Thermal Image Refinement with Depth Estimation using Recurrent Networks for Monocular ORB-SLAM3

2026-03-16

AI Summary

This work addresses the challenge of enabling monocular thermal-inertial SLAM for unmanned aerial vehicles in GPS-denied and visually degraded environments. To this end, the authors propose a lightweight supervised depth estimation network that integrates a recurrent module with a Temporal Refinement Network (T-RefNet) to extract temporally consistent depth cues from non-radiometric thermal imagery. The estimated depth is seamlessly incorporated into the ORB-SLAM3 framework. This approach achieves high-precision depth estimation and localization using only non-radiometric thermal data, eliminating the need for costly radiometric thermal cameras. Experimental results demonstrate an absolute relative depth error of 0.06 on the VIVID++ dataset and below 0.10 on a newly collected indoor non-radiometric thermal dataset, with SLAM trajectory errors consistently under 0.4 meters.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Autonomous navigation in GPS-denied and visually degraded environments remains challenging for unmanned aerial vehicles (UAVs). To this end, we investigate the use of a monocular thermal camera as a standalone sensor on a UAV platform for real-time depth estimation and simultaneous localization and mapping (SLAM). To extract depth information from thermal images, we propose a novel pipeline employing a lightweight supervised network with recurrent blocks (RBs) integrated to capture temporal dependencies, enabling more robust predictions. The network combines lightweight convolutional backbones with a thermal refinement network (T-RefNet) to refine raw thermal inputs and enhance feature visibility. The refined thermal images and predicted depth maps are integrated into ORB-SLAM3, enabling thermal-only localization. Unlike previous methods, the network is trained on a custom non-radiometric dataset, obviating the need for high-cost radiometric thermal cameras. Experimental results on datasets and UAV flights demonstrate competitive depth accuracy and robust SLAM performance under low-light conditions. On the radiometric VIVID++ (indoor-dark) dataset, our method achieves an absolute relative error of approximately 0.06, compared to baselines exceeding 0.11. In our non-radiometric indoor set, baseline errors remain above 0.24, whereas our approach remains below 0.10. Thermal-only ORB-SLAM3 maintains a mean trajectory error under 0.4 m.

Problem

• thermal imaging
• depth estimation
• monocular SLAM
• UAV navigation
• GPS-denied environments

Innovation

• Thermal SLAM
• Depth Estimation
• Recurrent Networks
• Non-radiometric Thermal Imaging
• ORB-SLAM3