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

Altered hypothalamic functional connectivity in adolescents with severe obesity.

International journal of obesity (2005)·2026
Same author

Effect of Herbs and Spices on Acceptance, Preference, and Intake of Vegetables Among Rural Adolescents.

Nutrition reviews·2026
Same author

Understanding the Biocultural Factors Influencing Infant Dietary Diversity in Periurban Guinea: Findings from a Mixed-Methods Study.

Food and nutrition bulletin·2026
Same author

Food variety affects food selection and variety-seeking behaviors in an immersive virtual reality food buffet.

Appetite·2026
Same author

Sensory-specific satiety and the influence of variety on snack intake in school-aged children.

Appetite·2026
Same author

Style mixing houses: The role of high- and low-level visual features in human house facade evaluation.

Acta psychologica·2025

Related Experiment Video

Updated: Jan 14, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

ByteTrack: a deep learning approach for bite count and bite rate detection using meal videos in children.

Yashaswini Rajendra Bhat1, Kathleen L Keller1,2, Timothy R Brick3,4

  • 1Department of Nutritional Sciences, Pennsylvania State University, University Park, PA, United States.

Frontiers in Nutrition
|October 20, 2025
PubMed
Summary

ByteTrack, an automated system, accurately detects children's eating behaviors like bite count from videos. This technology offers a scalable solution for assessing overconsumption and obesity risks.

Keywords:
automationbite detectionchildhood obesitydietary assessmenteating behaviorsneural networks

More Related Videos

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method
06:21

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method

Published on: February 19, 2021

6.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K

Related Experiment Videos

Last Updated: Jan 14, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method
06:21

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method

Published on: February 19, 2021

6.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K

Area of Science:

  • Pediatric nutrition and behavior analysis.
  • Development of AI-driven health monitoring tools.
  • Obesity and overconsumption research.

Background:

  • Assessing eating behaviors, such as eating rate, is crucial for identifying risks of overconsumption and obesity.
  • Current methods for analyzing eating behaviors, like sensor use or manual video coding, have limitations in scalability and naturalness.

Purpose of the Study:

  • To develop and evaluate ByteTrack, a deep learning system for automated bite count and bite-rate detection in children's meals.
  • To provide a scalable and less disruptive method for analyzing eating behaviors compared to existing approaches.

Main Methods:

  • Developed ByteTrack, a two-stage deep learning system utilizing Faster R-CNN, YOLOv7, EfficientNet, and LSTM for face detection and bite classification.
  • Trained and tested the model on 1,440 minutes of video data from 94 children (ages 7-9) across multiple meals.
  • Designed the model to be robust against common video challenges like blur, low light, camera shake, and occlusions.

Main Results:

  • ByteTrack achieved an average precision of 79.4%, recall of 67.9%, and F1 score of 70.6% on a test set of 51 videos.
  • Intraclass correlation coefficient indicated an average agreement of 0.66 with manual coding, though reliability varied with movement and occlusions.

Conclusions:

  • This pilot study confirms the feasibility of ByteTrack as a scalable, automated tool for detecting bites in children's meals.
  • Future research will aim to enhance model robustness for diverse populations and challenging recording conditions.