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

Expression and clinical diagnostic value of miR-383 in patients with severe preeclampsia.

Cellular and molecular biology (Noisy-le-Grand, France)·2020
Same author

FNDC5 Attenuates Oxidative Stress and NLRP3 Inflammasome Activation in Vascular Smooth Muscle Cells via Activating the AMPK-SIRT1 Signal Pathway.

Oxidative medicine and cellular longevity·2020
Same author

Obesity-induced excess of 17-hydroxyprogesterone promotes hyperglycemia through activation of glucocorticoid receptor.

The Journal of clinical investigation·2020
Same author

Human neutralizing antibodies elicited by SARS-CoV-2 infection.

Nature·2020
Same author

Extensive intracranial arterial dolichoectasia involving distal branches of intracranial arteries: two cases report and review of the literature.

The International journal of neuroscience·2020
Same author

Photocaged FRET nanoflares for intracellular microRNA imaging.

Chemical communications (Cambridge, England)·2020

Related Experiment Video

Updated: Jun 19, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

8.9K

Monocular Pose Estimation Method for Automatic Citrus Harvesting Using Semantic Segmentation and Rotating Target

Xu Xiao1,2, Yaonan Wang1,2, Yiming Jiang1,2

  • 1College of Electrical and Information Engineering, Hunan University, Changsha 410082, China.

Foods (Basel, Switzerland)
|July 27, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a novel method for robotic citrus harvesting, improving fruit recognition and positioning accuracy. The new approach enhances the success rate of automated fruit picking in orchards.

Keywords:
automatic harvestingcitrus fruitmonocular pose estimationrotating target detectionsemantic segmentation

More Related Videos

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

2.7K
Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

765

Related Experiment Videos

Last Updated: Jun 19, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

8.9K
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

2.7K
Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

765

Area of Science:

  • Agricultural Robotics
  • Computer Vision
  • Machine Learning

Background:

  • Robotic harvesting of citrus fruits is hindered by inaccurate spatial pose information and low positioning accuracy of the target fruit.
  • Existing methods lack the precision required for efficient and reliable automated citrus picking.

Purpose of the Study:

  • To develop and validate a new method for automatic citrus fruit harvesting using semantic segmentation and rotating target detection.
  • To improve the spatial pose estimation and positioning accuracy for citrus-picking robots.

Main Methods:

  • Utilized Faster R-CNN for grab detection and a semantic segmentation network to extract citrus fruit contour information.
  • Employed image processing and a camera imaging model to refine fruit segmentation, estimate rough angles, and fit contour, centroid, and boundary frames.
  • Estimated the 3D pose of citrus fruits based on their positional relationship with epiphytic branches.

Main Results:

  • Achieved a 93.6% success rate for citrus fruit recognition and positioning.
  • Obtained an average attitude estimation angle error of 7.9°.
  • Reached an 85.1% success rate for fruit picking with an average picking time of 5.6 seconds.

Conclusions:

  • The proposed method effectively addresses the challenges of spatial pose information and positioning accuracy in robotic citrus harvesting.
  • The validated approach demonstrates the potential for robots to perform intelligent picking operations efficiently in natural orchard environments.