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

Introduction to Learning

Introduction to Learning

Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...

You might also read

Related Articles

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

Sort by

Same author

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

Research (Washington, D.C.)·2025

Same author

Vibration Analysis and Vehicle Detection by MEMS Acceleration Sensors Embedded in PCC Pavement.

Sensors (Basel, Switzerland)·2025

Same author

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

Nature communications·2025

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

A Longitudinal Functional Magnetic Resonance Imaging Study of Working Memory in Patients Following a Transient Ischemic Attack: A Preliminary Study.

Neuroscience bulletin·2018

Same author

Micro-nanostructured δ-Bi<sub>2</sub>O<sub>3</sub> with surface oxygen vacancies as superior adsorbents for SeO<sub>x</sub><sup>2-</sup> ions.

Journal of hazardous materials·2018

Search research articles

Related Experiment Video

Updated: Jul 23, 2025

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

Automatic pavement texture recognition using lightweight few-shot learning.

Shuo Pan¹, Hai Yan¹, Zhuo Liu¹

¹Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, People's Republic of China.

Philosophical Transactions. Series A, Mathematical, Physical, and Engineering Sciences

|July 16, 2023

Summary

This summary is machine-generated.

This study introduces a few-shot learning model for pavement texture recognition, overcoming data scarcity. The Siamese network model achieves high accuracy, offering efficient solutions for road maintenance professionals.

Keywords:

Siamese network convolutional neural network deep learning one-dimensional convolution pavement detection

More Related Videos

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

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Related Experiment Videos

Last Updated: Jul 23, 2025

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

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

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

Area of Science:

Civil Engineering
Materials Science
Computer Science

Background:

Pavement texture significantly impacts road performance and safety.
Accurate pavement texture recognition is vital for effective road maintenance and hazard detection.
Limited datasets pose a challenge for traditional deep learning models in pavement texture analysis.

Purpose of the Study:

To develop a few-shot learning model for pavement texture recognition using limited data.
To address the data scarcity issue in pavement texture classification.
To create lightweight models suitable for engineering practice.

Main Methods:

Proposed a few-shot learning model based on the Siamese network.
Implemented global average pooling (GAP) and one-dimensional convolution for model optimization.
Conducted comparative experiments to evaluate model performance, storage, and training time.

Main Results:

Achieved 89.8% accuracy in a four-way five-shot pavement texture classification task.
Lightweight models significantly reduced storage volume (up to 94%) and training time (up to 99%).
A model with GAP achieved the highest accuracy (93.5%) while reducing storage by 83% and training time by 6%.

Conclusions:

Few-shot learning effectively addresses data scarcity in pavement texture recognition.
Optimized lightweight models offer practical solutions for real-world engineering applications.
The proposed Siamese network-based approach enhances pavement safety and maintenance efficiency.