# Spiking Neural Network based Region Proposal Networks for Neuromorphic Vision Sensors

## TL;DR

This paper introduces a three-layer spiking neural network for region proposal in neuromorphic vision sensors, demonstrating superior recall over existing event-based algorithms with comparable complexity.

## Contribution

It presents a novel bio-inspired spiking neural network architecture tailored for neuromorphic vision data, improving region proposal recall significantly.

## Key findings

- 50% better recall than mean shift algorithm
- Similar computational and memory complexity to existing methods
- Effective on traffic scene recordings from DAVIS sensor

## Abstract

This paper presents a three layer spiking neural network based region proposal network operating on data generated by neuromorphic vision sensors. The proposed architecture consists of refractory, convolution and clustering layers designed with bio-realistic leaky integrate and fire (LIF) neurons and synapses. The proposed algorithm is tested on traffic scene recordings from a DAVIS sensor setup. The performance of the region proposal network has been compared with event based mean shift algorithm and is found to be far superior (~50% better) in recall for similar precision (~85%). Computational and memory complexity of the proposed method are also shown to be similar to that of event based mean shift