全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于改进YOLOv5的行人目标检测算法研究
Research on Pedestrian Target Detection Algorithm Based on Improved YOLOv5

DOI: 10.12677/airr.2025.143051, PP. 519-526

Keywords: 行人目标检测,YOLOv5,Ghost,SE
Pedestrian Target Detection
, YOLOv5, Ghost, SE

Full-Text   Cite this paper   Add to My Lib

Abstract:

本文针对行人目标检测中的挑战,提出了一种基于改进YOLOv5的行人检测算法。该算法融合了Ghost模块和SE注意力机制,旨在提高特征提取能力的同时,保持模型的轻量性。在面对密集场景和遮挡问题时,改进的YOLOv5能有效提取重要特征并提升检测精度。通过对比实验和模拟分析,验证了该算法在提升检测性能的同时,仍能保持较低的计算复杂度和较高的实时性。实验结果表明,所提算法在行人检测任务中具有较好的表现,尤其是在低照度和复杂背景条件下。
Aiming at the challenges in pedestrian target detection, this paper proposes a pedestrian detection algorithm based on improved YOLOv5. The algorithm combines the Ghost module and SE attention mechanism to improve the feature extraction capability while maintaining the lightweight of the model. When faced with dense scenes and occlusion problems, the improved YOLOv5 can effectively extract important features and improve detection accuracy. Through comparative experiments and simulation analysis, it is verified that the algorithm can maintain low computational complexity and high real-time performance while improving detection performance. Experimental results show that the proposed algorithm has good performance in pedestrian detection tasks, especially under low illumination and complex background conditions.

References

[1]  Ren, Z., Lam, E.Y. and Zhao, J. (2020) Real-time Target Detection in Visual Sensing Environments Using Deep Transfer Learning and Improved Anchor Box Generation. IEEE Access, 8, 193512-193522.
https://doi.org/10.1109/access.2020.3032955
[2]  Wang, T., Anwer, R.M., Cholakkal, H., Khan, F.S., Pang, Y. and Shao, L. (2019) Learning Rich Features at High-Speed for Single-Shot Object Detection. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 27 October-2 November 2019, 1971-1980.
https://doi.org/10.1109/iccv.2019.00206
[3]  Bodla, N., Singh, B., Chellappa, R. and Davis, L.S. (2017) Soft-NMS—Improving Object Detection with One Line of Code. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 5562-5570.
https://doi.org/10.1109/iccv.2017.593
[4]  Xue, Y., Ju, Z., Li, Y. and Zhang, W. (2021) MAF-YOLO: Multi-Modal Attention Fusion Based YOLO for Pedestrian Detection. Infrared Physics & Technology, 118, Article ID: 103906.
https://doi.org/10.1016/j.infrared.2021.103906
[5]  王维锋, 邵琳骞, 黄建鑫, 等. 基于改进YOLOv5的双模态融合行人检测方法[J/OL]. 吉林大学学报(工学版): 1-11.
https://doi.org/10.13229/j.cnki.jdxbgxb.20241288, 2025-03-12.
[6]  薛仁政, 吴乾龙, 叶宝丰. 基于可变形卷积的YOLOv5行人检测算法[J]. 齐齐哈尔大学学报(自然科学版), 2025, 41(2): 14-21, 27.
[7]  舒密, 王占刚. 基于Ghost卷积与自适应注意力的点云分类[J]. 现代电子技术, 2025, 48(6): 106-112.
[8]  Hu, J., Shen, L. and Sun, G. (2018) Squeeze-and-Excitation Networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 7132-7141.
https://doi.org/10.1109/cvpr.2018.00745
[9]  许皓翔, 殳国华. 基于轻量化的YOLOv5的PCB缺陷检测算法[J]. 电气自动化, 2024, 46(2): 95-97, 102.
[10]  Girshick, R. (2015) Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1440-1448.
https://doi.org/10.1109/iccv.2015.169

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133