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

Visual System

Visual System

Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...

You might also read

Related Articles

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

Sort by

Same author

Data Resource Profile: A Protocol of China National Diabetic Chronic Complications Study.

Biomedical and environmental sciences : BES·2022

Same author

Tuberculosis relapse is more common than reinfection in Beijing, China.

Infectious diseases (London, England)·2020

Same author

High-flow nasal cannula therapy for children with bronchiolitis: a systematic review and meta-analysis.

Archives of disease in childhood·2019

Same author

Markov Clustering Analysis-Based Validation for Traditional Chinese Medicine Syndrome Patterns of Poststroke Cognitive Impairment.

Journal of alternative and complementary medicine (New York, N.Y.)·2019

Same author

Correction to: High-performance gene expression and knockout tools using sleeping beauty transposon system.

Mobile DNA·2019

Same author

Herbal medicine in the treatment of patients with type 2 diabetes mellitus.

Chinese medical journal·2019

Search research articles

Related Experiment Video

Updated: Jan 4, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Embedded system for road damage detection by deep convolutional neural network.

Si Yu Chen¹, Yin Zhang¹, Yu Hang Zhang²

¹Department of Electronic and Computer Engineering, Southeast University Chengxian College, Nanjing 210088, China.

Mathematical Biosciences and Engineering : MBE

|November 9, 2019

Summary

This summary is machine-generated.

This study presents a low-cost system for detecting road damage using a deep convolutional neural network and common cameras. The developed embedded system achieves a 76% recall rate, offering a cost-effective solution for road maintenance.

Keywords:

convolutional neural network deep learning embedded system object detection road damage detection road survey

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: Jan 4, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

Road infrastructure monitoring
Computer vision for transportation

Background:

Road pavement damage, including cracks and pits, poses significant traffic safety risks.
Current detection methods using specialized vehicles like laser scanners are effective but prohibitively expensive.

Purpose of the Study:

To develop a cost-effective road damage detection system.
To leverage deep learning and common vehicle sensors for pavement assessment.

Main Methods:

Training an object detection model based on deep convolutional neural networks (CNNs) using a road damage image dataset.
Deploying the trained model on a low-cost embedded platform integrated with a common vehicle camera.

Main Results:

The embedded system processes images at approximately 352 ms per frame.
Achieved a recall rate of about 76% for road damage detection.
Demonstrated significantly lower economic cost compared to specialized detection vehicles.

Conclusions:

The proposed system offers a viable, economical alternative for road damage detection, particularly for maintenance departments with limited funding.
While recall rates are lower than high-end detectors, the cost-benefit analysis favors this approach for broader implementation.
Further development can enhance the system's performance for practical road maintenance applications.