Unlocking Thermal Aerial Imaging: Synthetic Enhancement of UAV Datasets
This work addresses a domain-specific problem for researchers and practitioners in UAV-based thermal imaging applications like search and rescue, but it is incremental as it builds on existing datasets and methods.
The paper tackles the scarcity of large-scale thermal aerial datasets by introducing a procedural pipeline to generate synthetic thermal images, enhancing existing datasets with new object classes like drones and animals, and shows that thermal detectors outperform visible-light-trained ones in object detection tasks.
Thermal imaging from unmanned aerial vehicles (UAVs) holds significant potential for applications in search and rescue, wildlife monitoring, and emergency response, especially under low-light or obscured conditions. However, the scarcity of large-scale, diverse thermal aerial datasets limits the advancement of deep learning models in this domain, primarily due to the high cost and logistical challenges of collecting thermal data. In this work, we introduce a novel procedural pipeline for generating synthetic thermal images from an aerial perspective. Our method integrates arbitrary object classes into existing thermal backgrounds by providing control over the position, scale, and orientation of the new objects, while aligning them with the viewpoints of the background. We enhance existing thermal datasets by introducing new object categories, specifically adding a drone class in urban environments to the HIT-UAV dataset and an animal category to the MONET dataset. In evaluating these datasets for object detection task, we showcase strong performance across both new and existing classes, validating the successful expansion into new applications. Through comparative analysis, we show that thermal detectors outperform their visible-light-trained counterparts and highlight the importance of replicating aerial viewing angles. Project page: https://github.com/larics/thermal_aerial_synthetic.