Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

In vitro and in vivo drug release behavior and osteogenic potential of a composite scaffold based on poly(ε-caprolactone)-block-poly(lactic-co-glycolic acid) and β-tricalcium phosphate.

Journal of materials chemistry. B·2020
Same author

Nerve conduits constructed by electrospun P(LLA-CL) nanofibers and PLLA nanofiber yarns.

Journal of materials chemistry. B·2020
Same author

Polypyrrole-coated poly(l-lactic acid-co-ε-caprolactone)/silk fibroin nanofibrous membranes promoting neural cell proliferation and differentiation with electrical stimulation.

Journal of materials chemistry. B·2020
Same author

Upregulation of deubiquitinase PSMD14 in lung adenocarcinoma (LUAD) and its prognostic significance.

Journal of Cancer·2020
Same author

Rapid Identification of X-ray Diffraction Patterns Based on Very Limited Data by Interpretable Convolutional Neural Networks.

Journal of chemical information and modeling·2020
Same author

CCR4, a RNA decay factor, is hijacked by a plant cytorhabdovirus phosphoprotein to facilitate virus replication.

eLife·2020
Same journal

PlasmiDB: an open-source and customizable database for plasmid lifecycle management in multi-user, multi-project plant molecular biology laboratories.

Plant methods·2026
Same journal

Establishment of a protoplast isolation and transient transformation system for tung tree (Vernicia fordii).

Plant methods·2026
Same journal

Deep aerenchyma: a transformer-based pipeline for scalable phenotyping of rice root aerenchyma lacunae across environments.

Plant methods·2026
Same journal

Comparative analysis of SP3 and S-Trap sample preparation protocols for proteomic profiling associated with somatic embryogenesis efficiency in Olea europaea L.

Plant methods·2026
Same journal

DAPR-AM-Net: an end-to-end smart farming system powered by dual-attention progressive refinement and adaptive MixUp for explainable tomato leaf disease classification and forecasting.

Plant methods·2026
Same journal

Deep soil layers show the most pronounced genetic variation in wheat root length.

Plant methods·2026
See all related articles

Related Experiment Video

Updated: Jul 11, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

A comparative study on point cloud down-sampling strategies for deep learning-based crop organ segmentation.

Dawei Li1,2,3, Yongchang Wei4, Rongsheng Zhu5,6

  • 1Engineering Research Center of Digitized Textile and Fashion Technology, Ministry of Education, Donghua University, Shanghai, 201620, China. daweili@dhu.edu.cn.

Plant Methods
|November 11, 2023
PubMed
Summary
This summary is machine-generated.

This study comprehensively evaluates down-sampling strategies for 3D crop point cloud segmentation. No single strategy excels across all deep learning networks, but 3DEPS and UVS show promise for semantic segmentation.

Keywords:
3D crop dataCrop organ segmentationDeep learningPlant phenotypingPoint cloud down-sampling

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

435
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.9K

Related Experiment Videos

Last Updated: Jul 11, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

435
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.9K

Area of Science:

  • Agricultural Science
  • Computer Vision
  • Machine Learning

Background:

  • 3D crop data is crucial for modern breeding and yield improvement.
  • Deep learning models require fixed-scale, consistent point cloud inputs for training.
  • Effective down-sampling is vital for noise reduction and preserving 3D spatial structures in crop point clouds.

Purpose of the Study:

  • To conduct the first comprehensive study on the relationship between down-sampling strategies and deep learning network performance for plant point clouds.
  • To evaluate five down-sampling strategies (FPS, RS, UVS, VFPS, 3DEPS) against five segmentation networks (PointNet++, DGCNN, PlantNet, ASIS, PSegNet).

Main Methods:

  • Cross-evaluation of five distinct down-sampling strategies.
  • Testing these strategies on five popular deep learning-based segmentation networks.
  • Analysis of both qualitative and quantitative experimental results.

Main Results:

  • No universal 'golden rule' exists for selecting a down-sampling strategy for crop deep learning networks; optimal choices vary by network.
  • 3DEPS and UVS generally yield superior results for semantic segmentation networks.
  • Voxel-based strategies may be better suited for complex, dual-function networks.
  • At 4096-point resolution, 3DEPS demonstrates high stability, closely matching the best-performing strategies.

Conclusions:

  • The optimal down-sampling strategy is network-dependent for 3D crop organ segmentation.
  • 3DEPS emerges as a consistently stable and effective option across various networks.
  • Findings provide guidance for selecting appropriate down-sampling methods to enhance deep learning model accuracy in agriculture.