Spiking Neural Network Enhanced Hand Gesture Recognition Using Low-Cost Single-photon Avalanche Diode Array
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910322543034368 |
|---|---|
| author | Zang, Zhenya Li, Xingda Li, David Day Uei |
| author_facet | Zang, Zhenya Li, Xingda Li, David Day Uei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05441 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Spiking Neural Network Enhanced Hand Gesture Recognition Using Low-Cost Single-photon Avalanche Diode Array Zang, Zhenya Li, Xingda Li, David Day Uei Computer Vision and Pattern Recognition Image and Video Processing 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. |
| title | Spiking Neural Network Enhanced Hand Gesture Recognition Using Low-Cost Single-photon Avalanche Diode Array |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2402.05441 |