RadMamba: Efficient Human Activity Recognition Through a Radar-Based Micro-Doppler-Oriented Mamba State-Space Model

Abstract

Radar-based human activity recognition (RadHAR) is an attractive alternative to wearables and cameras because it preserves privacy, is contactless, and is robust to occlusions. However, dominant convolutional neural network (CNN)- and recurrent neural network (RNN)-based solutions are computationally intensive at deployment, and recent lightweight vision transformer (ViT) and state-space model (SSM) variants still exhibit substantial complexity. In this article, we present RadMamba, a parameter-efficient, micro-Doppler-oriented Mamba SSM tailored to radar HAR under on-sensor compute, latency, and energy constraints typical of distributed radar systems. RadMamba combines 1) channel fusion with downsampling; 2) Doppler-aligned segmentation that preserves the physical continuity of Doppler over time; and 3) convolutional token projections that better capture Doppler-span variations, thereby retaining temporal–Doppler structure while reducing the number of Floating-point Operations/Inference (\# FLOP/Inf.). Evaluated across three datasets with different radars and types of activities, RadMamba matches the prior best 99.8% accuracy of a recent SSM-based model on the continuous wave (CW) radar dataset, while requiring only 1/400 of its parameters. On a dataset of non-continuous activities with frequency-modulated continuous wave (FMCW) radar, RadMamba remains competitive with leading 92.0% results using about 1/10 of the parameters, and on a continuous FMCW radar dataset it surpasses methods with far more parameters by at least 3%, using only 6.7k parameters.