Learning point process models for vehicles detection using CNNs in satellite images - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Learning point process models for vehicles detection using CNNs in satellite images

Résumé

We present a method combining marked point processes and convolutional neural networks applied to the detection of small objects in optical satellite images. In such images, objects are densely scattered, and visual information is scarce. The point process framework allows factoring in priors to account for object interactions. Classical point process approaches make use of contrast measures to account for object location. These fail when contrast is low and visual aspect is varied. We replace those with terms build from convolutional neural network outputs. Moreover, we propose a method to learn the parameters of the point process energy model. We show our approach improves results from the straight convolutional neural network outputs. The code will be available at github.com/Ayana-Inria/
Fichier principal
Vignette du fichier
sitis_mabon_191023.pdf (11.25 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04250535 , version 1 (19-10-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04250535 , version 1

Citer

Jules Mabon, Mathias Ortner, Josiane Zerubia. Learning point process models for vehicles detection using CNNs in satellite images. SITIS 2023 - 17th International Conference on Signal-Image Technology &Internet-Based Systems, Nov 2023, Bangkok, Thailand. ⟨hal-04250535⟩
81 Consultations
6 Téléchargements

Partager

Gmail Facebook X LinkedIn More