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: Dec 21, 2025

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

Robust seam tracking via a deep learning framework combining tracking and detection.

Yanbiao Zou, Rui Lan, Xianzhong Wei

|May 14, 2020

Summary

This summary is machine-generated.

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

An interpretable machine learning model for predicting myocardial injury in patients with high cervical spinal cord injury.

Frontiers in genetics·2025

Same author

"Smart" Nerves Sprout and Assemble in an Extracellular Matrix-Based 3D Nerve-in-a-Chip Microfluidic Model.

Small (Weinheim an der Bergstrasse, Germany)·2025

Same author

Dynamic changes in liver stiffness measurement by 2D shear-wave elastography predict hepatocellular carcinoma in patients with chronic hepatitis B and well-controlled viremia: a retrospective study.

BMC gastroenterology·2025

Same author

Predicting hourly indoor ozone concentrations with sensor-based measurements and easily accessible predictors.

Eco-Environment & Health·2025

Same author

The Association Between Health Literacy and Depressive Symptoms With the Mediation Role of Family Health and Perceived Social Support in Older Adults: A Nationwide Cross-Sectional Study in China.

International journal of geriatric psychiatry·2025

Same author

An investigation of the relationship and pathways of influence between body mass index, motor coordination, and health-related physical fitness index in preschool children.

Frontiers in public health·2025

Same journal

Multifunctional reconfigurable terahertz metasurface based on vanadium dioxide phase transition: achieving broadband absorption and efficient polarization conversion.

Applied optics·2026

Same journal

High-Q-factor electromagnetically induced transparency utilizing quasi-bound states in the continuum in an all-dielectric terahertz metasurface.

Applied optics·2026

Same journal

Automated stitching interferometry for high-precision metrology of X-ray mirrors.

Applied optics·2026

Same journal

Experimental demonstration of an approach to designing a metal-dielectric DBR resonant cavity structure.

Applied optics·2026

Same journal

High-precision wavefront reconstruction from a single-shot interferogram using a physics-driven hybrid feature calibration network.

Applied optics·2026

Same journal

Ultra-high-Q Fano resonance based on coupled topological corner states in Kagome photonic crystals.

Applied optics·2026

See all related articles

This study introduces a deep learning method for precise welding in challenging environments. The approach enhances visual tracking and object detection, achieving high accuracy despite disturbances like arc lights and splashes.

Area of Science:

Robotics and Automation
Computer Vision
Materials Science

Background:

Welding precision is often compromised by environmental disturbances such as arc lights, splashes, and thermal deformations.
Existing methods struggle to maintain accuracy in complex, unstructured welding scenarios.

Purpose of the Study:

To develop a robust deep learning framework for precise visual tracking and object detection in challenging welding environments.
To mitigate the impact of disturbances on welding precision and ensure reliable performance.

Main Methods:

A convolutional long short-term memory (CLSTM) network is employed for initial visual tracking, preserving spatial structures and memory efficiency.
Multi-layer convolutional neural network (CNN) features are utilized for weld feature point determination via similarity matching.

Related Experiment Videos

Last Updated: Dec 21, 2025

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

A welding seam detection network is implemented for periodic reinitialization of the object filter to counteract model drift caused by noisy images.

Main Results:

The proposed method demonstrates smooth operation of the welding torch even under strong arc light and welding splash interference.
Tracking errors are reduced to ±0.5 mm, meeting practical welding requirements.
Comparative experiments validate the algorithm's superior accuracy and robustness over existing approaches.

Conclusions:

The integrated deep learning framework effectively addresses disturbances in complex welding environments.
The method significantly improves welding precision and robustness, making it suitable for industrial applications.
The algorithm offers a reliable solution for achieving high-accuracy automated welding.