# TinyRadarNN: Combining Spatial and Temporal Convolutional Neural Networks for Embedded Gesture Recognition with Short Range Radars

arXiv: https://arxiv.org/abs/2006.16281 · HTML: https://mlsanity.com/paper/2006.16281/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

## Built on by (most cited first, 12 of 12)

- [Multi-View Radar Semantic Segmentation](https://mlsanity.com/paper/2103.16214/) (2021)
- [Towards Domain-Independent and Real-Time Gesture Recognition Using mmWave Signal](https://mlsanity.com/paper/2111.06195/) (2021)
- [CubeLearn: End-to-end Learning for Human Motion Recognition from Raw mmWave Radar Signals](https://mlsanity.com/paper/2111.03976/) (2021)
- [TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers](https://mlsanity.com/paper/2306.00001/) (2023)
- [TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision In-Sensor for Gaze Estimation](https://mlsanity.com/paper/2307.07813/) (2023)
- [TinyML Platforms Benchmarking](https://mlsanity.com/paper/2112.01319/) (2021)
- [Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing](https://mlsanity.com/paper/2309.05686/) (2023)
- [Deep learning for radar data exploitation of autonomous vehicle](https://mlsanity.com/paper/2203.08038/) (2022)
- [A Lightweight 3D-CNN for Event-Based Human Action Recognition with Privacy-Preserving Potential](https://mlsanity.com/paper/2511.03665/) (2025)
- [Resonate-and-Fire Spiking Neurons for Target Detection and Hand Gesture Recognition: A Hybrid Approach](https://mlsanity.com/paper/2405.19351/) (2024)
- [Advanced Acceptance Score: A Holistic Measure for Biometric Quantification](https://mlsanity.com/paper/2602.15535/) (2026)
- [One Residual with Three Reuses: A Wristband Front End for Gesture Sensing](https://mlsanity.com/paper/2608.16542/) (2026)

## Abstract (arXiv)

This work proposes a low-power high-accuracy embedded hand-gesture recognition algorithm targeting battery-operated wearable devices using low power short-range RADAR sensors. A 2D Convolutional Neural Network (CNN) using range frequency Doppler features is combined with a Temporal Convolutional Neural Network (TCN) for time sequence prediction. The final algorithm has a model size of only 46 thousand parameters, yielding a memory footprint of only 92 KB. Two datasets containing 11 challenging hand gestures performed by 26 different people have been recorded containing a total of 20,210 gesture instances. On the 11 hand gesture dataset, accuracies of 86.6% (26 users) and 92.4% (single user) have been achieved, which are comparable to the state-of-the-art, which achieves 87% (10 users) and 94% (single user), while using a TCN-based network that is 7500x smaller than the state-of-the-art. Furthermore, the gesture recognition classifier has been implemented on a Parallel Ultra-Low Power Processor, demonstrating that real-time prediction is feasible with only 21 mW of power consumption for the full TCN sequence prediction network, while a system-level power consumption of less than 100 mW is achieved. We provide open-source access to all the code and data collected and used in this work on tinyradar.ethz.ch.