Season-invariant GNSS-denied visual localization for UAVs
This addresses the critical need for reliable autonomous UAV operations in environments with seasonal changes and perspective discrepancies, representing a strong domain-specific advancement.
The paper tackles the problem of GNSS-denied visual localization for UAVs by proposing a convolutional neural network model that matches UAV camera images to georeferenced orthophotos, achieving major improvements in convergence speed and localization accuracy compared to six reference methods, especially under high seasonal variation.
Localization without Global Navigation Satellite Systems (GNSS) is a critical functionality in autonomous operations of unmanned aerial vehicles (UAVs). Vision-based localization on a known map can be an effective solution, but it is burdened by two main problems: places have different appearance depending on weather and season, and the perspective discrepancy between the UAV camera image and the map make matching hard. In this work, we propose a localization solution relying on matching of UAV camera images to georeferenced orthophotos with a trained convolutional neural network model that is invariant to significant seasonal appearance difference (winter-summer) between the camera image and map. We compare the convergence speed and localization accuracy of our solution to six reference methods. The results show major improvements with respect to reference methods, especially under high seasonal variation. We finally demonstrate the ability of the method to successfully localize a real UAV, showing that the proposed method is robust to perspective changes.