1 研究现状
2 算法总体设计
2.1 算法总体方案
2.2 加权K邻近无线通讯网络通信指纹定位算法
2.3 图像匹配定位算法
2.3.1 图像匹配策略
表1 特征数量与图像匹配因子Tab.1 Number of features and image matching factor |
| 名称 | F(DB,i) | Fc | ηi |
|---|---|---|---|
| 样本a | 659 | 647 | 1.888 |
| 样本b | 643 | 563 | 1.664 |
| 样本c | 628 | 489 | 1.6641.464 |
|
李耀宇(1984—),男,副教授,研究方向为军事运筹、任务规划、建模与仿真。 |
|
陈杰(1985—),男,副教授。 |
Copy editor: 张培培
收稿日期: 2023-03-17
修回日期: 2023-04-11
网络出版日期: 2023-12-07
Research on crowd-sourced localization algorithm for narrow and closed battlefield environment
Received date: 2023-03-17
Revised date: 2023-04-11
Online published: 2023-12-07
为解决在狭小封闭的战场环境,如敌方指挥中心、船舱、地下建筑物中,如何快速准确地获取自组织网络或目标对象的位置信息的问题,基于单兵智能终端设备提供的通信模块,利用可见光传感器等硬件设备的支持,通过研究群智感知式的通信信号指纹,结合图像匹配算法,提出了一种定位算法。该算法利用通信指纹数据实现了初步定位,结合融合图像和姿态传感器的加权平均算法,并采用群智感知方式补充与更新定位数据,通过调整图像匹配策略,在保持准确率的前提下,相比单一图像匹配定位算法,降低了算力的需求,在通信条件复杂的战场环境中提高了实时性能。对比标准的WKNN(Weighted K-Nearest Neighbors)算法,提高了在复杂环境下定位的稳定性,且定位误差平均值低于1.72 m,误差降低约50%。
李耀宇 , 陈杰 , 魏勇 . 面向狭小封闭战场环境的群智感知定位算法研究[J]. 指挥控制与仿真, 2023 , 45(6) : 36 -41 . DOI: 10.3969/j.issn.1673-3819.2023.06.006
In order to solve the problem of how to quickly and accurately obtain the location information of self-organizing networks or target objects in the narrow and closed battlefield environment, such as the enemy command center, cabins, and underground buildings, this paper proposes a positioning algorithm based on the communication module provided by individual intelligent terminal equipment, we use the support of hardware devices such as visible light sensors, and study the communication signal fingerprint of swarm intelligence perception, combined with image matching algorithm. This algorithm mainly communicates with fingerprint data to achieve preliminary positioning, combines a weighted average algorithm of fused images and attitude sensors, and uses swarm intelligence perception to supplement and update positioning data. By adjusting the image matching strategy, while maintaining accuracy, compared to a single image matching positioning algorithm, it reduces computational power requirements and improves real-time performance in battlefield environments with complex communication conditions. Compared with the standard WKNN (Weighted K-Nearest Neighbors) algorithm, it improves the stability of localization in complex environments, and the average localization error is less than 1.72 m, reducing the error by about 50%.
表1 特征数量与图像匹配因子Tab.1 Number of features and image matching factor |
| 名称 | F(DB,i) | Fc | ηi |
|---|---|---|---|
| 样本a | 659 | 647 | 1.888 |
| 样本b | 643 | 563 | 1.664 |
| 样本c | 628 | 489 | 1.6641.464 |
| [1] |
|
| [2] |
乐燕芬, 许远航, 施伟斌. 基于DPC指纹子空间匹配的室内WiFi定位方法[J]. 仪器仪表学报, 2021, 42(11):106-114.
|
| [3] |
聂大惟, 朱海, 吴飞, 等. 基于RSSI概率分布与贝叶斯估计的加权定位方法[J]. 全球定位系统, 2022, 47(2):52-59.
|
| [4] |
|
| [5] |
|
| [6] |
|
| [7] |
刘春燕, 王坚. 基于几何聚类指纹库的约束KNN室内定位模型[J]. 武汉大学学报(信息科学版), 2014, 39(11): 1287-1292.
|
| [8] |
|
| [9] |
|
| [10] |
|
| [11] |
|
| [12] |
常强,
|
| [13] |
|
| [14] |
|
/
| 〈 |
|
〉 |