What question did this study set out to answer?

This study aims to evaluate YOLO architectures for detecting buried manhole covers through GPR radargrams.

April 24, 2026IET Smart CitiesOpen Access

Comparative Evaluation of YOLO Architectures for Automated Detection of Buried Manhole Covers in GPR Radargrams

View Full Paper

Ask AI

Bookmark

Authors

JPJantana PanyavarapornBurapha University SESitthiphat Eua-apiwatchBurapha University

Discussion

Member takes

Implication

Comparative evaluation of YOLO variants improves detection accuracy in buried manhole cover applications, suggesting optimal model selection for infrastructure inspection.

Key Points

This study aims to evaluate YOLO architectures for detecting buried manhole covers through GPR radargrams.
Compare YOLOv5s, YOLOv8s, and YOLOv11s in detecting buried manhole covers.
Use 9-fold cross-validation on 54 radargrams with varied surface types, burial depths, and compaction levels.
Assess detection performance metrics such as accuracy, precision, recall, and mAP.
YOLOv5s demonstrated the best performance with an accuracy of 0.7865 and low variability.
YOLOv8s showed better generalization on strict thresholds but had limitations in deployment stability.
Detection accuracy decreased significantly at higher compaction levels and greater burial depths due to electromagnetic attenuation.

Cite This Study

Panyavaraporn et al. (2026) studied this question.

synapsesocial.com/papers/69eb0bc7553a5433e34b5552 https://doi.org/10.1049/smc2.70027

View Full Paper

Ask AI

Bookmark

April 24, 2026IET Smart CitiesOpen Access

Comparative Evaluation of YOLO Architectures for Automated Detection of Buried Manhole Covers in GPR Radargrams

View Full Paper

Ask AI

Bookmark

Authors

JPJantana PanyavarapornBurapha University SESitthiphat Eua-apiwatchBurapha University

Discussion

Member takes

Implication

Comparative evaluation of YOLO variants improves detection accuracy in buried manhole cover applications, suggesting optimal model selection for infrastructure inspection.

Key Points

This study aims to evaluate YOLO architectures for detecting buried manhole covers through GPR radargrams.
Compare YOLOv5s, YOLOv8s, and YOLOv11s in detecting buried manhole covers.
Use 9-fold cross-validation on 54 radargrams with varied surface types, burial depths, and compaction levels.
Assess detection performance metrics such as accuracy, precision, recall, and mAP.
YOLOv5s demonstrated the best performance with an accuracy of 0.7865 and low variability.
YOLOv8s showed better generalization on strict thresholds but had limitations in deployment stability.
Detection accuracy decreased significantly at higher compaction levels and greater burial depths due to electromagnetic attenuation.

Cite This Study

Panyavaraporn et al. (2026) studied this question.

synapsesocial.com/papers/69eb0bc7553a5433e34b5552 https://doi.org/10.1049/smc2.70027

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark