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

Assessment of Diffusion and Perfusion

Assessment of Diffusion and Perfusion

Understanding and evaluating diffusion and perfusion is critical in assessing a patient's respiratory and circulatory health. These processes play key roles in maintaining the body's internal environment, ensuring that tissues receive adequate oxygen while waste products are efficiently removed.
The Role of Diffusion in Respiration
Diffusion is the process by which molecules move from an area of higher concentration to an area of lower concentration. In the respiratory system, this...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

TactiVis: Towards Better Understanding of Team-Based Combat Tactics.

IEEE transactions on visualization and computer graphics·2025

Same author

Lightweight deep learning for real-time road distress detection on mobile devices.

Nature communications·2025

Same author

Automatic pavement texture recognition using lightweight few-shot learning.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2023

Same author

Introduction to 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2023

Same author

Simultaneous Measurements of Refractive Index and Methane Concentration through Electromagnetic Fano Resonance Coupling in All-Dielectric Metasurface.

Sensors (Basel, Switzerland)·2021

Same author

Inguinal Subcutaneous White Adipose Tissue (ISWAT) Transplantation Model of Murine Islets.

Journal of visualized experiments : JoVE·2020

Search research articles

Related Experiment Video

Updated: May 1, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

RoadDiffBox: Automatic Road Distress Diagnosis through Controlled Image Generation and Semi-Supervised Learning.

Yuanyuan Hu¹, Ning Chen², Hancheng Zhang¹

¹Institute of Highway Engineering, RWTH Aachen University, Aachen, Germany.

Research (Washington, D.C.)

|August 27, 2025

Summary

This summary is machine-generated.

RoadDiffBox utilizes AI-powered image generation and semi-supervised learning to create diverse road distress images with automatic annotations. This framework significantly reduces manual labeling, enabling efficient road maintenance even with limited data.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Related Experiment Videos

Last Updated: May 1, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Area of Science:

Civil Engineering
Computer Science
Artificial Intelligence

Background:

Road infrastructure damage is inevitable due to repeated loading and environmental factors.
Traditional road distress inspection is costly and labor-intensive.
AI-based methods require large, high-quality datasets, limiting practical application.

Purpose of the Study:

Introduce RoadDiffBox, a novel framework for AI-based road distress detection.
Address dataset limitations through controlled image generation and semi-supervised learning.
Reduce manual labeling efforts for road distress identification.

Main Methods:

Employing a denoising diffusion implicit model for accelerated image generation.
Utilizing class control to address dataset imbalances.
Implementing knowledge distillation for resource-constrained devices.
Generating diverse, high-quality road distress images with automatic bounding box annotations.

Main Results:

RoadDiffBox demonstrates strong generalizability across different geographic regions (Germany, China, India).
Achieved high performance metrics: F1-score of 0.95 for classification, mAP@50 of 0.95 and F1-score of 0.91 for detection in controlled settings.
Maintained robust performance in real-world conditions (F1-score of 0.86, mAP@50 of 0.91).
Image generation time as low as 0.18 seconds per image on server-class hardware.

Conclusions:

RoadDiffBox offers a scalable and efficient solution for real-time road maintenance.
The framework effectively overcomes limitations of small or imbalanced datasets.
Shows potential for cross-domain applications, including medical imaging.