Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Lumber Defects01:23

Lumber Defects

217
Lumber defects, which can affect both the appearance and structural integrity of wood, include a variety of growth and manufacturing flaws. Growth defects such as knots and knotholes occur where branches were once attached to the tree trunk, with knotholes forming when these knots fall out. Other natural defects include decay and insect damage, which compromise the wood's strength and durability.
Shakes are minor fractures that run along or across the wood's annual rings, while wane is...
217
Detection of Black Holes01:10

Detection of Black Holes

2.3K
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
2.3K
Non-destructive Tests for Concrete Strength01:12

Non-destructive Tests for Concrete Strength

193
The rebound hammer test, also known as the Schmidt hammer test, is a non-destructive technique for evaluating the hardness of concrete and, indirectly, the strength of concrete. It operates on the principle that the rebound of a spring-driven mass from a concrete surface correlates to the surface's hardness. The device comprises a mass within a tubular housing, a spring mechanism, and a plunger that strikes the concrete. Upon release, the energy imparted to the mass by the spring causes it...
193
Structural Classification of Joints01:20

Structural Classification of Joints

4.1K
Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...
4.1K
Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

6.4K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
6.4K
Steel Manufacturing01:26

Steel Manufacturing

790
Steel manufacturing is a multi-stage process that begins by smelting iron ore into cast iron in a blast furnace. This initial stage involves layering iron ore with coke, a type of fuel, and crushed limestone within the furnace. The coke is ignited with a high volume of air, leading to the creation of carbon monoxide, which acts to reduce the iron ore to pure iron.
During this smelting process, limestone plays a crucial role by forming slag. Slag captures impurities within the molten iron, such...
790

You might also read

Related Articles

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

Sort by
Same author

Hydrogel-Woven COF Membranes With Orthogonal, Opposite Thermoresponsive Nanochannels: Overcoming the Permeance-Selectivity Trade-off.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Efficient CuO coating on assembled Cu<sub>2</sub>V<sub>2</sub>O<sub>7</sub>nanoflakes for better lithium storage performance.

Nanotechnology·2026
Same author

Progress and Challenges in Joining for Precision Endoscope Fabrication.

Sensors (Basel, Switzerland)·2026
Same author

Design of CoNiCrFeCu-xSc High-Entropy Alloy Fillers for Braze-Welding of WC-Co to Steel.

Materials (Basel, Switzerland)·2026
Same author

Parametric study of a new pressure relief borehole layout for high-stress roadway rockburst prevention.

Scientific reports·2026
Same author

Dual-Phase Design Enables High Capacitive Energy-Storage Capacity Under Moderate Electric Fields in Relaxor Ferroelectric Ceramics.

Small (Weinheim an der Bergstrasse, Germany)·2026

Related Experiment Video

Updated: Sep 11, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.2K

Detection of Surface Defects in Steel Based on Dual-Backbone Network: MBDNet-Attention-YOLO.

Xinyu Wang1, Shuhui Ma2, Shiting Wu1

  • 1School of Materials Science and Engineering, Shanghai University of Engineering Science, Shanghai 201620, China.

Sensors (Basel, Switzerland)
|August 14, 2025
PubMed
Summary

This study introduces MBY (MBDNet-Attention-YOLO), a novel framework for automated steel surface defect detection. MBY achieves high accuracy and real-time performance, addressing limitations of existing methods for diverse defect types and complex surfaces.

Keywords:
Inner-SIoUMBDNetMultiSEAMYOLOdynamic align fusionsteel surface defect detection

More Related Videos

Applicability Analysis of Assessment Methods for Morphological Parameters of Corroded Steel Bars
10:24

Applicability Analysis of Assessment Methods for Morphological Parameters of Corroded Steel Bars

Published on: November 1, 2018

6.8K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

635

Related Experiment Videos

Last Updated: Sep 11, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.2K
Applicability Analysis of Assessment Methods for Morphological Parameters of Corroded Steel Bars
10:24

Applicability Analysis of Assessment Methods for Morphological Parameters of Corroded Steel Bars

Published on: November 1, 2018

6.8K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

635

Area of Science:

  • Materials Science
  • Computer Vision
  • Manufacturing Engineering

Background:

  • Automated surface defect detection in steel manufacturing is crucial for quality control but challenged by diverse defect morphologies and complex backgrounds.
  • Existing methods, including classical vision and deep learning, struggle with accuracy, robustness to scale variation, and real-time processing on constrained hardware.

Purpose of the Study:

  • To develop a lightweight and accurate framework for automated steel surface defect detection that overcomes the limitations of current approaches.
  • To improve detection accuracy for sub-millimeter flaws, enhance robustness against textured backgrounds and scale-varying defects, and achieve real-time throughput.

Main Methods:

  • Introduced MBY (MBDNet-Attention-YOLO), a framework combining a novel MBDNet backbone with a YOLO detection head.
  • The MBDNet backbone features HGStem for enriched representations, Dynamic Align Fusion (DAF) for adaptive cross-scale feature fusion, and C2f-DWR for expanded receptive fields.
  • A MultiSEAM module enhances feature representation, and Inner-SIoU loss improves bounding box localization accuracy.

Main Results:

  • MBY achieved 85.8% mAP@0.5 on the NEU-DET benchmark and 75.9% mAP@0.5 on the PVEL-AD benchmark, outperforming existing state-of-the-art methods.
  • The model demonstrated real-time inference capabilities on an NVIDIA Jetson Xavier, suitable for resource-constrained industrial environments.
  • Ablation studies confirmed the effectiveness of individual components and the overall robustness of MBY across different defect scales and surface conditions.

Conclusions:

  • MBY offers a significant advancement in automated steel surface defect detection, balancing high accuracy, efficiency, and deployability.
  • The proposed framework provides a pragmatic solution for next-generation industrial quality control systems, capable of handling complex defect scenarios.
  • MBY's novel components and architecture contribute to superior performance and robustness, making it a valuable tool for steel manufacturing.