Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 228, P. 109689 - 109689
Published: Nov. 28, 2024
Language: Английский
Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 228, P. 109689 - 109689
Published: Nov. 28, 2024
Language: Английский
Automation in Construction, Journal Year: 2024, Volume and Issue: 170, P. 105906 - 105906
Published: Dec. 5, 2024
Language: Английский
Citations
1Engineering and Applied Sciences, Journal Year: 2024, Volume and Issue: 9(4), P. 69 - 82
Published: Aug. 30, 2024
Crack detection in pavements is a critical task for infrastructure maintenance, but it often requires extensive manual labeling of training samples, which both time-consuming and labor-intensive. To address this challenge, paper proposes semi-supervised learning approach based on DenseNet classification model to detect pavement cracks more efficiently. The primary objective leverage small set labeled samples improve the model's performance by incorporating large number unlabeled through learning. This method enhances ability generalize iteratively from new datasets. As result, proposed not only reduces need also mitigates issues related label inconsistency errors original labels. experimental results demonstrate that achieves prediction precision 96.77% recall 94.17%, with an F1 score 95.45% Intersectidn over Union (IoU) 91.30%. These metrics highlight high accuracy effectiveness crack detection. improves quality offers practical value engineering applications field making valuable tool management.
Language: Английский
Citations
1Structures, Journal Year: 2024, Volume and Issue: 70, P. 107834 - 107834
Published: Nov. 16, 2024
Language: Английский
Citations
0Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 228, P. 109689 - 109689
Published: Nov. 28, 2024
Language: Английский
Citations
0