ThermalLoc: A Vision Transformer-Based Approach for Robust Thermal Camera Relocalization in Large-Scale Environments

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.

Authors

• Yu Liu
• Yangtao Meng
• Xianfei Pan
• Jie Jiang
• Changhao Chen

Keywords

• Deep learning
• Visualization
• Urban areas
• Robot vision systems
• Lighting
• Cameras
• Transformers
• Feature extraction
• Robustness
• Resilience
• Infrared Imaging
• Large-scale Environments
• Camera Relocalization
• Local Features
• Global Features
• Multilayer Perceptron
• Advances In Deep Learning
• Multilayer Perceptron Network
• Light Conditions
• Feature Maps
• Dynamic Conditions
• Localization Accuracy
• Singular Value Decomposition
• Linear Transformation
• Transformer Model
• Pose Estimation
• L1 Loss
• Self-attention Mechanism
• Camera Pose
• Transformation Module
• Vision Transformer
• Brightness Adjustment
• Neural Architecture Search
• Unit Quaternion
• Gaussian Low-pass Filter
• Values Of S1
• Contrast Adjustment
• Camera Pose Estimation
• Grayscale Value