Condition-Invariant Multi-View Place Recognition

TL;DR

This paper introduces three novel deep network approaches that leverage temporal sequence information to improve visual place recognition under appearance changes, achieving more compact and accurate descriptors.

Contribution

It proposes Descriptor Grouping, Fusion, and Recurrent Descriptors methods to enhance deep networks for sequence-based place recognition, outperforming existing baselines.

Findings

More compact descriptors than baselines

Higher recognition accuracy in public databases

Effective handling of appearance variations

Abstract

Visual place recognition is particularly challenging when places suffer changes in its appearance. Such changes are indeed common, e.g., due to weather, night/day or seasons. In this paper we leverage on recent research using deep networks, and explore how they can be improved by exploiting the temporal sequence information. Specifically, we propose 3 different alternatives (Descriptor Grouping, Fusion and Recurrent Descriptors) for deep networks to use several frames of a sequence. We show that our approaches produce more compact and best performing descriptors than single- and multi-view baselines in the literature in two public databases.