hectare—a key criterion allocating agricultural subsidies region. Although accuracy optimal, average ±15.04 hectare makes it viable tool practical applications extreme precision required. developed may also extrapolated other cases crop types, such as fruit or forest masses, offering efficient solution annual estimates without relying aerial images. Future research could enhance by grouping according additional characteristics, size plantation type.

Language: Английский

Citations

0
Evaluating sowing uniformity in hybrid rice using image processing and the OEW-YOLOv8n network DOI Creative Commons
Zehua Li,

Yihui Pan,

Xu Ma

et al.

Frontiers in Plant Science, Journal Year: 2025, Volume and Issue: 16

Published: Feb. 3, 2025

Sowing uniformity is an important evaluation indicator of mechanical sowing quality. In order to achieve accurate in hybrid rice sowing, this study takes the seeds a seedling tray blanket-seedling nursing as research object and proposes method for evaluating by combining image processing methods ODConv_C2f-ECA-WIoU-YOLOv8n (OEW-YOLOv8n) network. Firstly, are used segment seed obtain grids. Next, improved model named OEW-YOLOv8n based on YOLOv8n proposed identify number unit grid. The strategies include following: (1) Replacing Conv module Bottleneck C2f modules with Omni-Dimensional Dynamic Convolution (ODConv) module, where located at connection between Backbone Neck. This improvement can enhance feature extraction ability network, new fully utilize information all dimensions convolutional kernel. (2) An Efficient Channel Attention (ECA) added Neck improving network’s capability extract deep semantic detection target. (3) Bbox prediction head, Complete Intersection over Union (CIoU) loss function replaced Weighted version 3 (WIoUv3) improve convergence speed bounding box reduce value function. results show that mean average precision (mAP) network reaches 98.6%. Compared original model, mAP 2.5%. advanced algorithms such Faster-RCNN, SSD, YOLOv4, YOLOv5s YOLOv7-tiny, YOLOv10s, increased 5.2%, 7.8%, 4.9%, 2.8% 2.9%, 3.3%, respectively. Finally, actual experiment showed test error from −2.43% 2.92%, indicating demonstrates excellent estimation accuracy. provide support mechanized quality intelligent seeder.

Language: Английский

Citations

0
Online segmentation of street trees from mobile laser scanning data via deep learning image instance segmentation DOI
Qiujie Li, Junjie Gao

Optics & Laser Technology, Journal Year: 2025, Volume and Issue: 184, P. 112603 - 112603

Published: Feb. 13, 2025

Language: Английский

Citations

0
Three-Dimensional Point Cloud Applications, Datasets, and Compression Methodologies for Remote Sensing: A Meta-Survey DOI Creative Commons
Emil Dumić, Luís A. da Silva Cruz

Sensors, Journal Year: 2025, Volume and Issue: 25(6), P. 1660 - 1660

Published: March 7, 2025

This meta-survey provides a comprehensive review of 3D point cloud (PC) applications in remote sensing (RS), essential datasets available for research and development purposes, state-of-the-art compression methods. It offers exploration the diverse clouds sensing, including specialized tasks within field, precision agriculture-focused applications, broader general uses. Furthermore, that are commonly used remote-sensing-related surveyed, urban, outdoor, indoor environment datasets; vehicle-related object agriculture-related other more datasets. Due to their importance practical this article also surveys technologies from widely tree- projection-based methods recent deep learning (DL)-based technologies. study synthesizes insights previous reviews original identify emerging trends, challenges, opportunities, serving as valuable resource advancing use sensing.

Language: Английский

Citations

0
PRISMA Review: Drones and AI in Inventory Creation of Signage DOI Creative Commons

Geovanny Satama-Bermeo,

José Manuel López-Guede, Javad Rahebi

et al.

Drones, Journal Year: 2025, Volume and Issue: 9(3), P. 221 - 221

Published: March 19, 2025

This systematic review explores the integration of unmanned aerial vehicles (UAVs) and artificial intelligence (AI) in automating road signage inventory creation, employing preferred reporting items for reviews meta-analyses (PRISMA) methodology to analyze recent advancements. The study evaluates cutting-edge technologies, including UAVs equipped with deep learning algorithms advanced sensors like light detection ranging (LiDAR) multispectral cameras, highlighting their roles enhancing traffic sign classification. Key challenges include detecting minor or partially obscured signs adapting diverse environmental conditions. findings reveal significant progress automation, notable improvements accuracy, efficiency, real-time processing capabilities. However, limitations such as computational demands variability persist. By providing a comprehensive synthesis current methodologies performance metrics, this establishes robust foundation future research advance automated infrastructure management improve safety operational efficiency urban rural settings.

Language: Английский

Citations

0