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: May 23, 2026

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Anti-interference framework for weakly supervised thermal defect segmentation on high-rise building facades.

Zeming Zhao¹, Yongqiang Jin¹, Daiming Liu²

¹China MCC5 Group Corp, Sichuan, 610063, China.

Scientific Reports

|May 21, 2026

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

Rectal malignant peripheral nerve sheath tumor with extremely high Ki-67 index (80%) and concomitant meningioma history: a case report.

Frontiers in oncology·2026

Same author

Study on isolation pillar thickness optimization and slope stability control in hanging wall ore mining.

Scientific reports·2026

Same author

Cohydrothermal carbonization of cellulose and organic matter from municipal sewage sludge for the controllable synthesis of N-doped porous carbon for supercapacitor electrodes.

Journal of environmental management·2026

Same author

Reversal of Glenn-associated diffuse pulmonary arteriovenous malformations after total cavopulmonary connection: a case report.

Frontiers in cardiovascular medicine·2026

Same author

Intelligent Detection Method of Defects in High-Rise Building Facades Using Infrared Thermography.

Sensors (Basel, Switzerland)·2026

Same author

V-Y advancement flap technique for severe cicatricial lower eyelid ectropion: A case report and outcome assessment.

JPRAS open·2025

Same journal

Peripheral B-cell receptor repertoire predicts immune-related adverse events following immune checkpoint inhibitor therapy in advanced renal cell carcinoma.

Scientific reports·2026

Same journal

Effects of black soldier fly (Hermetia illucens L.) larvae zoocompost on the mineral element content of blue honeysuckle berries.

Scientific reports·2026

Same journal

Investigation on absorption refrigeration performance of R1243zf with imidazolium ionic liquid as the working pairs.

Scientific reports·2026

Same journal

DeepTriage-CN: integrating clinical text with vital signs for emergency department admission prediction in an aging population.

Scientific reports·2026

Same journal

Gold nanoparticles as dual-action antiviral agents: disruption of SARS-CoV-2 viral envelopes and RNA integrity.

Scientific reports·2026

Same journal

Comparison of capillary microsampling and venous blood for multi-pathogen serosurveillance.

Scientific reports·2026

See all related articles

This study introduces a new weakly supervised framework for segmenting infrared facade defects, significantly reducing annotation costs while improving accuracy in high-rise building inspections. The method effectively rejects interference and achieves precise pixel-level segmentation using only box-level annotations.

Area of Science:

Building Science and Engineering
Computer Vision and Image Analysis
Materials Science

Background:

Infrared thermography is vital for high-rise building facade safety.
Accurate defect quantification requires costly pixel-level annotations.
Existing weakly supervised methods struggle with low-quality pseudo-labels and inaccurate boundaries in infrared images.

Purpose of the Study:

To develop an anti-interference-driven segmentation framework for infrared facade defects.
To reduce annotation costs for semantic segmentation in facade inspections.
To improve the accuracy of defect boundary detection in infrared images.

Main Methods:

An improved DeepLabV3+ module with boundary-aware triplet loss and superpixel consistency for interference rejection.

Keywords:

DeepLabV3+Defect detection Infrared thermography SAM 2 Weakly supervised segmentation YOLOV11

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Related Experiment Videos

Last Updated: May 23, 2026

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

YOLOv11 for defect localization and generating bounding box prompts.

Weakly supervised fine-tuning of Segment Anything Model 2 using box prompts and pseudo-mask guidance.

Main Results:

Achieved 76.2% mean Intersection over Union (IoU) for interference rejection.
Attained 86.5% mean Average Precision (mAP@0.5) for precise defect localization.
Reached 63.4% IoU, 87.0% F1-score, 83.1% precision, and 91.3% recall for pixel-level segmentation using only box annotations.

Conclusions:

The proposed framework effectively rejects pseudo-thermal anomalies and achieves high-precision segmentation of infrared facade defects.
Weakly supervised learning with box prompts and pseudo-masks significantly reduces the need for manual pixel-level annotations.
Demonstrated the feasibility of high-precision thermal defect segmentation for large-scale facade inspection of high-rise buildings.