EvSegSNN: Neuromorphic Semantic Segmentation for Event Data

arXiv:2406.14178v1 Announce Type: new
Abstract: Semantic segmentation is an important computer vision task, particularly for scene understanding and navigation of autonomous vehicles and UAVs. Several variations of deep neural network architectures have been designed to tackle this task. However, due to their huge computational costs and their high memory consumption, these models are not meant to be deployed on resource-constrained systems. To address this limitation, we introduce an end-to-end biologically inspired semantic segmentation approach by combining Spiking Neural Networks (SNNs, …

abstract architectures arxiv autonomous autonomous vehicles computational computer computer vision consumption costs cs.cv data deep neural network event however important memory memory consumption navigation network neural network neuromorphic segmentation semantic type understanding vehicles vision