Spike-EVPR: Deep Spiking Residual Network with Cross-Representation Aggregation for Event-Based Visual Place Recognition

arXiv:2402.10476v1 Announce Type: new
Abstract: Event cameras have been successfully applied to visual place recognition (VPR) tasks by using deep artificial neural networks (ANNs) in recent years. However, previously proposed deep ANN architectures are often unable to harness the abundant temporal information presented in event streams. In contrast, deep spiking networks exhibit more intricate spatiotemporal dynamics and are inherently well-suited to process sparse asynchronous event streams. Unfortunately, directly inputting temporal-dense event volumes into the spiking network introduces excessive time steps, …

abstract aggregation ann anns architectures artificial artificial neural networks arxiv cameras cs.cv event harness information network networks neural networks recognition representation residual tasks temporal type visual