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

Astrocyte elevated gene-1 induces breast cancer proliferation and invasion through upregulating HER2/neu expression.

Chinese medical journal·2012
Same author

Inhibition of proliferation, viability, migration and invasion of gastric cancer cells by Aurora-A deletion.

Asian Pacific journal of cancer prevention : APJCP·2012
Same author

Repression of PDGF-R-α after cellular injury involves TNF-α, formation of a c-Fos-YY1 complex, and negative regulation by HDAC.

American journal of physiology. Cell physiology·2012
Same author

Single-stage posterior debridement and single-level instrumented fusion for spontaneous infectious spondylodiscitis of the lumbar spine.

Acta orthopaedica Belgica·2012
Same author

Cancer prevention health services research: an emerging field.

Journal of cancer education : the official journal of the American Association for Cancer Education·2012
Same author

[Assessment of cochlear implant performance with Mandarin Hearing In Noise Test].

Lin chuang er bi yan hou tou jing wai ke za zhi = Journal of clinical otorhinolaryngology head and neck surgery·2012
Same journal

UAV-based temporal synergistic estimation of multiple alfalfa qualities integrating physics-informed network and 3D allometric operator.

Plant phenomics (Washington, D.C.)·2026
Same journal

Machine learning to predict genotypes and genotype-environment interaction associated with complex traits for genomic selection.

Plant phenomics (Washington, D.C.)·2026
Same journal

FQGR-net: Morphology-based litchi flower quantification and gender recognition.

Plant phenomics (Washington, D.C.)·2026
Same journal

Thermal image segmentation in weedy fields via synthetic RGB-trained models and GAN-based cross-modality alignment.

Plant phenomics (Washington, D.C.)·2026
Same journal

Unlocking almond breeding for nutritional composition with hyperspectral imaging.

Plant phenomics (Washington, D.C.)·2026
Same journal

From plots to commercial fields: scalable, transferable cotton morphology and productivity estimation using functional growth proxies from UAV and PlanetScope time series.

Plant phenomics (Washington, D.C.)·2026
See all related articles

Related Experiment Video

Updated: Jan 8, 2026

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.8K

PodNet: Pod real-time instance segmentation in pre-harvest soybean fields.

Shuo Zhou1, Qixin Sun1,2, Ning Zhang1,3

  • 1Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China.

Plant Phenomics (Washington, D.C.)
|December 19, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces PodNet, a novel instance segmentation model for accurately identifying soybean pods in preharvest fields. This breakthrough enables precise, noninvasive phenotyping crucial for advancing soybean breeding research.

Keywords:
High-throughput field phenotypingInstance segmentationPre-harvest datasetSoybean pod

More Related Videos

High-Throughput Analysis of Non-Photochemical Quenching in Crops Using Pulse Amplitude Modulated Chlorophyll Fluorometry
10:08

High-Throughput Analysis of Non-Photochemical Quenching in Crops Using Pulse Amplitude Modulated Chlorophyll Fluorometry

Published on: July 6, 2022

4.7K
Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes
06:41

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

1.5K

Related Experiment Videos

Last Updated: Jan 8, 2026

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.8K
High-Throughput Analysis of Non-Photochemical Quenching in Crops Using Pulse Amplitude Modulated Chlorophyll Fluorometry
10:08

High-Throughput Analysis of Non-Photochemical Quenching in Crops Using Pulse Amplitude Modulated Chlorophyll Fluorometry

Published on: July 6, 2022

4.7K
Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes
06:41

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

1.5K

Area of Science:

  • Agricultural Science
  • Computer Vision
  • Plant Breeding

Background:

  • Noninvasive pod phenotyping is vital for soybean breeding.
  • Existing methods are limited to postharvest or indoor settings, lacking real-field applicability.

Purpose of the Study:

  • To develop a precise, noninvasive method for extracting soybean pod areas from images in preharvest fields.
  • To create a robust instance segmentation model for real-world field conditions.

Main Methods:

  • A cost-effective workflow for dataset creation using video recording and automatic frame selection.
  • Utilized a large vision model for dense annotation, building a 20k soybean pod mask dataset.
  • Developed PodNet, an instance segmentation model based on YOLOv8, incorporating hierarchical prototype aggregation and U-EMA for small object detection.

Main Results:

  • PodNet achieved a mean average accuracy of 0.786 on a custom pod segmentation dataset.
  • The model demonstrates competitive performance on in-field images without a backdrop.
  • PodNet enables real-time inference on edge computing platforms.

Conclusions:

  • PodNet is the first instance segmentation model for preharvest soybean fields, offering low-cost, high-precision pod extraction.
  • This technology is essential for phenotypic analysis and cross-scale phenotyping from plant to seed levels.