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

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

A lightweight crack segmentation network based on the importance-enhanced Mamba model.

Yunfeng Wang^1,2,3, Jie Jin^4,5,6, Xiong Chen⁷

¹Research Institute of Highway, Ministry of Transport, Beijing, 100088, China.

Scientific Reports

|November 25, 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

SRC3 expressed in BMSCs promotes growth and migration of multiple myeloma cells by regulating the expression of Cx43.

International journal of oncology·2017

Same author

A Review on Experimental Measurements for Understanding Efficiency Droop in InGaN-Based Light-Emitting Diodes.

Materials (Basel, Switzerland)·2017

Same author

Analysis of microbial community composition and diversity in postoperative intracranial infection using high‑throughput sequencing.

Molecular medicine reports·2017

Same author

Primary central nervous system lymphoma: Retrospective analysis of 34 cases in a single centre.

The Journal of international medical research·2017

Same author

Seasonal water chemistry variability in the Pangani River basin, Tanzania.

Environmental science and pollution research international·2017

Same author

Are prostate biopsies necessary for all patients 75years and older?

Journal of geriatric oncology·2017

This study introduces a lightweight crack segmentation network using an Importance-Enhanced Mamba model. It improves accuracy for infrastructure maintenance while reducing computational costs.

Area of Science:

Civil Engineering
Computer Vision
Artificial Intelligence

Background:

Crack segmentation is vital for transportation infrastructure maintenance, road safety, and service life extension.
Existing methods face challenges with complex backgrounds, intricate crack morphologies, and high computational costs.
There is a need for efficient and accurate crack segmentation models.

Purpose of the Study:

To propose a lightweight crack segmentation network.
To address limitations of existing methods in accuracy and computational cost.
To enhance the perception of global and local crack features.

Main Methods:

Developed a lightweight crack segmentation network based on the U-Net architecture.
Integrated a dual-branch design combining Convolutional Neural Networks (CNN) and Mamba modules.

Keywords:

Crack segmentation Dynamic scanning Importance-enhanced Mamba

More Related Videos

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

Related Experiment Videos

Last Updated: Jan 10, 2026

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

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

Introduced an importance-enhanced dynamic scanning module within the Mamba branch for adaptive path adjustment.

Utilized an attention-guided module for fusing CNN and Mamba features, enabling pixel-wise integration of local and global information.

Main Results:

The proposed Importance-Enhanced Mamba model achieved superior segmentation accuracy compared to advanced methods on public datasets (Crack500, CrackTree260, CrackForest).
Demonstrated significant reductions in model parameters and computational complexity.
Effectively captured both microstructural details and macroscopic relationships of cracks.

Conclusions:

The Importance-Enhanced Mamba network offers an efficient and accurate solution for crack segmentation in transportation infrastructure.
The dual-branch design synergistically extracts local and global features, overcoming limitations of previous approaches.
This model contributes to improved road safety and extended infrastructure service life through precise crack detection.