基于雷达微多普勒角点与动态图学习，提升室内人体活动识别泛化能力
Generalizable Indoor Human Activity Recognition Method Based on Micro-Doppler Corner Point Cloud and Dynamic Graph Learning
- 提取双类型雷达的微多普勒角点，构建三维点云特征
- 通过多项式平滑过滤，最大化运动模型约束下的特征距离
- 采用动态图神经网络实现跨测试者数据的高泛化识别
穿透墙雷达（TWR）可通过融合微多普勒特征提取与智能决策算法实现人体活动识别。然而，在实际室内场景中，由于测试者先验信息不足，基于某一测试者训练的模型在其他测试者上推理性能差，导致泛化能力弱。为此，本文提出一种基于微多普勒角点云与动态图学习的可泛化室内人体活动识别方法。该方法首先利用DoG-μD-CornerDet在两类雷达信号上提取微多普勒角点；随后提出一种基于多项式拟合平滑的角点滤波方法，在运动模型约束下最大化特征距离；将两类雷达的角点拼接为三维点云；最后设计基于动态图神经网络（DGNN）的识别方法，实现从数据到活动标签的映射。通过可视化、对比与消融实验验证，结果表明所提方法在不同测试者采集的数据上均具备强泛化能力。
原文摘要 · Abstract (English)
Through-the-wall radar (TWR) human activity recognition can be achieved by fusing micro-Doppler signature extraction and intelligent decision-making algorithms. However, limited by the insufficient priori of tester in practical indoor scenarios, the trained models on one tester are commonly difficult to inference well on other testers, which causes poor generalization ability. To solve this problem, this paper proposes a generalizable indoor human activity recognition method based on micro-Doppler corner point cloud and dynamic graph learning. In the proposed method, DoG-μD-CornerDet is used for micro-Doppler corner extraction on two types of radar profiles. Then, a micro-Doppler corner filtering method based on polynomial fitting smoothing is proposed to maximize the feature distance under the constraints of the kinematic model. The extracted corners from the two types of radar profiles are concatenated together into three-dimensional point cloud. Finally, the paper proposes a dynamic graph neural network (DGNN)-based recognition method for data-to-activity label mapping. Visualization, comparison and ablation experiments are carried out to verify the effectiveness of the proposed method. The results prove that the proposed method has strong generalization ability on radar data collected from different testers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。