TL;DR
A Yolov8-MED design integrate MHSA, ECA and DCNv3 to enhance the model’s ability to capture fine crack details and improve detection accuracy, to enhance the crack location accuracy and keep the computational cost simultaneously.
Pavement crack detection plays a fundamental role in ensuring the safety, durability, and sustainable operation of urban transportation infrastructure. These factors often lead to missed detections and false detections in existing deep learning models. To address these challenges, this paper proposes an improved YOLOv8-based crack detection framework termed SCD-YOLO. The proposed method introduces two key improvements. First, ConvNeXt V2 is employed as the backbone network to enhance feature extraction capability, enabling more accurate representation of fine cracks and weak structural features. Second, an Efficient Multi-scale Attention (EMA) mechanism is integrated to suppress background interference and improve feature discrimination. Experiments conducted on the public dataset demonstrate that SCD-YOLO achieves a mAP@0.5 of 89.7%, precision of 90.3%, and recall of 90.3%, outperforming other methods. The proposed method achieves superior detection accuracy while maintaining real-time performance, providing a reliable and scalable solution for intelligent pavement inspection within city infrastructure systems.
Accurate detection and characterization of surface defects in concrete dams is vital for ensuring safe operation. To address the limitations of existing research focused solely on cracks and the challenges traditional convolutional networks face in adapting to deformation and multiscale features, this study introduces DCN-YOLO, a deformable convolution-augmented framework for the simultaneous detection and classification of multiple defect types from UAV-acquired imagery. The model outputs bounding box localizations and categorical labels. Based on YOLOv12, this proposed model integrates DCNv4 deformable convolutions with the C3k2 module. By leveraging adaptive sampling offsets and dynamic modulation, the proposed model enhances geometric modeling for irregular defects, improving the detection of small and medium defects while achieving an acceptable trade-off in inference efficiency. To address multiple defect coexistence, we adopt Binary Cross-Entropy (BCE) loss to decouple classification and localization, improving training stability in multi-label scenarios. A Multi-defects dataset was created using UAV images, and performance was validated on the CrackSeg public dataset. The proposed model achieved 77.4% ± 0.2% overall precision under complex conditions, exceeding the YOLOv12l baseline by 7.1% and improving mAP50-95 by 4.2%. It demonstrated competitive performance in detecting cracks, aggregate exposure, and construction joints, thereby providing a potentially robust and efficient approach for intelligent inspection of concrete dam surface defects.
To address the challenge that the diversity and complex morphology of pavement distresses make it difficult for traditional detection methods to simultaneously achieve high accuracy and real-time performance, a multi-class pavement distress detection approach based on the YOLO26 model is proposed. Seven common types of distresses, including block cracking, longitudinal cracking, transverse cracking, potholes, strip patching, block patching, and raveling, are considered as detection targets. A high-quality annotated dataset comprising 12,451 images is constructed. Experimental results show that YOLO26 achieves a precision of 0.80, a recall of 0.81, and an mAP@0.5 of 0.79 on the test set. These results outperform those of the comparative models, including YOLOv5, YOLOv8, and YOLO11. In particular, YOLO26 improves mAP@0.5 by 1.3% compared to YOLO11, while maintaining real-time inference speed. Visualization results further validate the model’s capability for accurate localization and classification of multiple distress types. This study provides a reliable and efficient technical solution for precise multi-class pavement distress detection.
Road surface cracks are key indicators of pavement deterioration, requiring accurate detection for timely maintenance. This study introduces a deep learning-based crack detection model using a hybrid U-Net architecture enhanced with a pre-trained ResNet50 encoder, Atrous Spatial Pyramid Pooling (ASPP), and attention gates. ResNet50 captures multi-level features, while ASPP extracts multi-scale contextual information, improving detection of cracks with diverse shapes and orientations. Attention mechanisms refine spatial features and suppress background noise, enhancing subtle crack identification. Trained on the Crack500 dataset (471 images with binary masks), the model incorporates preprocessing techniques like resizing, contrast normalization, and data augmentation to address class imbalance. Quantitative results show superior performance in accuracy, Dice coefficient, IoU, precision, and recall compared to traditional CNNs. Visual analysis confirms robustness under varied lighting and surface conditions. Future work may address challenges like noise, low contrast, and occlusion through advanced augmentation, domain adaptation, and real-time deployment via UAVs or robotic platforms.
Accurate road crack detection is essential for intelligent pavement inspection, yet thin crack morphology, cluttered backgrounds, and deployment constraints still challenge lightweight detectors. This paper presents an improved YOLOv11s-based detector for road distress recognition. Three coordinated modules are introduced: a C3k2- SHSA-CGLU backbone block for stronger contextual perception and dynamic crack-feature filtering, a GLSABiFPN neck for bidirectional multi-scale fusion with enhanced fine-detail retention, and a lightweight shared-convolution detection head for compact prediction. Experiments on the China subset of RDD2022 show that the proposed method improves mAP@0.5 from 87.2% to 89.4% and reduces parameters from 9.41 M to 7.32 M compared with YOLOv11s. Additional cross-dataset results on GRDDC2020 indicate acceptable generalization, while the reduced parameter count and compact model size suggest good deployment potential. Overall, the method provides a practical balance between detection accuracy and model compactness for automated pavement inspection.
In recent years, structural damage identification has emerged as a pivotal research focus within the field of Structural Health Monitoring (SHM). Currently, in-situ inspections primarily rely on traditional or manual measurement techniques, which demand substantial investments in both human resources and specialized instrumentation. Against this backdrop, the rapid advancement of Deep Learning models has surfaced as a highly promising approach to address these inherent limitations. This study proposes a solution utilizing the YOLOv11 computer vision model to automate the detection and analysis of geometric crack characteristics-including length, width, area, and orientation-in real-time from video or camera input data. Experimental results indicate that the loss function achieved stabilized convergence at the 175th epoch. With a mAP@50 of 80% and a mAP@50-95 of 60%, the model demonstrates robust performance in identifying crack objects, which are typically characterized by complex morphologies and ambiguous boundaries. This method exhibits significant potential for the automation of structural damage inspection and measurement.
