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

Comparison and development of machine learning tools for the prediction of chronic obstructive pulmonary disease in the Chinese population.

Journal of translational medicine·2020
Same author

Transplanted senescent renal scattered tubular-like cells induce injury in the mouse kidney.

American journal of physiology. Renal physiology·2020
Same author

Mesenchymal Stem Cell-Derived Extracellular Vesicles Induce Regulatory T Cells to Ameliorate Chronic Kidney Injury.

Hypertension (Dallas, Tex. : 1979)·2020
Same author

miR-34a regulates adipogenesis in porcine intramuscular adipocytes by targeting ACSL4.

BMC genetics·2020
Same author

Design and synthesis of novel 2-arylbenzimidazoles as selective mutant isocitrate dehydrogenase 2 R140Q inhibitors.

Bioorganic & medicinal chemistry letters·2020
Same author

Gene expression analysis reveals the tipping points during infant brain development for human and chimpanzee.

BMC genomics·2020

Related Experiment Video

Updated: Aug 8, 2025

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
11:37

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

16.3K

A method of cotton root segmentation based on edge devices.

Qiushi Yu1, Hui Tang1, Lingxiao Zhu2

  • 1College of Mechanical and Electrical Engineering, Hebei Agricultural University, Baoding, China.

Frontiers in Plant Science
|March 6, 2023
PubMed
Summary

This study introduces a low-cost, edge-deployed system for precise in situ root segmentation using an improved semantic model. The method enhances analysis efficiency and portability for outdoor plant root research.

Keywords:
edge equipmenthigh-throughput phenotypein situ rootlow-cost acquisitionsemantic segmentation

More Related Videos

Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform
09:23

Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform

Published on: August 15, 2017

8.6K
Micron-scale Phenotyping Techniques of Maize Vascular Bundles Based on X-ray Microcomputed Tomography
06:21

Micron-scale Phenotyping Techniques of Maize Vascular Bundles Based on X-ray Microcomputed Tomography

Published on: October 9, 2018

8.9K

Related Experiment Videos

Last Updated: Aug 8, 2025

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
11:37

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

16.3K
Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform
09:23

Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform

Published on: August 15, 2017

8.6K
Micron-scale Phenotyping Techniques of Maize Vascular Bundles Based on X-ray Microcomputed Tomography
06:21

Micron-scale Phenotyping Techniques of Maize Vascular Bundles Based on X-ray Microcomputed Tomography

Published on: October 9, 2018

8.9K

Area of Science:

  • Plant science
  • Computer vision
  • Agricultural technology

Background:

  • In situ root research is crucial for understanding plant water and nutrient uptake.
  • Current methods face challenges in efficiency, cost, and outdoor deployment of image acquisition devices.
  • Accurate root phenotype analysis requires efficient and accessible imaging techniques.

Purpose of the Study:

  • To develop a precise and efficient in situ root extraction method using semantic segmentation and edge computing.
  • To overcome the limitations of high cost, low efficiency, and difficult outdoor deployment in current root research.
  • To enable low-cost, portable, and high-precision root image acquisition and segmentation for field applications.

Main Methods:

  • Designed a precise in situ root extraction method based on a semantic segmentation model and edge device deployment.
  • Proposed two data expansion methods (pixel by pixel, equal proportion) to increase dataset size.
  • Developed an improved DeeplabV3+ root segmentation model incorporating CBAM and ASPP modules.
  • Implemented a time-saving Fast prediction strategy for accelerated image analysis.
  • Deployed the model on a Raspberry Pi for portable and low-cost field application.

Main Results:

  • Achieved a root segmentation accuracy of 93.01% with the improved DeeplabV3+ model.
  • Verified root phenotype parameters with low errors: 0.669% for root length and 1.003% for root diameter.
  • Reduced time consumption by 22.71% on GPU and 36.85% on Raspberry Pi using the Fast prediction strategy.
  • Demonstrated a low-cost ($247) and energy-efficient (0.051kWh) system for 8-hour operation.
  • Successfully deployed a portable and cost-effective solution for in situ root image acquisition and segmentation.

Conclusions:

  • The proposed method offers high accuracy, economic feasibility, and low energy consumption for in situ root segmentation.
  • Edge device deployment enables high-throughput field research and practical applications of in situ root analysis.
  • This approach provides new insights for advancing the efficiency and accessibility of plant root phenotyping in real-world conditions.