火力与指挥控制2026，Vol.51Issue(5)：50-58,9.DOI:10.3969/j.issn.1002-0640.2026.05.007
基于多尺度特征注意力机制的轻量化室内定位模型
Lightweight Indoor Localization Model Based on Multi-scale Feature Attention Mechanism
摘要
Abstract
To address the issues of narrow receptive fields and insufficient global feature learning in existing indoor localization models,this paper proposes a lightweight multi-scale feature fusion indoor localization model,MLGNet.A multi-scale feature pyramid module is designed,which employs multi-branch dilated convolution and asymmetric convolution to expand the model's receptive fields.Meanwhile,a kernel function-enhanced self-attention module and a dynamic aggregation channel attention module are constructed to achieve efficient feature extraction in both global and channel dimensions.Finally,a multi-stage feature fusion strategy is adopted to integrate local and global features step by step.Compared with existing models,MLGNet exhibits more than 15%localization accuracy improvement on the CTW and KU Leuven datasets.The number of model parameters is only 2.58 M.关键词
室内定位/特征提取/多尺度特征/注意力机制/信道状态信息Key words
indoor localization/feature extraction/multi-scale features/attention mechanism/chan-nel state information分类
信息技术与安全科学引用本文复制引用
王乐,徐兵,刘鹏,孙雪非,禹明刚..基于多尺度特征注意力机制的轻量化室内定位模型[J].火力与指挥控制,2026,51(5):50-58,9.基金项目
国家自然科学基金面上资助项目(72471240) （72471240）
