Small moving target MOT tracking with GM-PHD filter and attention-based CNN - IDEX UCA JEDI Université Côte d'Azur Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Small moving target MOT tracking with GM-PHD filter and attention-based CNN

Résumé

We present a multi-object tracking (MOT) approach to track small moving targets in satellite images. Our objects of interest span few pixels, do not present a defined texture, and are easily lost in cluttered environments. We propose a patchbased convolutional neural network (CNN) that focuses on specific regions to detect and discriminate nearby small objects. We use the object motion information to drive the patch selection and detect objects using a region-based CNN. In addition, we present a direct MOT data-association approach by using an improved Gaussian mixture-probability hypothesis density (GM-PHD) filter. The GM-PHD filter offers an efficient yet robust MOT formulation that takes into account clutter, misdetection, and target appearance and disappearance. We are able to detect and track blob-like moving objects and demonstrate an improvement over competing state-of-the-art tracking approaches.
Fichier principal
Vignette du fichier
MLSP_2021_hal.pdf (4.26 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03351017 , version 1 (22-09-2021)

Identifiants

Citer

Camilo Aguilar, Mathias Ortner, Josiane Zerubia. Small moving target MOT tracking with GM-PHD filter and attention-based CNN. MLSP 2021 - IEEE international workshop on machine learning for signal processing, Oct 2021, Gold Coast / Virtual, Australia. ⟨10.1109/MLSP52302.2021.9596204⟩. ⟨hal-03351017⟩
146 Consultations
218 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More