Unlocking Thermal Aerial Imaging: Synthetic Enhancement of UAV Datasets

TL;DR

This paper presents a novel pipeline for generating synthetic thermal aerial images, expanding existing datasets with new object categories, and demonstrating improved object detection performance in thermal UAV imagery.

Contribution

A new procedural method for creating synthetic thermal images with controllable object placement, enhancing datasets with new categories, and validating improved detection results.

Findings

Synthetic data improves detection accuracy.

Thermal detectors outperform visible-light models.

Aerial viewing angles are crucial for detection.

Abstract

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.