Enhance the Concrete Crack Classification Based on a Novel Multi-Stage YOLOV10-ViT Framework DOI Creative Commons
Ali Mayya, Nizar Faisal Alkayem

Sensors, Journal Year: 2024, Volume and Issue: 24(24), P. 8095 - 8095

Published: Dec. 19, 2024

Early identification of concrete cracks and multi-class detection can help to avoid future deformation or collapse in structures. Available traditional methodologies require enormous effort time. To overcome such difficulties, current vision-based deep learning models effectively detect classify various cracks. This study introduces a novel multi-stage framework for crack type classification. First, the recently developed YOLOV10 model is trained possible defective regions images. After that, modified vision transformer (ViT) images into three main types: normal, simple cracks, multi-branched The evaluation process includes feeding test model, identifying defect regions, finally delivering detected ViT which decides appropriate those regions. Experiments are conducted using individual proposed framework. improve generation ability, multi-source datasets structures used. For classification part, dataset consisting 12,000 classes utilized, while composed materials from historical buildings containing 1116 with their corresponding bounding boxes, utilized. Results prove that accurately classifies types 90.67% precision, 90.03% recall, 90.34% F1-score. results also show outperforms by 10.9%, 19.99%, 19.2% F1-score, respectively. YOLOV10-ViT be integrated construction systems based on obtain early warning

Language: Английский

Co-CrackSegment: A New Corporative Deep Learning Framework for Pixel-Level Semantic Segmentation of Concrete Cracks DOI Open Access
Nizar Faisal Alkayem, Ali Mayya, Xin Zhang

et al.

Published: Aug. 27, 2024

In the era of massive construction, damaged and aging infrastructure are becoming more common. Defects, such as cracking, spalling, etc., main types structural damage that widely occur. Hence, ensuring safe operation existing through health monitoring has emerged an important challenge facing engineers. recent years, intelligent approaches, data driven machine deep learning crack detection, gradually dominate over traditional methods. Among them, semantic segmentation using models is a process characterization accurate location portrait cracks pixel level classification. Most available studies rely on single model knowledge to perform this task. However, it well-known might suffer from low variance ability generalize in case alteration. By leveraging ensemble philosophy, novel corporative concrete method called Co-CrackSegment proposed. Firstly, five models, namely U-net, SegNet, DeepCrack19, DeepLabV3-ResNet50, DeepLabV3-ResNet101 trained serve core for Co-CrackSegment. To build Co-CrackSegment, new iterative approach based best evaluation metrics, dice score, IoU, accuracy, precision, recall metrics developed. Results show exhibits prominent performance compared weighted average by means considered statistical metrics.

Language: Английский

Citations

2
Enhance the Concrete Crack Classification Based on a Novel Multi-Stage YOLOV10-ViT Framework DOI Creative Commons
Ali Mayya, Nizar Faisal Alkayem

Sensors, Journal Year: 2024, Volume and Issue: 24(24), P. 8095 - 8095

Published: Dec. 19, 2024

Early identification of concrete cracks and multi-class detection can help to avoid future deformation or collapse in structures. Available traditional methodologies require enormous effort time. To overcome such difficulties, current vision-based deep learning models effectively detect classify various cracks. This study introduces a novel multi-stage framework for crack type classification. First, the recently developed YOLOV10 model is trained possible defective regions images. After that, modified vision transformer (ViT) images into three main types: normal, simple cracks, multi-branched The evaluation process includes feeding test model, identifying defect regions, finally delivering detected ViT which decides appropriate those regions. Experiments are conducted using individual proposed framework. improve generation ability, multi-source datasets structures used. For classification part, dataset consisting 12,000 classes utilized, while composed materials from historical buildings containing 1116 with their corresponding bounding boxes, utilized. Results prove that accurately classifies types 90.67% precision, 90.03% recall, 90.34% F1-score. results also show outperforms by 10.9%, 19.99%, 19.2% F1-score, respectively. YOLOV10-ViT be integrated construction systems based on obtain early warning

Language: Английский

Citations

0