Flying Objects Detection from a Single Moving Camera
This addresses the challenge of vision-guided collision avoidance for autonomous systems, though it is incremental as it builds on existing detection techniques with new datasets.
The paper tackled the problem of detecting small flying objects like UAVs and aircraft from a single moving camera against complex backgrounds, achieving state-of-the-art performance by combining appearance and motion cues with a regression-based motion stabilization method.
We propose an approach to detect flying objects such as UAVs and aircrafts when they occupy a small portion of the field of view, possibly moving against complex backgrounds, and are filmed by a camera that itself moves. Solving such a difficult problem requires combining both appearance and motion cues. To this end we propose a regression-based approach to motion stabilization of local image patches that allows us to achieve effective classification on spatio-temporal image cubes and outperform state-of-the-art techniques. As the problem is relatively new, we collected two challenging datasets for UAVs and Aircrafts, which can be used as benchmarks for flying objects detection and vision-guided collision avoidance.