Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades

TL;DR

This paper introduces a biologically inspired method to convert static image datasets into neuromorphic datasets using a pan-tilt camera, facilitating direct comparison with traditional computer vision methods.

Contribution

It presents a novel approach for converting existing datasets into neuromorphic formats using sensor movement, and provides benchmark results for spike-based recognition algorithms.

Findings

Converted MNIST and Caltech101 datasets into neuromorphic datasets.

Provided performance metrics for spike-based recognition algorithms on these datasets.

Enabled direct comparison between neuromorphic and traditional computer vision approaches.

Abstract

Creating datasets for Neuromorphic Vision is a challenging task. A lack of available recordings from Neuromorphic Vision sensors means that data must typically be recorded specifically for dataset creation rather than collecting and labelling existing data. The task is further complicated by a desire to simultaneously provide traditional frame-based recordings to allow for direct comparison with traditional Computer Vision algorithms. Here we propose a method for converting existing Computer Vision static image datasets into Neuromorphic Vision datasets using an actuated pan-tilt camera platform. Moving the sensor rather than the scene or image is a more biologically realistic approach to sensing and eliminates timing artifacts introduced by monitor updates when simulating motion on a computer monitor. We present conversion of two popular image datasets (MNIST and Caltech101) which have played important roles in the development of Computer Vision, and we provide performance metrics on these datasets using spike-based recognition algorithms. This work contributes datasets for future use in the field, as well as results from spike-based algorithms against which future works can compare. Furthermore, by converting datasets already popular in Computer Vision, we enable more direct comparison with frame-based approaches.