In this work, we propose an open-source scalable end-to-end RTL framework FieldHAR, for complex human activity recognition (HAR) from heterogeneous sensors using artificial neural networks (ANN) optimized for FPGA or ASIC integration. FieldHAR aims to address the lack of apparatus to transform complex HAR methodologies often limited to offline evaluation to efficient run-time edge applications. The framework uses parallel sensor interfaces and integer-based multi-branch convolutional neural networks (CNNs) to support flexible modality extensions with synchronous sampling at the maximum rate of each sensor. To validate the framework, we used a sensor-rich kitchen scenario HAR application which was demonstrated in a previous offline study. Through resource-aware optimizations, with FieldHAR the entire RTL solution was created from data acquisition to ANN inference taking as low as 25\% logic elements and 2\% memory bits of a low-end Cyclone IV FPGA and less than 1\% accuracy loss from the original FP32 precision offline study. The RTL implementation also shows advantages over MCU-based solutions, including superior data acquisition performance and virtually eliminating ANN inference bottleneck.

翻译：本文提出了一种开源可扩展的端到端RTL框架FieldHAR，该框架利用针对FPGA或ASIC集成优化的人工神经网络（ANN），实现对异构传感器采集的复杂人体活动进行识别。FieldHAR旨在解决现有设备缺乏将复杂HAR方法（通常局限于离线评估）转化为高效运行时边缘应用的能力。该框架采用并行传感器接口和基于整数的多分支卷积神经网络（CNN），支持以各传感器最大速率进行同步采样的灵活模态扩展。为验证该框架，我们应用了先前离线研究中演示的富含传感器的厨房场景HAR应用。通过资源感知优化，FieldHAR从数据采集到ANN推理的完整RTL解决方案，仅消耗低端Cyclone IV FPGA 25%的逻辑单元和2%的存储位，且相较原始FP32精度离线研究的准确率损失低于1%。该RTL实现相比基于MCU的方案也显示出优势，包括更优的数据采集性能及几乎消除ANN推理瓶颈。