ThermalLoc: A Vision Transformer-Based Approach for Robust Thermal Camera Relocalization in Large-Scale Environments
This work addresses thermal camera relocalization for large-scale environments, an underexplored area, but it is incremental as it adapts existing deep learning techniques to a specific domain.
The paper tackled the problem of thermal camera relocalization, where traditional methods for visible light images are not applicable, by introducing ThermalLoc, a vision transformer-based approach that outperformed existing methods like AtLoc and PoseNet in accuracy and robustness on thermal datasets.
Thermal cameras capture environmental data through heat emission, a fundamentally different mechanism compared to visible light cameras, which rely on pinhole imaging. As a result, traditional visual relocalization methods designed for visible light images are not directly applicable to thermal images. Despite significant advancements in deep learning for camera relocalization, approaches specifically tailored for thermal camera-based relocalization remain underexplored. To address this gap, we introduce ThermalLoc, a novel end-to-end deep learning method for thermal image relocalization. ThermalLoc effectively extracts both local and global features from thermal images by integrating EfficientNet with Transformers, and performs absolute pose regression using two MLP networks. We evaluated ThermalLoc on both the publicly available thermal-odometry dataset and our own dataset. The results demonstrate that ThermalLoc outperforms existing representative methods employed for thermal camera relocalization, including AtLoc, MapNet, PoseNet, and RobustLoc, achieving superior accuracy and robustness.