Automotive Object Detection via Learning Sparse Events by Spiking Neurons

arXiv:2307.12900v4 Announce Type: replace
Abstract: Event-based sensors, distinguished by their high temporal resolution of 1 $\mathrm{\mu}\text{s}$ and a dynamic range of 120 $\text{dB}$, stand out as ideal tools for deployment in fast-paced settings like vehicles and drones. Traditional object detection techniques that utilize Artificial Neural Networks (ANNs) face challenges due to the sparse and asynchronous nature of the events these sensors capture. In contrast, Spiking Neural Networks (SNNs) offer a promising alternative, providing a temporal representation that is inherently aligned …

abstract anns artificial artificial neural networks arxiv automotive challenges cs.cv deployment detection drones dynamic event events face networks neural networks neurons object resolution sensors temporal text tools type vehicles via