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

Intrinsic capacity and the trajectory of ischemic heart disease and its complications: the mediating role of insulin resistance indices.

Maturitas·2026
Same author

Timing and regimen of antiretroviral therapy and all-cause mortality in people with HIV: A time-to-event mediation analysis via opportunistic infection.

International journal of antimicrobial agents·2026
Same author

Neutrophil membrane-mediated biomimetic nanoparticle for co-delivery of icariin and siORMDL3 attenuates asthma exacerbated by respiratory syncytial virus.

Journal of nanobiotechnology·2026
Same author

Whole β-glucan particles modulate BCG-induced macrophage and CD4<sup>+</sup> T-cell responses via the Dectin-1-JAK1/STAT1 pathway.

Communications biology·2026
Same author

Remodeling the pathological airway: advanced nanotechnology for diagnostics and therapeutics in cystic fibrosis.

Journal of nanobiotechnology·2026
Same author

Rational design of low-risk and high-efficiency β-triketone herbicide alternatives via integrative computational toxicology and NGBoost modeling.

Molecular diversity·2026

Related Experiment Video

Updated: Jul 9, 2025

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

8.5K

Pixel Self-Attention Guided Real-Time Instance Segmentation for Group Raised Pigs.

Zongwei Jia1, Zhichuan Wang1, Chenyu Zhao1

  • 1College of Information Science and Engineering, Shanxi Agricultural University, Jinzhong 030801, China.

Animals : an Open Access Journal From MDPI
|December 9, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a pixel self-attention (PSA) module to improve instance segmentation for pigs in farms. The PSA module enhances the YOLACT model, outperforming other attention mechanisms for accurate pig tracking and management.

Keywords:
attention mechanismchannel self-attentioninstance segmentationspatial self-attention

More Related Videos

Noninvasive EEG Recordings from Freely Moving Piglets
04:05

Noninvasive EEG Recordings from Freely Moving Piglets

Published on: July 13, 2018

7.3K
Subretinal Implantation of RPE on a Carrier in Minipigs: Guidelines for Preoperative Preparations, Surgical Techniques, and Postoperative Care
11:06

Subretinal Implantation of RPE on a Carrier in Minipigs: Guidelines for Preoperative Preparations, Surgical Techniques, and Postoperative Care

Published on: November 11, 2022

2.8K

Related Experiment Videos

Last Updated: Jul 9, 2025

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

8.5K
Noninvasive EEG Recordings from Freely Moving Piglets
04:05

Noninvasive EEG Recordings from Freely Moving Piglets

Published on: July 13, 2018

7.3K
Subretinal Implantation of RPE on a Carrier in Minipigs: Guidelines for Preoperative Preparations, Surgical Techniques, and Postoperative Care
11:06

Subretinal Implantation of RPE on a Carrier in Minipigs: Guidelines for Preoperative Preparations, Surgical Techniques, and Postoperative Care

Published on: November 11, 2022

2.8K

Area of Science:

  • Computer Vision
  • Agricultural Technology
  • Animal Science

Background:

  • Accurate instance segmentation of pigs is vital for modern farm management.
  • Challenges include pig adhesion, occlusion, and posture changes, complicating segmentation.
  • Existing models face limitations in feature fusion within the Feature Pyramid Network (FPN).

Purpose of the Study:

  • To develop an improved instance segmentation model for pigs in dynamic farming environments.
  • To propose and evaluate a novel pixel self-attention (PSA) module for the YOLACT model.
  • To enhance feature utilization and fusion in the FPN module.

Main Methods:

  • Collected video data from 45 pigs (20-105 days old) across eight pens.
  • Labeled 1917 images for training, validation, and testing.
  • Integrated a proposed pixel self-attention (PSA) module with joint channel and spatial attention into the YOLACT model's FPN.
  • Utilized ResNet50 and ResNet101 as backbone networks.
  • Compared PSA module performance against BAM, CBAM, and SCSE attention modules using metrics like AP and AR.

Main Results:

  • The PSA module consistently outperformed BAM, CBAM, and SCSE attention modules across different backbone networks.
  • With ResNet101, the PSA module achieved a 2.7% improvement in AP0.5-0.95 compared to no attention.
  • Visualizations confirmed the PSA module's effectiveness in capturing pig-specific features and improving YOLACT's segmentation mechanism.
  • The model demonstrated robust transfer performance on a top-down view dataset.

Conclusions:

  • The proposed PSA module significantly enhances instance segmentation accuracy for pigs in agricultural settings.
  • The PSA module offers a robust solution for addressing challenges like occlusion and posture variation in pig farming.
  • The YOLACT model integrated with the PSA module shows strong potential for practical application in precision agriculture and pig farm management.