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

Direct air capture technologies: innovations, integration, and pathways to scale.

Chemical Society reviews·2026
Same author

Utidelone exhibits favorable responses in refractory patients with advanced breast cancer.

Translational cancer research·2026
Same author

Clinical multidimensional prediction model for futile reperfusion in acute ischemic stroke after endovascular thrombectomy.

Frontiers in neurology·2026
Same author

Indolent natural killer-cell lymphoproliferative disorder of the gallbladder: a rare case report.

Frontiers in oncology·2026
Same author

Effect of dapagliflozin on heart failure with reduced ejection fraction in children.

Frontiers in cardiovascular medicine·2026
Same author

Prediction model for daily feed intake during the growing period in floor-reared Wanxi White Geese based on machine learning and feeding behavior features.

Poultry science·2026

Related Experiment Video

Updated: May 14, 2025

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K

Two-Stream Bidirectional Interaction Network Based on RGB-D Images for Duck Weight Estimation.

Diqi Zhu1, Shan Bian1,2, Xiaofeng Xie1

  • 1College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China.

Animals : an Open Access Journal From MDPI
|April 12, 2025
PubMed
Summary

This study introduces an automated, non-contact method for measuring duck weight using RGB-D images. The novel approach accurately estimates duck weight, promoting animal welfare and efficient livestock management.

Keywords:
RGB-D datasetcross-modalityduck weight estimation

More Related Videos

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

6.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K

Related Experiment Videos

Last Updated: May 14, 2025

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

6.8K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K

Area of Science:

  • Agricultural Engineering
  • Computer Vision
  • Animal Science

Background:

  • Traditional methods for measuring duck weight can induce stress, negatively impacting animal health and development.
  • Accurate, non-invasive weight monitoring is crucial for precision livestock management and welfare.

Purpose of the Study:

  • To develop an automated, non-contact method for accurate duck weight estimation using RGB-D imagery.
  • To reduce stress in ducks by eliminating manual handling during weight measurement.
  • To support data-driven decisions in precision feeding and health management for ducks.

Main Methods:

  • A two-stream bidirectional interaction network utilizing RGB and depth (RGB-D) images was proposed.
  • The network employed separate encoder branches for texture and spatial information, with a cross-modality feature supplement module.
  • A decoder fused multi-scale features for final weight regression.

Main Results:

  • A new dataset of 2865 RGB-D duck images was created for evaluation.
  • The proposed method achieved a Mean Absolute Error (MAE) of 0.1550, outperforming existing methods.
  • Experimental results demonstrate the effectiveness and accuracy of the automated weight measurement.

Conclusions:

  • The developed automated, non-contact method accurately estimates duck weight, minimizing stress and enhancing animal welfare.
  • This technology facilitates automated growth data collection, crucial for precision feeding and health management.
  • The method promotes a digital transformation in the livestock industry, improving efficiency and sustainability.