How Many Events do You Need? Event-based Visual Place Recognition Using Sparse But Varying Pixels

TL;DR

This paper proposes a sparse pixel-based event stream method for visual place recognition using event cameras, enabling efficient and robust localization suitable for energy-constrained robotic platforms.

Contribution

It introduces a novel approach using a small subset of varying pixels' event counts for place recognition, demonstrating efficiency and robustness in diverse scenarios.

Findings

Achieves competitive performance on outdoor and indoor datasets.

Enables frequent, low-cost updates suitable for real-time applications.

Shows robustness to velocity changes and energy efficiency.

Abstract

Event cameras continue to attract interest due to desirable characteristics such as high dynamic range, low latency, virtually no motion blur, and high energy efficiency. One of the potential applications that would benefit from these characteristics lies in visual place recognition for robot localization, i.e. matching a query observation to the corresponding reference place in the database. In this letter, we explore the distinctiveness of event streams from a small subset of pixels (in the tens or hundreds). We demonstrate that the absolute difference in the number of events at those pixel locations accumulated into event frames can be sufficient for the place recognition task, when pixels that display large variations in the reference set are used. Using such sparse (over image coordinates) but varying (variance over the number of events per pixel location) pixels enables frequent and computationally cheap updates of the location estimates. Furthermore, when event frames contain a constant number of events, our method takes full advantage of the event-driven nature of the sensory stream and displays promising robustness to changes in velocity. We evaluate our proposed approach on the Brisbane-Event-VPR dataset in an outdoor driving scenario, as well as the newly contributed indoor QCR-Event-VPR dataset that was captured with a DAVIS346 camera mounted on a mobile robotic platform. Our results show that our approach achieves competitive performance when compared to several baseline methods on those datasets, and is particularly well suited for compute- and energy-constrained platforms such as interplanetary rovers.