Scalable Place Recognition Under Appearance Change for Autonomous Driving

TL;DR

This paper introduces a scalable, efficient place recognition method for autonomous driving that adapts to appearance changes over time without increasing computational costs, using a novel Hidden Markov Model-based approach.

Contribution

It presents a new scalable place recognition technique that can be efficiently retrained and compressed, leveraging temporal image matching with Hidden Markov Models.

Findings

Outperforms state-of-the-art techniques in large-scale scenarios

Maintains efficiency despite dataset growth

Effective handling of appearance variations over time

Abstract

A major challenge in place recognition for autonomous driving is to be robust against appearance changes due to short-term (e.g., weather, lighting) and long-term (seasons, vegetation growth, etc.) environmental variations. A promising solution is to continuously accumulate images to maintain an adequate sample of the conditions and incorporate new changes into the place recognition decision. However, this demands a place recognition technique that is scalable on an ever growing dataset. To this end, we propose a novel place recognition technique that can be efficiently retrained and compressed, such that the recognition of new queries can exploit all available data (including recent changes) without suffering from visible growth in computational cost. Underpinning our method is a novel temporal image matching technique based on Hidden Markov Models. Our experiments show that, compared to state-of-the-art techniques, our method has much greater potential for large-scale place recognition for autonomous driving.