Using Shape Descriptors for UAV Detection

Eren Unlu (1) , Emmanuel Zenou (1) , Nicolas Rivière (2)

1 DISC - Département d'Ingénierie des Systèmes Complexes
2 ONERA - The French Aerospace Lab [Toulouse]

The rapid development of Unmanned Aerial Vehicle (UAV) technology, -also known as drones- has raised concerns on the safety of critical locations such as governmental buildings, nuclear stations, crowded places etc. Computer vision based approach for detecting these threats seems as a viable solution due to various advantages. We envision an autonomous drone detection and tracking system for the protection of strategic locations. It has been reported numerous times that, one of the main challenges for aerial object recognition with computer vision is discriminating birds from the targets. In this work, we have used 2-dimensional scale, rotation and translation invariant Generic Fourier Descriptor (GFD) features and classified targets as a drone or bird by a neural network. For the training of this system, a large dataset composed of birds and drones is gathered from open sources. We have achieved up to 85.3% overall correct classification rate.

Mots clés: Shape descriptors; Object recognition; Computer vision

Domaines: Optimisation et contrôle [math.OC]

Eren Unlu, Emmanuel Zenou, Nicolas Rivière. Using Shape Descriptors for UAV Detection. Electronic Imaging 2017, Jan 2018, Burlingam, United States. pp. 1-5. ⟨hal-01740282⟩