Classification, Localization and Quantization of Eddy Current Detection Defects in CFRP Based on EDC-YOLO DOI Creative Commons

Robert K. Wen,

Chongcong Tao,

Hongli Ji

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(20), P. 6753 - 6753

Published: Oct. 21, 2024

The accurate detection and quantification of defects is vital for the effectiveness eddy current nondestructive testing (ECNDT) carbon fiber-reinforced plastic (CFRP) materials. This study investigates identification measurement three common CFRP defects-cracks, delamination, low-velocity impact damage-by employing You Only Look Once (YOLO) model an improved Eddy Current YOLO (EDC-YOLO) model. YOLO's limitations in detecting multi-scale features are addressed through integration Transformer-based self-attention mechanisms deformable convolutional sub-modules, with additional global feature extraction via CBAM. By leveraging Wise-IoU loss function, performance further enhanced, leading to a 4.4% increase mAP50 defect detection. EDC-YOLO proves be effective industrial inspections, providing detailed insights, such as correlation between damage size energy levels.

Language: Английский

MS-YOLOv8-Based Object Detection Method for Pavement Diseases DOI Creative Commons
Zhibin Han,

Yutong Cai,

Anqi Liu

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(14), P. 4569 - 4569

Published: July 14, 2024

Detection of pavement diseases is crucial for road maintenance. Traditional methods are costly, time-consuming, and less accurate. This paper introduces an enhanced disease recognition algorithm, MS-YOLOv8, which modifies the YOLOv8 model by incorporating three novel mechanisms to improve detection accuracy adaptability varied conditions. The Deformable Large Kernel Attention (DLKA) mechanism adjusts convolution kernels dynamically, adapting multi-scale targets. Separable (LSKA) enhances SPPF feature extractor, boosting extraction capabilities. Additionally, Multi-Scale Dilated in network's neck performs Spatially Weighted Convolution (

Language: Английский

Citations

3
Improving real-time object detection in Internet-of-Things smart city traffic with YOLOv8-DSAF method DOI Creative Commons
Yihong Li, Yanrong Huang, Qi Tao

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: July 26, 2024

With the rise of global smart city construction, target detection technology plays a crucial role in optimizing urban functions and improving quality life. However, existing technologies still have shortcomings terms accuracy, real-time performance, adaptability. To address this challenge, study proposes an innovative model. Our model adopts structure YOLOv8-DSAF, comprising three key modules: depthwise separable convolution (DSConv), dual-path attention gate module (DPAG), feature enhancement (FEM). Firstly, DSConv optimizes computational complexity, enabling within limited hardware resources. Secondly, DPAG introduces dual-channel mechanism, allowing to selectively focus on areas, thereby accuracy high-dynamic traffic scenarios. Finally, FEM highlights features prevent their loss, further enhancing accuracy. Additionally, we propose Internet Things framework consisting four main layers: application domain, infrastructure layer, edge cloud layer. The proposed algorithm utilizes layer collect process data real-time, achieving faster response times. Experimental results KITTI V Cityscapes datasets indicate that our outperforms YOLOv8 This suggests complex scenarios, exhibits superior performance with higher We believe will significantly propel development cities advance technology.

Language: Английский

Citations

3
MarineYOLO: Innovative deep learning method for small target detection in underwater environments DOI Creative Commons

Linlin Liu,

Chengxi Chu,

Chuangchuang Chen

et al.

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 104, P. 423 - 433

Published: Aug. 7, 2024

In the realm of underwater object detection, conventional methodologies often encounter challenges in accurately identifying and detecting small targets. These difficulties stem primarily from intricate nature environments, suboptimal lighting conditions, diminutive scale targets themselves. To address this persistent challenge, MarineYOLO network is introduced. This approach involves refining C2f module into EC2f module, alongside integration Efficient Multi-scale Attention (EMA) YOLOv8. Additionally, Convolutional Block Module (CBAM) introduced to further refine Feature Pyramid Network (FPN), facilitating enhanced feature extraction pertinent Furthermore, CIoU replaced with Wise-IoU augment precision stability target localization. Experimental findings demonstrate that achieves an average (AP) 78.5% on RUOD dataset 88.1% URPC dataset, marking improvements 12.2% 16.8%, respectively, compared YOLOv8n. As emerging paradigm harbors significant potential both practical applications scholarly endeavors, furnishing efficacious remedy associated settings.

Language: Английский

Citations

3
CT-DETR and ReID-Guided Multi-Target Tracking Algorithm in Complex Scenes DOI
Ming Gao,

Shixin Yang

Published: May 29, 2024

In the era of rapid technological advancement, demand for sophisticated Multi-Object Tracking (MOT) systems in applications such as intelligent surveillance and autonomous navigation has become increasingly critical.However, existing models often struggle with accuracy efficiency densely populated or dynamically complex environments. Addressing these challenges, we introduce a novel deep learning-based MOT model that incorporates latest CT-DETR detection technology an advanced ReID module improved pedestrian tracking. Experimental results demonstrate model's superior performance accurately identifying tracking multiple targets across varied scenarios, significantly outperforming benchmarks.This research not only marks significant leap forward field video but also lays foundational framework future advancements system applications, underscoring importance innovation learning methodologies real-world challenges.

