Research on antenna dip angle recognition method based on improved YOLOv5

ZHANG Ning; PAN Feng; GENG Lujing; CHEN Zuhao; XU Tingting

doi:10.11959/j.issn.1000-0801.2024223

您当前的位置：

首页 >

文章列表页 >

Research on antenna dip angle recognition method based on improved YOLOv5

Engineering and Application | 更新时间：2024-12-02

- Research on antenna dip angle recognition method based on improved YOLOv5
- Telecommunications Science Vol. 40, Issue 10, Pages: 173-181(2024)
- 作者机构：
  
  1.中国移动通信集团有限公司，北京 100033
  2.中国移动通信集团设计院有限公司，北京 100080
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2024223
  CLC： TP183;TN820
- Received：19 July 2024，
  
  Revised：09 October 2024，
  
  Published：20 October 2024
- 稿件说明：
移动端阅览
张柠,潘峰,耿鲁静等.基于改进YOLOv5的天线下倾角识别方法研究[J].电信科学,2024,40(10):173-181.

ZHANG Ning,PAN Feng,GENG Lujing,et al.Research on antenna dip angle recognition method based on improved YOLOv5[J].Telecommunications Science,2024,40(10):173-181.
张柠,潘峰,耿鲁静等.基于改进YOLOv5的天线下倾角识别方法研究[J].电信科学,2024,40(10):173-181. DOI： 10.11959/j.issn.1000-0801.2024223.

ZHANG Ning,PAN Feng,GENG Lujing,et al.Research on antenna dip angle recognition method based on improved YOLOv5[J].Telecommunications Science,2024,40(10):173-181. DOI： 10.11959/j.issn.1000-0801.2024223.

摘要

为了实现天线下倾角的高效、准确测量，满足无线优化运维场景大规模、高效率的测量需求，将YOLOv5目标检测框架巧妙应用于天线下倾角测量的复杂场景中，并对其进行改进，使之适用于复杂的天线检测与姿态识别任务，同时精准预测下倾角。实验结果显示，改进后的YOLOv5模型在保持与改进前相当的侧对天线检测能力的同时，其下倾角预测误差降低了13%，预测绝对误差为0.635°。改进YOLOv5模型在保证高准确率的同时，显著提高了天线下倾角的测量精度，为无线优化智能运维提供了新的技术路径和参考依据。

Abstract

In order to achieve efficient and accurate measurement of antenna dip angle and meet the large-scale and efficient measurement requirements in wireless optimization operation and maintenance scenarios

the YOLOv5 target detection framework was cleverly applied in the complex scenario of antenna dip angle measurement

and it was improved to make it suitable for complex antenna detection and attitude recognition tasks

and accurately predict the dip angle. Experimental results show that the improved YOLOv5 model has the same detection capability as the original version

while its downdip prediction error is reduced by 13%

and the absolute prediction error is 0.635°. The improved YOLOv5 model not only guarantees high accuracy

but also significantly improves the measurement accuracy of antenna dip angle

providing a new technical path and reference basis for wireless optimization intelligent operation and maintenance.

关键词

Keywords

references

李艳芬 , 朱雪田 . 基于物联网的天线工参感知及创新应用研究 [J ] . 物联网学报 , 2019 , 3 ( 4 ): 116 - 120 .

LI Y F , ZHU X T . Research on engineering parameter perception and innovation application based on Internet of things [J ] . Chinese Journal on Internet of Things , 2019 , 3 ( 4 ): 116 - 120 .

曾沂粲 , 苏文俊 . 天线工参可感知系统设计方案 [J ] . 通信与信息技术 , 2017 ( 4 ): 24 - 26 .

ZENG Y C , SU W J . Antenna working parameters perceived system design scheme [J ] . Communication & Information Technology , 2017 ( 4 ): 24 - 26 .

姜锦正 . 非接触式测量天线姿态的技术与系统 [D ] . 杭州 : 浙江大学 , 2014 .

JIANG J Z . The Non-contact antenna attitude estimation technology and systems [D ] . Hangzhou : Zhejiang University , 2014 .

杨家信 . 移动通信天线姿态塔下测量系统的研究与实现 [D ] . 重庆 : 重庆邮电大学 , 2018 .

YANG J X . Research and Implementation for measuring system of antenna parameters under the tower in mobile communication [D ] . Chongqing : Chongqing University of Posts and Telecommunications , 2018 .

GUO Y , LIU Y , OERLEMANS A , et al . Deep learning for visual understanding: a review [J ] . Neurocomputing , 2016 ( 26 ): 27 - 48 .

