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

X-ray Imaging01:24

X-ray Imaging

German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with X-rays, and by 1900, X-ray was widely...
Lumber Defects01:23

Lumber Defects

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...
Imaging Biological Samples with Optical Microscopy01:18

Imaging Biological Samples with Optical Microscopy

Optical microscopy uses optic principles to provide detailed images of samples. Antonie van Leeuwenhoek designed the first compound optical microscope in the 17th century to visualize blood cells, bacteria, and yeast cells. In 1830, Joseph Jackson Lister created an essentially modern light microscope. The 20th century saw the development of microscopes with enhanced magnification and resolution.
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...
Detection of Black Holes01:10

Detection of Black Holes

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...

You might also read

Related Articles

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

Sort by
Same author

Immunometabolic reprogramming of macrophages by miR-423-5p-enriched small extracellular vesicles delivered via glucose/ROS-responsive hydrogel for diabetic wound healing.

Journal of nanobiotechnology·2026
Same author

X-Ray Weld Image Detection Method of Water Injection Network Based on Sparse Representation.

Sensors (Basel, Switzerland)·2026
Same author

Single-cell transcriptomic profiling reveals PDK4 upregulation and impaired VEGF-C/VEGFR3 signaling in cardiac lymphatic endothelial cells in diabetic cardiomyopathy.

Molecular medicine (Cambridge, Mass.)·2026
Same author

Nondestructive Detection of Foreign Matter in Pu-erh Ripe Tea Based on Deep Learning.

Foods (Basel, Switzerland)·2026
Same author

Streamlined Dual-Readout HPV-16 DNA Sensor Empowered by the Intrinsic Colorimetric and Electrochemiluminescent Activities of Nanocrystalline PCN-224.

Analytical chemistry·2026
Same author

PVN oxytocin - VTA neurocircuit modulate the emergence of general anesthesia induced by isoflurane in mice.

Brain research bulletin·2026

Related Experiment Videos

YOLO11-Based Weld Defect Detection Method for X-Ray Images Integrating SIoU Bounding Box Regression and P2 Shallow

Li Gao1,2, Hailong Liu1,2, Weixin Gao1,2

  • 1School of Electronic Engineering, Xi'an Shiyou University, Xi'an 710065, China.

Sensors (Basel, Switzerland)
|July 15, 2026
PubMed
Summary

This study introduces an improved YOLOv11 model for X-ray weld defect detection, enhancing accuracy for small welds and large defects. The method integrates Smooth IoU and P2 shallow feature enhancement for robust non-destructive testing.

Keywords:
X-ray weld imageYOLOv11defect detectionwater injection network

Related Experiment Videos

Area of Science:

  • Materials Science
  • Computer Vision
  • Non-Destructive Testing

Background:

  • X-ray inspection is vital for pipeline weld non-destructive testing (NDT).
  • Automatic defect detection faces challenges: low contrast, complex backgrounds, and varied defect morphology.
  • Existing methods struggle with precise localization of small weld regions and detection of diverse defects.

Purpose of the Study:

  • To develop an improved YOLOv11-based method for enhanced X-ray weld defect detection.
  • To boost localization accuracy for small-diameter pipe weld regions using Smooth IoU (SIoU).
  • To improve the detection of large defects in long-distance pipeline welds via P2 shallow feature enhancement.

Main Methods:

  • Implemented Smooth IoU (SIoU) loss to replace CIoU loss, incorporating an Angle Cost for directional bounding box constraints.
  • Integrated a P2 detection layer (stride 4) to preserve high-resolution spatial and shallow edge features lost in deep downsampling.
  • Evaluated the enhanced YOLOv11 model on X-ray weld images with varying defect types and sizes.

Main Results:

  • The YOLOv11s + SIoU model achieved 99.5% mAP@50 and 99.9% precision, significantly improving baseline performance.
  • The YOLOv11s + P2 model demonstrated 93.07% precision, 94.8% mAP@50, and 72.01% mAP@50-95 for large defect detection.
  • The combined approach offers robust solutions for both Region of Interest (ROI) localization and large defect recognition.

Conclusions:

  • The proposed method effectively combines directional constraints with shallow feature preservation for superior X-ray weld defect detection.
  • The enhanced YOLOv11 model provides a robust and accurate solution for challenging NDT applications in pipeline inspection.
  • This work advances automatic defect recognition in complex industrial imaging scenarios.