Spike-TBR: a Noise Resilient Neuromorphic Event Representation
This work addresses noise resilience in event-driven vision applications, offering a solution for domains like robotics or autonomous systems, but it appears incremental as it builds on existing TBR and spiking neuron methods.
The paper tackles the problem of efficiently converting noisy event camera streams into formats compatible with computer vision pipelines by proposing Spike-TBR, a novel encoding strategy that integrates spiking neurons with Temporal Binary Representation, resulting in superior performance in noise-affected scenarios and improvements on clean data across multiple datasets.
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.