A Deep Learning based Framework for UAV Trajectory Pattern Recognition - Archive ouverte HAL Access content directly
Conference Papers Year :

A Deep Learning based Framework for UAV Trajectory Pattern Recognition

Abstract

Recognizing the trajectory patterns of Unmanned Aerial Vehicles (UAV) allows to identify their missions also to detect abnormalities for intelligent supervision. To take advantage of the developments of deep learning on image classification, we proposed a method that converts 3D trajectory data into 2D images and trains a deep network adapted to sketch-like images. We achieved a promising recognition rate of 99.5% on the database of simulated UAV trajectory images.
Fichier principal
Vignette du fichier
56.pdf (1.36 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02395872 , version 1 (05-12-2019)

Identifiers

  • HAL Id : hal-02395872 , version 1

Cite

Xingyu Pan, Pascal Desbarats, Serge Chaumette. A Deep Learning based Framework for UAV Trajectory Pattern Recognition. International Conference on Image Processing Theory, Tool & Applications, Nov 2019, Istanbul, Turkey. ⟨hal-02395872⟩

Collections

CNRS
101 View
393 Download

Share

Gmail Facebook Twitter LinkedIn More