2019 · 14 citations · 11 references
ComputingComputer EngineeringComputer ScienceEmbedded SystemsLow-power DesignMachine LearningDeep LearningGesture AnalysisGesture RecognitionGesture-based InteractionMultimodal InteractionPattern RecognitionConvolutional Neural NetworksHand GesturesLow-power Processor DesignLow-power SensorsPower ConsumptionSensor-based Gesture RecognitionSequence PredictionTemporal Convolutional Networks
This work proposes a low-power high-accuracy embedded hand-gesture recognition using low power short-range radar sensors. The hardware and software match the requirements for battery-operated wearable devices. 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 45723 parameters, yielding a memory footprint of only 91kB. Two datasets containing 11 challenging hand gestures performed by 26 different people have been recorded containing a total of 20210 gesture instances. On the 11 hands, gestures and an accuracy of 87% (26 users) and 92% (single user) have been achieved. Furthermore, the prediction algorithm has been implemented in the GAP8 Parallel Ultra-Low-Power processor by GreenWaves Technologies, showing that live-prediction is feasible with only 21mW of power consumption for the full gesture prediction neural network.
11
Jaime Lien, Nicholas Gillian, Mustafa Emre Karagozler et al. · ACM Transactions on Graphics · 2016 · 938 citations
Saiwen Wang, Jie Song, Jaime Lien et al. · 2016 · 432 citations · Full text
Yang Zhang, Chris Harrison · 2015 · 282 citations
Engineering, Biomedical Engineering, Electrical Engineering +17
Artem Dementyev, Joseph A. Paradiso · 2014 · 202 citations · Full text
Engineering, Mechatronics Engineering, Assistive Technology +16