Unmanned Aerial Vehicle Target Detection Integrating Computer Deep SORT Algorithm and Wireless Signal DOI Creative Commons

Ao Li

International Journal of Interdisciplinary Telecommunications and Networking, Год журнала: 2025, Номер 17(1), С. 1 - 15

Опубликована: Апрель 19, 2025

With the advancement of unmanned aerial vehicle (UAV) technology, accurately detecting UAV targets has become increasingly challenging. This study addresses this issue by proposing a novel target detection method that integrates real-time tracking algorithms with wireless signal technology. Experimental results demonstrate each improved module positively contributes to overall method. Compared traditional object approaches, proposed achieves superior performance on both VisDrone and COCO datasets, precision, recall, F1 score, mean squared error values 96.07%, 95.84%, 96.33%, 0.023%, respectively. integrated approach effectively enhances accuracy detection, offering robust solution for positioning in applications.

Язык: Английский

Improved YOLOv8n based helmet wearing inspection method DOI Creative Commons
Xinying Chen,

Z. Jiao,

Yuefan Liu

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 14, 2025

This paper proposes the YOLOv8n_H method to address issues regarding parameter redundancy, slow inference speed, and suboptimal detection precision in contemporary helmet-wearing target recognition algorithms. The YOLOv8 C2f module is enhanced with a new SC_Bottleneck structure, incorporating SCConv module, now termed SC_C2f, mitigate model complexity computational costs. Additionally, original Detect structure substituted PC-Head decoupling head, leading significant reduction count an enhancement efficiency. Moreover, replaced by significantly reducing enhancing Finally, regression accuracy convergence speed are boosted dynamic non-monotonic focusing mechanism introduced through WIoU boundary loss function. Experimental results on expanded SHWD dataset demonstrate 46.63% volume, 44.19% decrease count, 54.88% load, improvement mean Average Precision (mAP) 93.8% compared algorithm. In comparison other algorithms, proposed this markedly reduces size, load while ensuring superior accuracy.

Язык: Английский

Процитировано

0
Intelligent Transportation Surveillance via YOLOv9 and NASNet over Aerial Imagery DOI
Muhammad Hanzla, Ahmad Jalal

Опубликована: Фев. 18, 2025

Язык: Английский

Процитировано

0
Multi-source image feature extraction and segmentation techniques for karst collapse monitoring DOI Creative Commons
Wenbo Lin, Xiaozhen Li, Tingting Li

и другие.

Frontiers in Earth Science, Год журнала: 2025, Номер 13

Опубликована: Апрель 15, 2025

Introduction Karst collapse monitoring is a complex task due to data sparsity, underground dynamics, and the demand for real-time risk assessment. Traditional approaches often fall short in delivering timely accurate evaluations of risks. Methods To address these challenges, we propose Integrated Collapse Prediction Network (IKCPNet), novel framework that combines multi-source imaging, geophysical modeling, machine learning techniques. IKCPNet processes seismic hydrological patterns, environmental factors using an advanced encoding mechanism physics-informed module capture subsurface changes. A dynamic assessment strategy incorporated enable feedback probabilistic mapping. Results Experimental on OpenSARShip dataset demonstrate achieves accuracy 94.34 ± 0.02 IoU 90.23 ±0.02, outperforming previous best model by 1.22 0.89 points, respectively. Discussion These results highlight effectiveness improving prediction mitigation, showcasing its potential enhancing geological hazard through integration.

Язык: Английский

Процитировано

0
Unmanned Aerial Vehicle Target Detection Integrating Computer Deep SORT Algorithm and Wireless Signal DOI Creative Commons

Ao Li

International Journal of Interdisciplinary Telecommunications and Networking, Год журнала: 2025, Номер 17(1), С. 1 - 15

Опубликована: Апрель 19, 2025

With the advancement of unmanned aerial vehicle (UAV) technology, accurately detecting UAV targets has become increasingly challenging. This study addresses this issue by proposing a novel target detection method that integrates real-time tracking algorithms with wireless signal technology. Experimental results demonstrate each improved module positively contributes to overall method. Compared traditional object approaches, proposed achieves superior performance on both VisDrone and COCO datasets, precision, recall, F1 score, mean squared error values 96.07%, 95.84%, 96.33%, 0.023%, respectively. integrated approach effectively enhances accuracy detection, offering robust solution for positioning in applications.

Язык: Английский

Процитировано

0