Language: Английский

Citations

2
Vehicular mobility monitoring using remote sensing and deep learning on a UAV-based mobile computing platform DOI
Murat Bakırcı

Measurement, Journal Year: 2024, Volume and Issue: unknown, P. 116579 - 116579

Published: Dec. 1, 2024

Language: Английский

Citations

2
PerNet: Progressive and Efficient All-in-One Image-Restoration Lightweight Network DOI Open Access
Wentao Li,

Guang Zhou,

Sen Lin

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(14), P. 2817 - 2817

Published: July 17, 2024

The existing image-restoration methods are only effective for specific degradation tasks, but the type of image in practical applications is unknown, and mismatch between model actual will lead to performance decline. Attention mechanisms play an important role tasks; however, it difficult attention effectively utilize continuous correlation information noise. In order solve these problems, we propose a Progressive Efficient All-in-one Image Restoration Lightweight Network (PerNet). network consists Plug-and-Play Local Module (PPELAM). PPELAM composed multiple Units (ELAUs) can use global horizontal vertical features space, so as reduce loss have small number parameters. PerNet able learn properties images very well, which allows us reach advanced level tasks. Experiments show that has excellent results typical restoration tasks (image deraining, dehazing, desnowing underwater enhancement), ELAU combined with Transformer ablation experiment chapter further proves high efficiency ELAU.

Language: Английский

Citations

1
Enhancing brain tumor detection in MRI images using YOLO-NeuroBoost model DOI Creative Commons

A. Lumin Chen,

Da Lin, Qiqi Gao

et al.

Frontiers in Neurology, Journal Year: 2024, Volume and Issue: 15

Published: Aug. 22, 2024

Brain tumors are diseases characterized by abnormal cell growth within or around brain tissues, including various types such as benign and malignant tumors. However, there is currently a lack of early detection precise localization in MRI images, posing challenges to diagnosis treatment. In this context, achieving accurate target images becomes particularly important it can improve the timeliness effectiveness To address challenge, we propose novel approach–the YOLO-NeuroBoost model. This model combines improved YOLOv8 algorithm with several innovative techniques, dynamic convolution KernelWarehouse, attention mechanism CBAM (Convolutional Block Attention Module), Inner-GIoU loss function. Our experimental results demonstrate that our method achieves mAP scores 99.48 97.71 on Br35H dataset open-source Roboflow dataset, respectively, indicating high accuracy efficiency detecting images. research holds significant importance for improving treatment provides new possibilities development medical image analysis field.

Language: Английский

Citations

1
基于改进YOLOv8s的SAR图像舰船目标检测方法 DOI

杨明秋 Yang Mingqiu,

左小清 Zuo Xiaoqing,

董燕 Dong Yan

et al.

Laser & Optoelectronics Progress, Journal Year: 2024, Volume and Issue: 61(22), P. 2228001 - 2228001

Published: Jan. 1, 2024

Citations

1
Enhancing Real-time Target Detection in Smart Cities: YOLOv8-DSAF Insights DOI Creative Commons
Yihong Li, Yanrong Huang, Qi Tao

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 29, 2024

Abstract With the global rise of smart city construction, target detection technology plays a crucial role in optimizing urban functions and improving quality life. However, existing technologies still have shortcomings terms accuracy, real-time performance, adaptability. To address this challenge, study proposes an innovative model. Our model adopts structure YOLOv8-DSAF. The comprises three key modules: Depthwise Separable Convolution (DSConv), Dual-Path Attention Gate module (DPAG), Feature Enhancement Module (FEM). Firstly, DSConv optimizes computational complexity, enabling within limited hardware resources. Secondly, DPAG introduces dual-channel attention mechanism, allowing to selectively focus on areas, thereby accuracy high-dynamic traffic scenarios. Finally, FEM highlights features prevent their loss, further enhancing accuracy. Experimental results KITTI V Cityscapes datasets indicate that our outperforms YOLOv8 This suggests complex scenarios, exhibits superior performance with higher We believe will significantly propel development cities advance technology.

Language: Английский

Citations

0
YOLOv8-BCC: Lightweight Object Detection Model Boosts Urban Traffic Safety DOI Creative Commons
Jun Tang,

Zhouxian Lai,

Caixian Ye

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: April 5, 2024

Abstract With the rapid development of urbanization, role urban transportation systems has become increasingly prominent. However, traditional methods traffic management are struggling to cope with growing demands and complexity environments. In response this situation, we propose YOLOv8-BCC algorithm address existing shortcomings. Leveraging advanced technologies such as CFNet, CBAM attention modules, BIFPN structure, our aims enhance accuracy, real-time performance, adaptability intelligent detection systems. Experimental results demonstrate significant improvements in accuracy performance compared methods. The introduction provides a robust solution for enhancing safety management.

Language: Английский

Citations

0