Spike-TBR: a Noise Resilient Neuromorphic Event Representation

TL;DR

Spike-TBR introduces a noise-resilient event encoding method that combines temporal binary representation with spiking neural networks, enhancing robustness in event-based vision systems.

Contribution

It proposes a novel encoding strategy integrating TBR with spiking neurons to improve noise robustness in event stream processing.

Findings

Superior noise robustness across datasets

Improved performance on clean data

Effective noise filtering with spiking neurons

Abstract

Event cameras offer significant advantages over traditional frame-based sensors, including higher temporal resolution, lower latency and dynamic range. However, efficiently converting event streams into formats compatible with standard computer vision pipelines remains a challenging problem, particularly in the presence of noise. In this paper, we propose Spike-TBR, a novel event-based encoding strategy based on Temporal Binary Representation (TBR), addressing its vulnerability to noise by integrating spiking neurons. Spike-TBR combines the frame-based advantages of TBR with the noise-filtering capabilities of spiking neural networks, creating a more robust representation of event streams. We evaluate four variants of Spike-TBR, each using different spiking neurons, across multiple datasets, demonstrating superior performance in noise-affected scenarios while improving the results on clean data. Our method bridges the gap between spike-based and frame-based processing, offering a simple noise-resilient solution for event-driven vision applications.