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

A Review on Recent Deep Learning-Based Semantic Segmentation for Urban Greenness Measurement.

Sensors (Basel, Switzerland)·2024
Same author

Open set classification of sound event.

Scientific reports·2024
Same author

Transformer-Based Weed Segmentation for Grass Management.

Sensors (Basel, Switzerland)·2023
Same author

Detection of unknown strawberry diseases based on OpenMatch and two-head network for continual learning.

Frontiers in plant science·2022
Same author

Deep Metric Learning-Based Strawberry Disease Detection With Unknowns.

Frontiers in plant science·2022
Same author

An Instance Segmentation Model for Strawberry Diseases Based on Mask R-CNN.

Sensors (Basel, Switzerland)·2021

Related Experiment Video

Updated: Jun 25, 2025

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

9.3K

Transforming Poultry Farming: A Pyramid Vision Transformer Approach for Accurate Chicken Counting in Smart Farm

Ridip Khanal1,2, Yoochan Choi1, Joonwhoan Lee1

  • 1Division of Computer Science and Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea.

Sensors (Basel, Switzerland)
|May 25, 2024
PubMed
Summary

This study introduces an AI-powered transformer model for accurate automated chicken counting in smart farms. The advanced computer vision approach overcomes common challenges, improving livestock management efficiency.

Keywords:
augmentation strategychallenges in countingchicken countingpoultry farmingpyramid vision transformersmart farm environment

More Related Videos

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

14.1K
Low-Cost Automated Flight Intercept Trap for the Temporal Sub-Sampling of Flying Insects Attracted to Artificial Light at Night
06:19

Low-Cost Automated Flight Intercept Trap for the Temporal Sub-Sampling of Flying Insects Attracted to Artificial Light at Night

Published on: December 29, 2021

2.6K

Related Experiment Videos

Last Updated: Jun 25, 2025

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

9.3K
Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

14.1K
Low-Cost Automated Flight Intercept Trap for the Temporal Sub-Sampling of Flying Insects Attracted to Artificial Light at Night
06:19

Low-Cost Automated Flight Intercept Trap for the Temporal Sub-Sampling of Flying Insects Attracted to Artificial Light at Night

Published on: December 29, 2021

2.6K

Area of Science:

  • Agricultural Technology
  • Computer Vision
  • Artificial Intelligence

Background:

  • Efficient poultry management in smart farms requires accurate livestock monitoring.
  • Automated chicken counting is crucial for optimizing conditions and resource allocation.
  • Existing methods face challenges with variable lighting, occlusions, and background clutter.

Purpose of the Study:

  • To develop and evaluate a robust transformer-based model for automated chicken counting.
  • To address limitations in precise counting due to environmental and biological factors.
  • To enhance the accuracy and reliability of chicken population monitoring in smart farming.

Main Methods:

  • Integration of a pyramid vision transformer backbone and multi-scale regression head.
  • Development of a customized loss function with curriculum learning for progressive model training.
  • Creation of an augmented dataset featuring diverse conditions (lighting, density, scale, occlusion).

Main Results:

  • The transformer model achieved high accuracy with a test average accuracy of 96.9%.
  • Demonstrated robustness against various counting challenges, including lighting changes and occlusions.
  • Outperformed the SAFECount model by 7.7% in accuracy, showing superior resilience.

Conclusions:

  • The proposed transformer-based model offers a comprehensive and effective solution for automated chicken counting.
  • This technology significantly improves livestock management in smart farm environments.
  • The model's robustness and accuracy provide a reliable tool for poultry population assessment.