文章详情

摘要

移动网络覆盖问题是通信领域的研究热点。传统的MR.TadvRsrp图分类与诊断依赖于工程师的技能和经验，过程烦琐且实时性差。为解决这一问题，文章提出了一种基于改进YOLOv8-cls算法的智能分类方法。该方法采用YOLOv8n-cls网络作为特征提取网络，在骨干网络中融合混合注意力模块（CBAM），提升特征提取能力，并加入空间金字塔池化模块（SPP-Fast），增强多尺度特征聚合效果。通过设计多层级感受野融合结构（MF），弥补了YOLOv8n-cls网络中缺少颈部结构（Neck）导致的特征融合不足问题。改进后的算法显著提升了图片分类的准确性和处理速度。实验结果表明，该方法对某地4G/5G网络覆盖切片图的分类与诊断准确率达到了95.7%，处理速度（FPS）达到了110帧/秒，具备高准确性和强实时性，为网络规划和运营优化提供了高效的评估支撑。

关键词

移网覆盖；图片分类；多尺度融合；YOLOv8-cls

参考文献

1. [1] KRIZHEVSKY A，SUTSKEVER I，HINTON G E. ImageNet Classification with Deep Convolutional Neural Networks [J].Communications of the ACM，2017，60（6）：84-90.
2. [2] SZEGEDY C，LIU W，JIA Y Q，et al. Going Deeper with Convolutions [C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Boston：IEEE，2015：1-9.
3. [3] HE K M，ZHANG X Y，REN S Q AND SUN J. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification [C]//2015 IEEE International Conference on Computer Vision (ICCV).Santiago：IEEE，2015：1026-1034.
4. [4] REDMON J，DIVVALA S，GIRSHICK R，et al. You Only Look Once: Unified, Real-Time Object Detection [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas：IEEE，2016：779-788.
5. [5] REDMON J，FARHADI A. YOLO9000: Better, Faster, Stronger [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu：IEEE，2017：6517-6525.
6. [6] REDMON J，FARHADI A. YOLOv3: An Incremental Improvement [J/OL].arXiv:1804.02767 [cs.CV].[2024-11-03].https://arxiv.org/abs/1804.02767.
7. [7] LU Y，QIU Z B，LIAO C B，et al. A GIS Partial Discharge Defect Identification Method Based on YOLOv5 [J/OL].Applied Sciences，2022，12（16）：8360[2024-10-27].https://doi.org/10.3390/app12168360.
8. [8] ZENG J Y，ZHONG H. YOLOv8-PD: An Improved Road Damage Detection Algorithm Based on YOLOv8n Model [J/OL].Scientific Reports，2024，14（1）：12052[2024-10-06].https://doi.org/10.1038/s41598-024-62933-z.
9. [9] ZHANG S F，CHIC，YA0 Y Q，et al. Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle：IEEE，2020：9759-9768.
10. [10] LI C Y，LI L L，JLANG H L，et al. YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications [J/OL].arXiv:2209.02976 [cs.CV].[2024-11-05].https://arxiv.org/abs/2209.02976.
11. [11] LI X，LYU C Q，WANG W H，et al. Generalized Focal Loss: Towards Efficient Representation Learning for Dense Object Detection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2022，45（3）：3139-3153.
12. [12] TIAN Z，SHEN C H，CHEN H，et al. FCOS: Fully Convolutional One-Stage Object Detection [C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV).Seoul：IEEE，2019：9626-9635.
13. [13] WOO S ，PARK J，LEE J-Y，et al. CBAM: Convolutional Block Attention Module [C]//Computer Vision-ECCV 2018: 15th European Conference, Munich, Germany.Munich：Springer-Verlag，2018：3-19.
14. [14] 付浩辰，白堂博，许贵阳，等．基于改进 YOLOv8 的轨道板裂缝检测算法 [J]．北京交通大学学报，2024，48（6）：133-143.
15. [15] HE K M，ZHANG X Y，REN S Q. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，37（9）：1904-1916.
16. [16] TANG H Y，LIANG S，YAO D，et al. A Visual Defect Detection for Optics Lens Based on the YOLOv5 -C3CA-SPPF Network Model [J].Optics Express，2023，31（2）：2628-2643.
17. [17] LIU S，QI L，QIN H F，et al. Path Aggregation Network for Instance Segmentation [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City：IEEE，2018：8759-8768.
18. [18] LIN T-Y，DOLLÁR P，GIRSHICK R，et al. Feature Pyramid Networks for Object Detection [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu：IEEE，2017：2117-2125.
19. [19] TAN M X，PANG R M，LE Q V. EfficientDet: Scalable and Efficient Object Detection [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattl：IEEE，2020：10778-10787.
20. [20] WANG Q L，WU B G，ZHU P F，et al. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle：IEEE，2020：11531-11539.
21. [21] HE K M，ZHANG X Y，REN S Q，et al. Deep Residual Learning for Image Recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Los Alamitos：IEEE，2016：770-778.
22. [22] ZHANG Q L，YANG Y B. SA-Net: Shuffle Attention for Deep Convolutional Neural Networks [J/OL].arXiv:2102.00240 [cs.CV].[2024-10-07].https://arxiv.org/abs/2102.00240.
23. [23] GUAN B X，ZHAO Y H，LI Y，An Ant Colony Optimization Based on Information Entropy for Constraint Satisfaction Problems [J/OL].Entropy，2019，21（8）：766[2024-09-28].https://doi.org/10.3390/e21080766.

作者简介

唐天彪（1987—），男，汉族，四川巴中人，工程师，硕士研究生，研究方向：机器学习与移动网络优化；王舒波（1993—），男，汉族，新疆乌鲁木齐人，工程师，硕士研究生，研究方向：人工智能与机器学习。