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

Efficacy and safety of dual antiplatelet treatment up to 72 hours after mild ischemic stroke or transient ischemic attack in patients with established cardiovascular disease.

Neurotherapeutics : the journal of the American Society for Experimental NeuroTherapeutics·2026
Same author

Benzothiadiazole-based covalent organic frameworks with red-light emission for visual detection of norfloxacin.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Clinical and neuroimaging correlates of motoric cognitive risk syndrome in cerebral small vessel disease: a cross-sectional study.

Frontiers in aging neuroscience·2026
Same author

Dual Antiplatelet Therapy and Immediate Intensive Statin in Mild Ischemic Stroke: A Randomized Trial.

Neurology·2026
Same author

Multi-omics integration and clinical validation identify CKAP2 as a diagnostic biomarker for bladder cancer.

World journal of surgical oncology·2026
Same author

ABCD-GENE Score Stratifying Risk-Benefit Profile of Clopidogrel-Aspirin Therapy in Ischemic Stroke Within 24-72 Hours.

Journal of stroke·2026

Related Experiment Video

Updated: Jun 5, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.3K

Hydroponic Chinese flowering cabbage detection and localization algorithm based on improved YOLOv5s.

Zhongjian Xie1, Yaya Zhang1, Weilin Wu1,2

  • 1School of Physics and Electronic Information, Guangxi Minzu University, Nanning, China.

Plos One
|December 16, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a two-stage algorithm for detecting and localizing hydroponic Chinese flowering cabbage, enhancing automated harvesting. The improved P-YOLOv5s-GRNF and YOLOv5s-SBC models achieve higher accuracy and efficiency.

More Related Videos

Visual Detection of Multiple Nucleic Acids in a Capillary Array
08:56

Visual Detection of Multiple Nucleic Acids in a Capillary Array

Published on: November 15, 2017

7.2K
Development of a Cabbage Protoplast System for Studying Hypoxia Tolerance in Brassica
08:09

Development of a Cabbage Protoplast System for Studying Hypoxia Tolerance in Brassica

Published on: September 20, 2024

402

Related Experiment Videos

Last Updated: Jun 5, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.3K
Visual Detection of Multiple Nucleic Acids in a Capillary Array
08:56

Visual Detection of Multiple Nucleic Acids in a Capillary Array

Published on: November 15, 2017

7.2K
Development of a Cabbage Protoplast System for Studying Hypoxia Tolerance in Brassica
08:09

Development of a Cabbage Protoplast System for Studying Hypoxia Tolerance in Brassica

Published on: September 20, 2024

402

Area of Science:

  • Agricultural Engineering
  • Computer Vision
  • Robotics

Background:

  • Automated harvesting of hydroponic crops requires precise detection and localization of plants.
  • Existing object detection algorithms may lack the efficiency and accuracy needed for real-time agricultural applications.
  • Hydroponic Chinese flowering cabbage presents unique challenges for automated harvesting systems.

Purpose of the Study:

  • To develop a robust two-stage algorithm for the detection and localization of hydroponic Chinese flowering cabbage.
  • To improve the performance of object detection models for enhanced automated harvesting systems.
  • To provide a technical foundation for intelligent and automated harvesting solutions in hydroponics.

Main Methods:

  • Proposed a macro-detection algorithm, P-YOLOv5s-GRNF, incorporating pruning, GSConv, receptive field attention convolution (RFAConv), normalization-based attention module (NAM), and Focal-EIOU Loss.
  • Developed a micro-localization algorithm, YOLOv5s-SBC, featuring an adjusted detection layer configuration, weighted bidirectional feature pyramid network (BiFPN), and coordinate attention (CA) mechanism.
  • Integrated the improved models with a depth camera to create a positioning system.

Main Results:

  • P-YOLOv5s-GRNF demonstrated significant mAP (mean average precision) improvements over various mainstream object detection algorithms.
  • P-YOLOv5s-GRNF achieved reduced parameters (18%), model size (11.9MB), and FLOPs (14.5G), while increasing FPS by 4.3 compared to the original YOLOv5s.
  • YOLOv5s-SBC increased mAP by 4.0% with substantial reductions in parameters (65%), model size (60%), and FLOPs (15.3G) compared to the original YOLOv5s.

Conclusions:

  • The proposed P-YOLOv5s-GRNF and YOLOv5s-SBC algorithms significantly enhance the detection and localization accuracy and efficiency for hydroponic Chinese flowering cabbage.
  • These optimized models contribute to the development of practical and intelligent automated harvesting systems in controlled agricultural environments.
  • The developed positioning system offers valuable technical support for advancing automated and intelligent harvesting in hydroponics.