Flying Objects Detection from a Single Moving Camera

TL;DR

This paper introduces a novel method for detecting small flying objects like UAVs and aircrafts from a moving camera by combining appearance and motion cues, and provides new datasets for benchmarking.

Contribution

It presents a regression-based motion stabilization technique and new challenging datasets for flying object detection in complex, real-world scenarios.

Findings

Outperforms state-of-the-art techniques in detection accuracy

Effective classification on spatio-temporal image cubes

Provides benchmark datasets for UAVs and aircrafts detection

Abstract

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.