轻量级雷达人体动作识别模型，可在边缘设备实时运行。
Neural-HAR: A Dimension-Gated CNN Accelerator for Real-Time Radar Human Activity Recognition
- 用门控卷积融合多普勒与时间特征，降低参数和计算量。
- 仅2.7千参数、0.28兆浮点运算，准确率达86.4%。
- 适配资源受限边缘设备，适合隐私敏感的实时监控场景。
基于雷达的人体活动识别（HAR）具有无感监测和保护隐私的优势，但多数CNN/RNN模型计算复杂度高，难以部署于边缘设备；即使轻量级ViT/SSM也常超出实际算力与内存预算。本文提出Neural-HAR，一种面向资源受限平台的维度门控CNN加速器。核心为GateCNN，一种参数高效的多普勒-时序网络：(i) 将多普勒向量嵌入以突出频率随时间演化特性；(ii) 采用双路径门控卷积，用时间门控调制多普勒感知特征，并辅以残差路径保证训练稳定。在格拉斯哥大学UoG2020连续雷达数据集上，GateCNN实现86.4%准确率，单次推理仅需2.7k参数与0.28M FLOPs，性能接近CNN-BiGRU但复杂度大幅降低。基于Xilinx Zynq-7000 Z-7007S的FPGA原型仅使用查找表和分布式内存（无DSP/BRAM），达到107.5 μs延迟与15 mW动态功耗，实现真正的实时、低功耗边缘推理。代码与HLS转换脚本见https://github.com/lab-emi/AIRHAR。
原文摘要 · Abstract (English)
Radar-based human activity recognition (HAR) is attractive for unobtrusive and privacy-preserving monitoring, yet many CNN/RNN solutions remain too heavy for edge deployment, and even lightweight ViT/SSM variants often exceed practical compute and memory budgets. We introduce Neural-HAR, a dimension-gated CNN accelerator tailored for real-time radar HAR on resource-constrained platforms. At its core is GateCNN, a parameter-efficient Doppler-temporal network that (i) embeds Doppler vectors to emphasize frequency evolution over time and (ii) applies dual-path gated convolutions that modulate Doppler-aware content features with temporal gates, complemented by a residual path for stable training. On the University of Glasgow UoG2020 continuous radar dataset, GateCNN attains 86.4% accuracy with only 2.7k parameters and 0.28M FLOPs per inference, comparable to CNN-BiGRU at a fraction of the complexity. Our FPGA prototype on Xilinx Zynq-7000 Z-7007S reaches 107.5 $μ$s latency and 15 mW dynamic power using LUT-based ROM and distributed RAM only (zero DSP/BRAM), demonstrating real-time, energy-efficient edge inference. Code and HLS conversion scripts are available at https://github.com/lab-emi/AIRHAR.
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。