Fast Event-based Double Integral for Real-time Robotics

TL;DR

This paper introduces a fast implementation of the event-based double integral (EDI) method that enables real-time motion deblurring on standard CPUs, significantly improving the applicability of event cameras in robotics.

Contribution

The paper presents a novel, efficient real-time version of EDI that supports high event rates and is suitable for practical robotics applications, unlike the original offline method.

Findings

Handles event rates up to 13 million per second

Enables real-time applications like localization and feature matching

Operates efficiently on single-core CPU devices

Abstract

Motion deblurring is a critical ill-posed problem that is important in many vision-based robotics applications. The recently proposed event-based double integral (EDI) provides a theoretical framework for solving the deblurring problem with the event camera and generating clear images at high frame-rate. However, the original EDI is mainly designed for offline computation and does not support real-time requirement in many robotics applications. In this paper, we propose the fast EDI, an efficient implementation of EDI that can achieve real-time online computation on single-core CPU devices, which is common for physical robotic platforms used in practice. In experiments, our method can handle event rates at as high as 13 million event per second in a wide variety of challenging lighting conditions. We demonstrate the benefit on multiple downstream real-time applications, including localization, visual tag detection, and feature matching.