A Noise Filter for Dynamic Vision Sensors using Self-adjusting Threshold

TL;DR

This paper introduces GF, a low-overhead noise filter for dynamic vision sensors that uses global space-time info to distinguish real events from background activity, improving clarity and speed.

Contribution

The paper presents a novel global space-time based noise filter for DVS that outperforms existing filters in clarity and computational efficiency.

Findings

GF produces clearer frames than baseline filters.

GF operates with low computational overhead.

Experimental results confirm GF's effectiveness across datasets.

Abstract

Neuromorphic event-based dynamic vision sensors (DVS) have much faster sampling rates and a higher dynamic range than frame-based imagers. However, they are sensitive to background activity (BA) events which are unwanted. we propose a new criterion with little computation overhead for defining real events and BA events by utilizing the global space and time information rather than the local information by Gaussian convolution, which can be also used as a filter. We denote the filter as GF. We demonstrate GF on three datasets, each recorded by a different DVS with different output size. The experimental results show that our filter produces the clearest frames compared with baseline filters and run fast.