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

Genome-wide modelling of plant transcription factor binding captures regulatory variants associated with phenotypic traits.

Nature communications·2026
Same author

Relationship Between Litter Weight Gain and Colostrum Fatty Acid Composition: Implications for Cross-Fostering?

Animals : an open access journal from MDPI·2026
Same author

Normalized cumulative gain as an alternative evaluation measure for genomic selection models.

Genetics, selection, evolution : GSE·2025
Same author

optRF: Optimising random forest stability by determining the optimal number of trees.

BMC bioinformatics·2025
Same author

Optimization of sparse phenotyping strategy in multi-environmental trials in maize.

TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik·2025
Same author

Computational Identification of Milk Trait Regulation Through Transcription Factor Cooperation in Murciano-Granadina Goats.

Biology·2024

Related Experiment Video

Updated: Oct 12, 2025

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
08:32

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

12.8K

Detecting Animal Contacts-A Deep Learning-Based Pig Detection and Tracking Approach for the Quantification of Social

Martin Wutke1,2, Felix Heinrich1, Pronaya Prosun Das3

  • 1Breeding Informatics Group, Department of Animal Sciences, Georg-August University, Margarethe von Wrangell-Weg 7, 37075 Göttingen, Germany.

Sensors (Basel, Switzerland)
|November 27, 2021
PubMed
Summary

This study introduces an automated system for identifying pig social interactions using AI. The framework accurately detects social contacts, improving animal behavior research efficiency and welfare.

Keywords:
Kalman filterconvolutional neural networkpig detectionpig trackingprecision livestock farming

More Related Videos

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior
06:59

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior

Published on: May 21, 2020

4.2K
Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

68

Related Experiment Videos

Last Updated: Oct 12, 2025

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
08:32

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

12.8K
A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior
06:59

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior

Published on: May 21, 2020

4.2K
Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

68

Area of Science:

  • Animal Behavior
  • Computer Vision
  • Machine Learning

Background:

  • Manual identification of social interactions in animal behavior studies is labor-intensive and costly.
  • Automated methods are needed to increase research efficiency and improve animal welfare.
  • Understanding social structures and behaviors is crucial for animal husbandry and welfare.

Purpose of the Study:

  • To develop and validate a framework for the automated identification of social contacts in pigs.
  • To overcome the limitations of manual observation in animal behavior research.
  • To enhance animal monitoring systems through technological advancements.

Main Methods:

  • Utilized a convolutional neural network (CNN) for detecting pig location and orientation in videos.
  • Employed a Kalman filter (KF) algorithm for tracking animal movement trajectories.
  • Developed a method to automatically identify head-head and head-tail contacts based on tracking data.
  • Constructed a social contact network using individual animal IDs.

Main Results:

  • Achieved high performance metrics for pig detection and tracking: Sensitivity (94.2%), Precision (95.4%), and F1-score (95.1%).
  • Demonstrated a Multi-Object Tracking Accuracy (MOTA) score of 94.4%.
  • Validated the effectiveness of the keypoint-based tracking-by-detection strategy.

Conclusions:

  • The proposed framework effectively automates the identification of social interactions in pigs.
  • This automated approach significantly enhances research efficiency and contributes to animal welfare.
  • The system has potential applications for improving comprehensive animal monitoring systems.