FieldHAR: A Fully Integrated End-to-end RTL Framework for Human Activity Recognition with Neural Networks from Heterogeneous Sensors
Abstract
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.
Dr. Sungho Suh
Senior Researcher
Human Activity Recognition, Safe and Trusted Human Centric Artificial Intelligence in Future Manufacturing Lines
Prof. Dr. rer. nat. Paul (Pawel) Lukowicz
Professor (W3) “Embedded Intelligence”
Paul Lukowicz is Full Professor of AI at the Technical University of Kaiserslautern in Germany where he is heading the Embedded Intelligence group at DFKI. From 2006 till 2011 he has been full Professor (W3) of Computer Science at the University of Passau. He has also been a senior researcher (“Oberassistent”) at the Electronics Laboratory at the Department of Information Technology and Electrical Engineering of ETH Zurich Paul Lukowicz has MSc. (Dipl. Inf.) and a Ph.D. (Dr. rer nat.) in Computer Science a MSc. in Physics (Dipl. Phys.). His research focus are context aware ubiquitous and wearable systems including sensing, pattern recognition, system architectures, models of large scale self-organized systems, and applications. Paul Lukowicz coordinates the FP7-FET SOCIONICAL projects, is Associate Editor in Chief of IEEE Pervasive Computing Magazine, and has been serving as TPC Chair of a number of international events in the area