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: Nov 30, 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 Lightweight Spatial and Temporal Multi-Feature Fusion Network for Defect Detection.

Bozhen Hu, Bin Gao, Wai Lok Woo

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|November 13, 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

Activated hepatic stellate cells impair NK cell anti-fibrosis capacity through a TGF-β-dependent emperipolesis in HBV cirrhotic patients.

Scientific reports·2017

Same author

Concurrent agglomeration and straining govern the transport of <sup>14</sup>C-labeled few-layer graphene in saturated porous media.

Water research·2017

Same author

Effects of temperature on graphene oxide deposition and transport in saturated porous media.

Journal of hazardous materials·2017

Same author

Computational Analysis of Intra-Ventricular Flow Pattern Under Partial and Full Support of BJUT-II VAD.

Medical science monitor : international medical journal of experimental and clinical research·2017

Same author

Inflammation is independent of steatosis in a murine model of steatohepatitis.

Hepatology (Baltimore, Md.)·2017

Same author

Electromagnetic pulsed thermography for natural cracks inspection.

Scientific reports·2017

This study introduces an automated thermography defect detection model using a hybrid spatial-temporal segmentation approach. The lightweight, efficient model achieves accurate and robust defect identification with enhanced semantic understanding.

Area of Science:

Computer Vision
Artificial Intelligence
Materials Science

Background:

Automated defect detection in thermography is crucial for quality control.
Existing deep semantic segmentation models face challenges in accuracy and robustness.

Purpose of the Study:

To propose a novel hybrid multi-dimensional features fusion structure for automated thermography defect detection.
To enhance feature representation and improve detection accuracy through an adaptive attention mechanism and Sequence-PCA layer.

Main Methods:

Developed a lightweight spatial and temporal segmentation model incorporating a novel attention block for adaptive feature recalibration.
Integrated a Sequence-PCA layer to enrich semantic information within the network.
Employed model compression techniques to maintain performance with fewer parameters.

Related Experiment Videos

Last Updated: Nov 30, 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

Main Results:

The proposed model demonstrates superior accuracy and robustness compared to state-of-the-art deep semantic segmentation algorithms.
The novel attention module significantly improves performance on classification tasks.
Experimental validation on four diverse datasets confirms the model's effectiveness and robustness for defect detection.

Conclusions:

The hybrid model offers an effective and efficient solution for automated thermography defect detection.
The adaptive attention mechanism and Sequence-PCA layer contribute to improved semantic understanding and detection rates.
The lightweight and high-performing model is suitable for practical applications requiring precise defect identification.