High Speed Event Camera TRacking

TL;DR

This paper introduces an ultra-fast event camera tracking algorithm capable of estimating six-degree-of-freedom motion at over 10 kHz, handling over a million events per second for highly dynamic applications.

Contribution

It presents a novel real-time tracking method using an error-state Kalman filter with Lie-theoretic formulation, robust event-line matching, and optimized sparse matrix computations.

Findings

Achieves 10 kHz processing throughput

Handles over a million events per second

Estimates high-dynamics motion over 25.8 g

Abstract

Event cameras are bioinspired sensors with reaction times in the order of microseconds. This property makes them appealing for use in highly-dynamic computer vision applications. In this work,we explore the limits of this sensing technology and present an ultra-fast tracking algorithm able to estimate six-degree-of-freedom motion with dynamics over 25.8 g, at a throughput of 10 kHz,processing over a million events per second. Our method is capable of tracking either camera motion or the motion of an object in front of it, using an error-state Kalman filter formulated in a Lie-theoretic sense. The method includes a robust mechanism for the matching of events with projected line segments with very fast outlier rejection. Meticulous treatment of sparse matrices is applied to achieve real-time performance. Different motion models of varying complexity are considered for the sake of comparison and performance analysis