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 Experiment Video

Updated: Nov 30, 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

13.0K

Markerless Rat Behavior Quantification With Cascade Neural Network.

Tianlei Jin1, Feng Duan1, Zhenyu Yang1

  • 1Department of Artificial Intelligence, Nankai University, Tianjin, China.

Frontiers in Neurorobotics
|November 16, 2020
PubMed
Summary

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

Population Pharmacokinetic Modeling Study of Glibenclamide in Chinese Healthy Volunteers.

European journal of drug metabolism and pharmacokinetics·2026
Same author

Correction to "Polycation-Carbon Nanohybrids with Superior Rough Hollow Morphology for the NIR-II Responsive Multimodal Therapy".

ACS applied materials & interfaces·2026
Same author

Nao Tan Qing exerts neuroprotection against traumatic brain injury via multi-targeted immunomodulation and neurorestoration.

Brain research bulletin·2026
Same author

A multimodal deep learning model predicting hyperprogressive disease for PD-1 blockade in advanced hepatocellular carcinoma.

NPJ digital medicine·2026
Same author

APOE ε4 Allele is Associated with Cognitive Impairment in Chinese Sporadic ALS: A Retrospective Cohort Study.

Biomedical and environmental sciences : BES·2026
Same author

Thecoperitoneal shunt placement for extensive spinal adhesive arachnoiditis or lumbosacral outlet obstruction with syringomyelia.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2026
This summary is machine-generated.

This study introduces novel deep learning models, the cascade convolution network (CCN) and cascade hourglass network (CHN), for precise rat landmark point estimation from video. The CCN with heatmap integral regression (HIR) achieved 75% accuracy, enabling accurate quantification of rat motion behavior.

Area of Science:

  • * Behavioral analysis
  • * Computer vision
  • * Neuroscience research

Background:

  • * Accurate quantification of rodent behavior is essential for preclinical research in medicine and neuroscience.
  • * Estimating key landmark points (eyes, joints) from video is a challenging but critical task for motion analysis.

Purpose of the Study:

  • * To develop and evaluate deep learning models for accurate rat landmark point estimation using image processing.
  • * To quantify rat motion behavior by precisely tracking joint movements.

Main Methods:

  • * Designed two deep learning architectures: Cascade Convolution Network (CCN) and Cascade Hourglass Network (CHN) for feature extraction.
  • * Employed three coordinate calculation methods: Fully Connected Regression (FCR), Heatmap Maximum Position (HMP), and Heatmap Integral Regression (HIR).
Keywords:
behavior quantificationcascade neural networkmarkerless observation methodrat joint motionrat landmark points estimation

More Related Videos

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents
09:13

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

Published on: May 3, 2012

14.7K
Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

361

Related Experiment Videos

Last Updated: Nov 30, 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

13.0K
A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents
09:13

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

Published on: May 3, 2012

14.7K
Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

361
  • * Utilized a high frame rate camera to capture rat motion on a specialized running apparatus.

    • Main Results:

    • * The CCN architecture combined with the HIR method yielded the highest estimation accuracy at 75%.
    • * Performance was rigorously evaluated using normalized criteria across various feature map sizes.
    • * The achieved accuracy is sufficient for detailed tracking and quantification of rat joint motion.

    Conclusions:

    • * The developed CCN-HIR model offers a robust solution for precise rat landmark point estimation.
    • * This advancement significantly improves the ability to quantify rat behavior for research applications.
    • * The findings support the use of advanced computer vision techniques in preclinical studies.