A Novel Approach for Neuromorphic Vision Data Compression based on Deep Belief Network

TL;DR

This paper introduces a deep belief network-based compression method for neuromorphic vision data, significantly reducing data size while preserving quality, and outperforming existing compression techniques.

Contribution

It presents the first deep learning approach using a deep belief network for efficient compression of event-based neuromorphic vision data.

Findings

Achieves higher compression ratios than state-of-the-art methods.

Maintains good reconstruction quality after compression.

Outperforms traditional lossless coding benchmarks.

Abstract

A neuromorphic camera is an image sensor that emulates the human eyes capturing only changes in local brightness levels. They are widely known as event cameras, silicon retinas or dynamic vision sensors (DVS). DVS records asynchronous per-pixel brightness changes, resulting in a stream of events that encode the brightness change's time, location, and polarity. DVS consumes little power and can capture a wider dynamic range with no motion blur and higher temporal resolution than conventional frame-based cameras. Although this method of event capture results in a lower bit rate than traditional video capture, it is further compressible. This paper proposes a novel deep learning-based compression scheme for event data. Using a deep belief network (DBN), the high dimensional event data is reduced into a latent representation and later encoded using an entropy-based coding technique. The proposed scheme is among the first to incorporate deep learning for event compression. It achieves a high compression ratio while maintaining good reconstruction quality outperforming state-of-the-art event data coders and other lossless benchmark techniques.