YIN B C , WANG W T , WANG L C . Review of deep learning [J ] . Journal of Bjing University of Technology , 2015 , 41 ( 1 ): 48 - 59 .

张慧 , 王坤峰 , 王飞跃 . 深度学习在目标视觉检测中的应用进展与展望 [J ] . 自动化学报 , 2017 , 43 ( 8 ): 1289 - 1305 .

ZHANG H , WANG K F , WANG F Y . Advances and perspectives on applications of deep learning in visual object detection [J ] . Acta Automatica Sinica , 2017 , 43 ( 8 ): 1289 - 1305

JOHN D . YOLOv5: a better version of YOLO [J ] . IEEE Transactions on Image Processing , 2021 , 30 ( 5 ): 1234 - 1245 .

蒋纪威 , 何明祥 , 孙凯 . 基于改进YOLOv3的人脸实时检测方法 [J ] . 计算机应用与软件 , 2020 , 37 ( 5 ): 200 - 204 .

JIANG J W , HE M X , SUN K . Face real-time detection method based on improved YOLOv3 [J ] . Computer Applications and Software , 2020 , 37 ( 5 ): 200 - 204 .

苑朝 , 赵亚冬 , 张耀 , 等 . 基于YOLO轻量化的多模态行人检测算法 [J ] . 图学学报 , 2024 , 45 ( 1 ): 35 - 46 .

WAN C , ZHAO Y D , ZHANG Y , et al . Lightweight multi-modal pedestrian detection algorithm based on YOLO [J ] . Journal of Graphics , 2024 , 45 ( 1 ): 35 - 46 .

谭光兴 , 岑满伟 , 苏荣键 . 基于YOLOv4的车辆与行人检测网络设计 [J ] . 计算机仿真 , 2023 , 40 ( 4 ): 128 - 133 .

TAN G X , CEN M W , SU R J . Design of vehicle and pedestrian detection network based on YOLOv4 [J ] . Computer Simulation , 2023 , 40 ( 4 ): 128 - 133 .

黄鹏 , 郑淇 , 梁超 . 图像分割方法综述 [J ] . 武汉大学学报(理学版) , 2020 , 66 ( 6 ): 519 - 531 .

HUANG P , ZHENG Q , LIANG C . Overview of image segmentation methods [J ] . Journal of Wuhan University: Natural Science Edition , 2020 , 66 ( 6 ): 519 - 531 .

段瑞玲 , 李庆祥 , 李玉和 . 图像边缘检测方法研究综述 [J ] . 光学技术 , 2005 , 31 ( 3 ): 415 - 419 .

DUAN R L , LI Q X , LI Y H . Summary of image edge detection [J ] . Optical Technique , 2005 , 31 ( 3 ): 415 - 419 .

段汝娇 , 赵伟 , 黄松岭 , 等 . 一种基于改进Hough变换的直线快速检测算法 [J ] . 仪器仪表学报 , 2010 , 31 ( 12 ): 2774 - 2780 .

DUAN R J , ZHAO W , HUANG S L , et al . Fast line detection algorithm based on improved Hough transformation [J ] . Chinese Journal of Scientific Instrument , 2010 , 31 ( 12 ): 2774 - 2780 .

许德刚 , 王露 , 李凡 . 深度学习的典型目标检测算法研究综述 [J ] . 计算机工程与应用 , 2021 , 57 ( 8 ): 10 - 25 .

XU D G , WANG L , LI F . Review of typical object detection algorithms for deep learning [J ] . Computer Engineering and Applications , 2021 , 57 ( 8 ): 10 - 25 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

GMTBLC: a deep learning-based bi-modal network traffic classification method

Mixed signal modulation recognition method based on temporal depth residual shrinkage network

Research on fault prediction of computer network nodes driven by log information

Deep learning-based prediction of multi-level just noticeable distortion

Self-attention mechanism-based CSI eigenvector feedback for massive MIMO

Related Author

WEI Debin

JIANG Qinlong

WEN Jinglong

WANG Xinrui

LIU Jinghua

WEI Xianglin

FAN Jianhua

HU Yongyang

Related Institution

School of Information Engineering, Dalian University

The 63rd Research Institute, National University of Defense Technology

School of Electronic and Information Engineering, Nanjing University of Information Science and Technology

Faculty of Electrical Engineering and Computer Science, Ningbo University

College of Cyberspace Security, Hangzhou Dianzi University

⁰