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

Search research articles

Related Experiment Video

Updated: Jan 10, 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

Structure-Aware Progressive Multi-Modal Fusion Network for RGB-T Crack Segmentation.

Zhengrong Yuan¹, Xin Ding², Xinhong Xia¹

¹Hunan Architectural Design Institute Group Co., Ltd., Changsha 410208, China.

Journal of Imaging

|November 26, 2025

Summary

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

Design and Control of a 1-DOF MRI Compatible Pneumatically Actuated Robot with Long Transmission Lines.

IEEE/ASME transactions on mechatronics : a joint publication of the IEEE Industrial Electronics Society and the ASME Dynamic Systems and Control Division·2011

Same author

Effect of oxidized low-density lipoprotein concentration polarization on human smooth muscle cells' proliferation, cycle, apoptosis and oxidized low-density lipoprotein uptake.

Journal of the Royal Society, Interface·2011

Same author

Acrolein hydrogenation on Pt(211) and Au(211) surfaces: a density functional theory study.

Physical chemistry chemical physics : PCCP·2011

Same author

Anhydrous proton-conducting membrane based on poly-2-vinylpyridinium dihydrogenphosphate for electrochemical applications.

The journal of physical chemistry. B·2011

Same author

Pharmacophore identification, virtual screening and biological evaluation of prenylated flavonoids derivatives as PKB/Akt1 inhibitors.

European journal of medicinal chemistry·2011

Same author

Metabolomic study of insomnia and intervention effects of Suanzaoren decoction using ultra-performance liquid-chromatography/electrospray-ionization synapt high-definition mass spectrometry.

Journal of pharmaceutical and biomedical analysis·2011

This study introduces a new network for crack segmentation using both RGB and thermal images. The method improves accuracy by fusing multi-modal data and incorporating structural edge information for better structural integrity monitoring.

Area of Science:

Computer Vision
Structural Health Monitoring
Artificial Intelligence

Background:

Crack segmentation is crucial for structural integrity assessment.
Existing RGB-based methods are limited by lighting conditions.
Multi-modal approaches can overcome these limitations.

Purpose of the Study:

To develop a robust crack segmentation method using RGB-thermal (RGB-T) data.
To enhance segmentation accuracy by fusing complementary information from different modalities.
To incorporate structural priors for improved crack region integrity.

Main Methods:

Proposed a structure-aware progressive multi-modal fusion network (SPMFNet).
Utilized gate control attention (GCA) and attention feature fusion (AFF) modules for progressive fusion.

Keywords:

crack segmentation deep learning feature fusion gate control attention

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Jan 10, 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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Integrated edge prior information with a joint loss function (edge-guided, multi-scale focal, adaptive fusion loss).

Main Results:

SPMFNet demonstrated superior performance compared to existing methods on RGB-T crack detection datasets.
The progressive fusion strategy effectively integrates multi-modal features.
Incorporating structural priors improved the integrity of segmented crack regions.

Conclusions:

The proposed SPMFNet effectively segments cracks in RGB-T images.
Progressive multi-modal fusion and structural priors are key to accurate and robust crack segmentation.
This method offers a promising solution for structural health monitoring in complex environments.