Condition-Invariant and Compact Visual Place Description by Convolutional Autoencoder

TL;DR

This paper introduces a convolutional autoencoder-based approach to generate low-dimensional, condition-invariant visual place descriptors, improving efficiency and robustness in environments with significant appearance changes.

Contribution

The authors propose a novel CAE-based method that reduces descriptor dimension and enhances condition invariance, outperforming existing CNN-based descriptors in challenging scenarios.

Findings

Outperforms state-of-the-art in challenging datasets

Produces low-dimensional, condition-invariant descriptors

Demonstrates robustness to illumination changes

Abstract

Visual place recognition (VPR) in condition-varying environments is still an open problem. Popular solutions are CNN-based image descriptors, which have been shown to outperform traditional image descriptors based on hand-crafted visual features. However, there are two drawbacks of current CNN-based descriptors: a) their high dimension and b) lack of generalization, leading to low efficiency and poor performance in applications. In this paper, we propose to use a convolutional autoencoder (CAE) to tackle this problem. We employ a high-level layer of a pre-trained CNN to generate features, and train a CAE to map the features to a low-dimensional space to improve the condition invariance property of the descriptor and reduce its dimension at the same time. We verify our method in three challenging datasets involving significant illumination changes, and our method is shown to be superior to the state-of-the-art. For the benefit of the community, we make public the source code.