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

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

StaticPigDetv2: Performance Improvement of Unseen Pig Monitoring Environment Using Depth-Based Background and Facility Information.

Sensors (Basel, Switzerland)·2026

Same author

Sustainable Self-Training Pig Detection System with Augmented Single Labeled Target Data for Solving Domain Shift Problem.

Sensors (Basel, Switzerland)·2025

Same author

Novel Method for Detecting Coughing Pigs with Audio-Visual Multimodality for Smart Agriculture Monitoring.

Sensors (Basel, Switzerland)·2024

Same author

Pattern Mining-Based Pig Behavior Analysis for Health and Welfare Monitoring.

Sensors (Basel, Switzerland)·2024

Same author

Automated Region of Interest-Based Data Augmentation for Fallen Person Detection in Off-Road Autonomous Agricultural Vehicles.

Sensors (Basel, Switzerland)·2024

Same author

StaticPigDet: Accuracy Improvement of Static Camera-Based Pig Monitoring Using Background and Facility Information.

Sensors (Basel, Switzerland)·2022

Search research articles

Related Experiment Video

Updated: Aug 5, 2025

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software

Published on: August 31, 2018

Behavior-Based Video Summarization System for Dog Health and Welfare Monitoring.

Othmane Atif¹, Jonguk Lee², Daihee Park²

¹Department of Computer and Information Science, Korea University, Sejong City 30019, Republic of Korea.

Sensors (Basel, Switzerland)

|March 30, 2023

Summary

This study introduces a novel video analysis system to monitor dog behavior, aiding owners in assessing pet health and welfare non-invasively. The system accurately recognizes behaviors, offering real-time insights and reducing veterinary costs.

Keywords:

computer vision dog behavior recognition dog health and welfare video monitoring system video summarization visualization

More Related Videos

Automated Interactive Video Playback for Studies of Animal Communication

Automated Interactive Video Playback for Studies of Animal Communication

Published on: February 9, 2011

Behavioral Disturbances: An Innovative Approach to Monitor the Modulatory Effects of a Nutraceutical Diet

Behavioral Disturbances: An Innovative Approach to Monitor the Modulatory Effects of a Nutraceutical Diet

Published on: January 3, 2017

Related Experiment Videos

Last Updated: Aug 5, 2025

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software

A Novel Single Animal Motor Function Tracking System Using Simple, Readily Available Software

Published on: August 31, 2018

Automated Interactive Video Playback for Studies of Animal Communication

Automated Interactive Video Playback for Studies of Animal Communication

Published on: February 9, 2011

Behavioral Disturbances: An Innovative Approach to Monitor the Modulatory Effects of a Nutraceutical Diet

Behavioral Disturbances: An Innovative Approach to Monitor the Modulatory Effects of a Nutraceutical Diet

Published on: January 3, 2017

Area of Science:

Veterinary Medicine
Computer Science
Animal Behavior

Background:

Growing popularity of dog ownership is linked to health benefits, but assessing canine welfare can be challenging and costly.
Owners face difficulties in monitoring their dogs' health and welfare, with frequent veterinary visits posing a financial strain.

Purpose of the Study:

To develop and evaluate a behavior-based video summarization and visualization system for monitoring dog health and welfare.
To provide owners with an accessible tool for understanding their dog's behavioral patterns and overall well-being.

Main Methods:

A four-module system was developed: video data collection/preprocessing, object detection for dog isolation, behavior recognition using EfficientNetV2 and Long Short-Term Memory (LSTM), and video summarization/visualization.
The behavior recognition module employed two-stream EfficientNetV2 for appearance and motion feature extraction, combined with LSTM for sequence analysis.
Object detection focused on isolating the dog to minimize background noise and improve recognition accuracy.

Main Results:

The system achieved a high average F1 score of 0.955 for dog behavior recognition.
The behavior recognition process was computationally efficient, allowing for real-time processing.
Visual summaries effectively presented the dog's location and behavioral data, aiding owner comprehension.

Conclusions:

The proposed system offers a viable solution for owners to monitor and understand their dog's health and welfare through behavior analysis.
The system's accuracy and real-time capabilities demonstrate its potential to reduce the financial burden of frequent veterinary checkups.
Behavior-based video analysis can be a powerful tool for enhancing canine care and owner-pet relationships.