Page 20 - 《武汉大学学报（信息科学版）》2025年第6期

第 50 卷 第 6 期 武 汉 大 学 学 报（ 信 息 科 学 版 ） Vol.50 No.6
2025 年 6 月 Geomatics and Information Science of Wuhan University Jun. 2025

引文格式：甄杰,祁俊杰,王勇，等 . 面向应急通信选址的增强卷积神经网络山顶点快速提取方法[J]. 武汉大学学报（信息科学
版）,2025,50(6):1042-1053.DOI:10.13203/j.whugis20250097
Citation：ZHEN Jie,QI Junjie,WANG Yong,et al.A Rapid Extraction Method of Summit Point for Emergency Communication
System Siting Based on Enhanced Convolutional Neural Network[J].Geomatics and Information Science of Wuhan University,
2025,50(6):1042-1053.DOI:10.13203/j.whugis20250097

面向应急通信选址的增强卷积神经网络山顶点

快速提取方法

甄 杰 祁俊杰 1,2 王 勇 徐胜华 刘纪平 1
1
1
1
1 中国测绘科学研究院，北京，100036
2 辽宁工程技术大学测绘与地理科学学院,辽宁 阜新,123000
摘 要：为解决重特大自然灾害发生时应急通信网络快速构建及优化部署问题，通过数字高程模型与等高线、坡度、坡向
融合的方法制作山顶点特征数据集，提升山顶区域特征信息，给出应急通信山顶区域筛选条件，提出适应多尺度山顶区
域定位的增强更快速区域卷积神经网络算法模型，并针对大区域进行拆分、检测再合并，提高山顶区域识别效果，运用局
部极大值方法实现了应急通信山顶点的精确化提取。所提改进算法模型与其他模型对比，均值平均精度达到 94.92%，
山顶点提取的准确度达到 94.2%，以此为通信节点的信号有效覆盖率达到 80.56%，可视率达到 77.43%，均优于正反地形
法和邻域分析法。
关键词：卷积神经网络；应急通信选址；山顶点提取；信号覆盖；可视域分析
中图分类号：TP208 文献标识码：A 收稿日期：2025‑03‑10
DOI：10.13203/j.whugis20250097 文章编号：1671‑8860（2025）06‑1042‑12
A Rapid Extraction Method of Summit Point for Emergency Communication

System Siting Based on Enhanced Convolutional Neural Network

1，2
1
1
1
ZHEN Jie QI Junjie WANG Yong XU Shenghua LIU Jiping 1
1 Chinese Academy of Surveying and Mapping, Beijing 100036, China
2 School of Geomatics, Liaoning Technology University, Fuxin 123000, China
Abstract： Objectives: It is urgent to solve the problem of rapid construction and optimal deployment of
emergency communication network when large-scale natural disaster occurs. Methods: First, the peak
points feature dataset is built up by fusing the digital elevation model with contour, slope, and slope aspect
to improve the feature information of the peak area. Then, the screening conditions of the peak area for
emergency communication are given and an enhanced faster region-based convolutional neural network
(Faster R-CNN) is proposed to adapted to the multi-scale positioning of the peak area. Finally, we split,
detect, and then merge the large area to improve the recognition effect of the peak area, and use the local
maximum value method to achieve the precise extraction of peak points for emergency communication. Re⁃
sults: Comparing the proposed improved algorithm with other algorithms, the mean average precision
(mAP) reaches 94.92%, the accuracy of peak points extraction reaches 94.2%, the effective coverage rate
of the communication node reaches 80.56%, and the visibility rate reaches 77.43%. Conclusions: The pro‑
posed method is effective in identifying small targets, more in line with the terrain characteristics than other
methods, and meets the actual communication needs in terms of communication to achieve a larger cover‑
age. The extraction results of the proposed method can be used as a reference for the deployment of emer‑

基金项目：国家重点研发计划（2022YFC3005705）。
第一作者：甄杰，博士，研究员，研究方向为室内外一体化导航定位、应急通信等。zhenjie@casm.ac.cn
通信作者：刘纪平，博士，研究员。liujp@casm.ac.cn