Towards Long Term SLAM on Thermal Imagery

TL;DR

This paper introduces a SLAM system that uses learned feature descriptors to improve long-term localization in thermal imagery, effectively handling significant diurnal temperature changes and challenging environments.

Contribution

It demonstrates the integration of learned features into classical SLAM, enabling robust relocalization across large thermal appearance variations.

Findings

Improved place recognition across day-night thermal changes

Effective local tracking in challenging thermal environments

Open-source code and datasets provided

Abstract

Visual SLAM with thermal imagery, and other low contrast visually degraded environments such as underwater, or in areas dominated by snow and ice, remain a difficult problem for many state of the art (SOTA) algorithms. In addition to challenging front-end data association, thermal imagery presents an additional difficulty for long term relocalization and map reuse. The relative temperatures of objects in thermal imagery change dramatically from day to night. Feature descriptors typically used for relocalization in SLAM are unable to maintain consistency over these diurnal changes. We show that learned feature descriptors can be used within existing Bag of Word based localization schemes to dramatically improve place recognition across large temporal gaps in thermal imagery. In order to demonstrate the effectiveness of our trained vocabulary, we have developed a baseline SLAM system, integrating learned features and matching into a classical SLAM algorithm. Our system demonstrates good local tracking on challenging thermal imagery, and relocalization that overcomes dramatic day to night thermal appearance changes. Our code and datasets are available here: https://github.com/neufieldrobotics/IRSLAM_Baseline