Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 23, 2025

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Published on: June 5, 2019

A Spatiotemporal Convolutional Network for Multi-Behavior Recognition of Pigs.

Dan Li¹, Kaifeng Zhang¹, Zhenbo Li¹

¹College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China.

Sensors (Basel, Switzerland)

|April 26, 2020

Summary

This study introduces an automated pig behavior recognition network using spatiotemporal convolutional networks. The system accurately classifies pig behaviors, improving health monitoring efficiency.

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

Multidentate Triazole Coordination Unlocks Color-Tunable Plasmonic Gold Nanoparticle Films to Achieve High Catalytic Performance.

Small methods·2026

Same author

Real-world serplulimab plus chemotherapy for extensive-stage small cell lung cancer in china: an external validation of ASTRUM-005 trial.

BMC medicine·2026

Same author

Normal reference values and determinants of right heart strain derived from speckle tracking echocardiography: a systematic review and meta-analysis.

Quantitative imaging in medicine and surgery·2026

Same author

High Dynamic Range 120 dB Ga<sub>2</sub>O<sub>3</sub>-In<sub>2</sub>Se<sub>3</sub> Photodetector Array by Ferroelectric Polarization Enhancement.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Cardiovascular Health Change Patterns After Multifaceted Antihypertensive Intervention and Cardiovascular Outcomes: A Post Hoc Analysis of CRHCP Trial.

Journal of the American College of Cardiology·2026

Same author

Multimodal Feature Prototype Learning for Interpretable and Discriminative Cancer Survival Prediction.

IEEE journal of biomedical and health informatics·2026

Area of Science:

Animal Science
Computer Vision
Machine Learning

Background:

Traditional pig behavior analysis relies on manual video observation, which is labor-intensive and time-consuming.
Accurate statistical data on pig behaviors is crucial for reflecting their health status.
There is a need for automated systems to efficiently monitor and classify pig behaviors.

Purpose of the Study:

To develop an automated pig behavior recognition network for efficient classification.
To reduce the labor and time involved in traditional pig behavior analysis.
To enable simultaneous pig detection and behavior recognition.

Main Methods:

A pig behavior recognition video dataset (PBVD-5) was created, comprising five behavior categories: feeding, lying, motoring, scratching, and mounting.

Keywords:

behavior recognition deep learning pig pig video dataset spatiotemporal convolutional network

More Related Videos

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Noninvasive EEG Recordings from Freely Moving Piglets

Noninvasive EEG Recordings from Freely Moving Piglets

Published on: July 13, 2018

Related Experiment Videos

Last Updated: Dec 23, 2025

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Published on: June 5, 2019

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Noninvasive EEG Recordings from Freely Moving Piglets

Noninvasive EEG Recordings from Freely Moving Piglets

Published on: July 13, 2018

A spatiotemporal convolutional network based on the SlowFast architecture, termed PMB-SCN, was proposed for multi-behavior recognition.

The proposed network's optimal architecture was compared against a state-of-the-art single-stream 3D convolutional network.

Main Results:

The 3D pig behavior recognition network achieved a top-1 accuracy of 97.63% and a views accuracy of 96.35% on the PBVD test set.
The network demonstrated strong generalization ability, achieving 91.87% top-1 accuracy and 84.47% views accuracy on a new test set from a different pigsty.
The proposed network shows significant potential for real-time pig detection and behavior recognition.

Conclusions:

The developed SlowFast-based spatiotemporal convolutional network effectively automates pig behavior classification.
The network exhibits excellent accuracy and generalization capabilities, outperforming existing methods.
This automated approach offers a viable solution for improving pig health monitoring and welfare assessment.