TP-TIO: A Robust Thermal-Inertial Odometry with Deep ThermalPoint
Lists
Only you see this
Abstract
To achieve robust motion estimation in visually degraded environments, thermal odometry has been an attraction in the robotics community. However, most thermal odometry methods are purely based on classical feature extractors, which is difficult to establish robust correspondences in successive frames due to sudden photometric changes and large thermal noise. To solve this problem, we propose ThermalPoint, a lightweight feature detection network specifically tailored for producing keypoints on thermal images, providing notable anti-noise improvements compared with other state-of-the-art methods. After that, we combine ThermalPoint with a novel radiometric feature tracking method, which directly makes use of full radiometric data and establishes reliable correspondences between sequential frames. Finally, taking advantage of an optimization-based visual-inertial framework, a deep feature-based thermal-inertial odometry (TP-TIO) framework is proposed and evaluated thoroughly in various visually degraded environments. Experiments show that our method outperforms state-of-the-art visual and laser odometry methods in smoke-filled environments and achieves competitive accuracy in normal environments.
BibTeX
@inproceedings{zhao2020tp,
author = {Shibo Zhao and Peng Wang and Hengrui Zhang and Zheng Fang and Sebastian A. Scherer},
title = {{TP-TIO: A Robust Thermal-Inertial Odometry with Deep ThermalPoint}},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
year = {2020},
url = {https://openreview.net/forum?id=95IMYjCHWQg},
}| Graph-Based Thermal-Inertial SLAM With Probabilistic Neural Networks | arXiv · 2021 |
| Edge-based Monocular Thermal-Inertial Odometry in Visually Degraded Environments | arXiv · 2022 |
| SLAM in the Dark: Self-Supervised Learning of Pose, Depth and Loop-Closure from Thermal Images | arXiv · 2025 |
| Towards Long Term SLAM on Thermal Imagery | arXiv · 2024 |
| Passive Infrared Image Detail Enhancement with Points and Lines for Visual Odometry | Proceedings of the 2018 3rd International Workshop on Materials Engineering and Computer Sciences (iwmecs 2018) · 2018 |
| ThermalLoc: A Vision Transformer-Based Approach for Robust Thermal Camera Relocalization in Large-Scale Environments | arXiv · 2025 |