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

Crop Pest Identification and Real-Time Monitoring System Design Based on Improved YOLOv8s.

Sensors (Basel, Switzerland)·2026
Same author

A Real-Time Lightweight Behavior Recognition Model for Multiple Dairy Goats.

Animals : an open access journal from MDPI·2025
Same author

Be-1DCNN: a neural network model for chromatin loop prediction based on bagging ensemble learning.

Briefings in functional genomics·2023
Same author

SheepInst: A High-Performance Instance Segmentation of Sheep Images Based on Deep Learning.

Animals : an open access journal from MDPI·2023
Same author

SCMcluster: a high-precision cell clustering algorithm integrating marker gene set with single-cell RNA sequencing data.

Briefings in functional genomics·2023
Same author

Immediate splenectomy down-regulates the MAPK-NF-κB signaling pathway in rat brain after severe traumatic brain injury.

The journal of trauma and acute care surgery·2013

Related Experiment Video

Updated: Jun 26, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

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

Published on: August 16, 2024

419

An Integrated Gather-and-Distribute Mechanism and Attention-Enhanced Deformable Convolution Model for Pig Behavior

Rui Mao1,2, Dongzhen Shen1, Ruiqi Wang1

  • 1College of Information Engineering, Northwest A&F University, Yangling 712100, China.

Animals : an Open Access Journal From MDPI
|May 11, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces DM-GD-YOLO, an advanced AI model for pig behavior recognition. It accurately identifies both normal and abnormal pig behaviors, supporting improved animal welfare and farm management.

Keywords:
DM-GD-YOLObehavior recognitiongather-and-distribute mechanismmulti-path coordinate attentionpig

More Related Videos

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

12.5K
Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
06:30

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

Published on: June 5, 2019

8.4K

Related Experiment Videos

Last Updated: Jun 26, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

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

Published on: August 16, 2024

419
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

12.5K
Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
06:30

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

Published on: June 5, 2019

8.4K

Area of Science:

  • Animal Science
  • Computer Vision
  • Machine Learning

Background:

  • Accurate recognition of pig behavior is crucial for health monitoring and management.
  • Non-rigid deformations in pig behavior pose challenges for traditional computer vision models.
  • Existing models often struggle with comprehensive feature extraction for complex animal behaviors.

Purpose of the Study:

  • To develop an advanced model for recognizing both common and abnormal pig behaviors.
  • To enhance feature extraction capabilities for non-rigid deformations in pig behavior analysis.
  • To improve pig health monitoring and welfare-focused breeding through intelligent management.

Main Methods:

  • Utilized deformable convolutional networks (DCN) with a multi-path coordinate attention (MPCA) mechanism for enhanced feature extraction (DCN-MPCA module).
  • Integrated the DCN-MPCA module into the cross-scale cross-feature (C2f) module of the backbone network.
  • Employed a gather-and-distribute (GD) mechanism in the neck of the YOLOv8 network for improved feature fusion, creating the DM-GD-YOLO model.

Main Results:

  • The DM-GD-YOLO model achieved high performance on a dataset of 11,999 pig images, recognizing four common and three abnormal behaviors.
  • Achieved a precision of 88.2%, recall of 92.2%, and mean average precision (mAP) of 95.3%.
  • Outperformed popular models like Faster R-CNN, EfficientDet, YOLOv7, and YOLOv8 in pig pen monitoring.

Conclusions:

  • The novel DM-GD-YOLO model offers significant improvements in pig behavior recognition accuracy and efficiency.
  • Provides robust technical support for intelligent pig management, enhancing animal welfare and breeding practices.
  • Contributes to the modernization and transformation of the pig industry through advanced AI solutions.