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: May 28, 2026

Advanced Self-Healing Asphalt Reinforced by Graphene Structures: An Atomistic Insight

Advanced Self-Healing Asphalt Reinforced by Graphene Structures: An Atomistic Insight

Published on: May 31, 2022

DSMUNet: A Lightweight Model for Road Crack Segmentation.

Yunqing Liu¹, Xu Du¹, Chunting Zuo²

¹School of Electronic Information and Engineering, Changchun University of Science of Technology, Changchun 130118, China.

Sensors (Basel, Switzerland)

|May 27, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Microcracking in Concrete

Microcracking in Concrete

Microcracking in concrete refers to the tiny cracks that can form within the material even before any external load is applied. These microcracks typically occur at the interface between the coarse aggregate and the hydrated cement paste, often as a result of differential volume changes prompted by variations in stress-strain behavior, as well as thermal and moisture movement. Initially, these microcracks remain stable and do not grow substantially until the concrete is stressed to about 30...

You might also read

Related Articles

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

Sort by

Same author

Sulfur vacancy-mediated selective S-O bond scission dictates dominant singlet oxygen evolution in PMS activation.

Environmental research·2026

Same author

Complementary Thiourethane-Boronate Chemistry for the Covalent Integration of Hyaluronic Acid into Dynamic Polyurethane Networks.

Biomacromolecules·2026

Same author

A cognitive synergetic hierarchical framework for UAV swarm combat via speculative inference and role-decoupled reinforcement learning.

Frontiers in neurorobotics·2026

Same author

P2X7 receptor: An emerging therapeutic target in acute myeloid leukemia (Review).

International journal of oncology·2026

Same author

Research progress in augmentation strategies for PD-1/PD-L1 inhibitors in bladder cancer: from biological determinants to clinical applications.

Frontiers in immunology·2026

Same author

Genetic Susceptibility and Inflammatory Mechanisms in Bortezomib-Induced Peripheral Neuropathy: Insights From Whole Exome Sequencing and Transcriptomic Analysis.

Journal of applied toxicology : JAT·2026

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

This study introduces DSMUNet, a lightweight pavement crack segmentation model. It efficiently identifies road cracks with high accuracy, even in challenging conditions, making it ideal for resource-limited environments.

Area of Science:

Civil Engineering
Computer Vision
Artificial Intelligence

Background:

Pavement cracks are a common road hazard requiring precise segmentation for maintenance.
Existing segmentation methods struggle with environmental interference, diverse crack morphologies, and computational efficiency.

Purpose of the Study:

To propose DSMUNet, a lightweight deep learning model for efficient and accurate pavement crack segmentation.
To address the limitations of current methods in handling complex interference and multi-morphology cracks with low computational cost.

Main Methods:

Utilized a U-shaped encoder-decoder architecture with depthwise separable convolutions to reduce computational load.
Incorporated the SGE spatial group enhancement mechanism to highlight crack features and minimize non-crack texture interference.

Keywords:

deep learning image segmentation lightweight model road maintenance

Related Experiment Videos

Last Updated: May 28, 2026

Advanced Self-Healing Asphalt Reinforced by Graphene Structures: An Atomistic Insight

Advanced Self-Healing Asphalt Reinforced by Graphene Structures: An Atomistic Insight

Published on: May 31, 2022

Developed a novel multi-scale feature fusion module to enhance crack connectivity and overall segmentation performance.

Main Results:

DSMUNet achieved high segmentation accuracy with Dice/mIoU scores of 78.10%/69.05% on a private dataset and 87.12%/79.57% on the Crack500 dataset.
The model is computationally efficient, featuring only 0.55 M parameters and 21.708 GFLOPs, with an average inference latency of 5.42 ms.
Demonstrated superior performance in balancing resource consumption and segmentation accuracy.

Conclusions:

DSMUNet offers an efficient and effective solution for pavement crack segmentation, particularly in resource-constrained settings.
The proposed model provides a practical implementation scheme for road maintenance decision-making support.