Towards Robust Drone Vision in the Wild
This addresses the problem of domain gaps in drone-based super-resolution for computer vision applications, though it is incremental as it adapts existing methods to a new dataset.
The authors tackled the lack of robust image super-resolution datasets for drone vision by creating the first such dataset with images captured at different altitudes, and proposed two methods (altitude-aware layers and one-shot learning) that efficiently improve super-resolution performance across varying altitudes.
The past few years have witnessed the burst of drone-based applications where computer vision plays an essential role. However, most public drone-based vision datasets focus on detection and tracking. On the other hand, the performance of most existing image super-resolution methods is sensitive to the dataset, specifically, the degradation model between high-resolution and low-resolution images. In this thesis, we propose the first image super-resolution dataset for drone vision. Image pairs are captured by two cameras on the drone with different focal lengths. We collect data at different altitudes and then propose pre-processing steps to align image pairs. Extensive empirical studies show domain gaps exist among images captured at different altitudes. Meanwhile, the performance of pretrained image super-resolution networks also suffers a drop on our dataset and varies among altitudes. Finally, we propose two methods to build a robust image super-resolution network at different altitudes. The first feeds altitude information into the network through altitude-aware layers. The second uses one-shot learning to quickly adapt the super-resolution model to unknown altitudes. Our results reveal that the proposed methods can efficiently improve the performance of super-resolution networks at varying altitudes.