Spiking Neural Network Enhanced Hand Gesture Recognition Using Low-Cost Single-photon Avalanche Diode Array
This work addresses efficient gesture recognition for low-cost embedded systems, but it is incremental as it adapts existing spiking methods to a specific sensor setup.
The paper tackled hand gesture recognition in varying light conditions using a low-cost SPAD array, achieving 90.8% accuracy with a spiking neural network that reduces computational operations compared to a conventional CNN.
We present a compact spiking convolutional neural network (SCNN) and spiking multilayer perceptron (SMLP) to recognize ten different gestures in dark and bright light environments, using a $9.6 single-photon avalanche diode (SPAD) array. In our hand gesture recognition (HGR) system, photon intensity data was leveraged to train and test the network. A vanilla convolutional neural network (CNN) was also implemented to compare the performance of SCNN with the same network topologies and training strategies. Our SCNN was trained from scratch instead of being converted from the CNN. We tested the three models in dark and ambient light (AL)-corrupted environments. The results indicate that SCNN achieves comparable accuracy (90.8%) to CNN (92.9%) and exhibits lower floating operations with only 8 timesteps. SMLP also presents a trade-off between computational workload and accuracy. The code and collected datasets of this work are available at https://github.com/zzy666666zzy/TinyLiDAR_NET_SNN.