Learning Point Processes and Convolutional Neural Networks for Object Detection in Satellite Images - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Remote Sensing Année : 2024

Learning Point Processes and Convolutional Neural Networks for Object Detection in Satellite Images

Résumé

Convolutional neural networks (CNN) have shown great results for object-detection tasks by learning texture and pattern-extraction filters. However, object-level interactions are harder to grasp without increasing the complexity of the architectures. On the other hand, Point Process models propose to solve the detection of the configuration of objects as a whole, allowing the factoring in of the image data and the objects' prior interactions. In this paper, we propose combining the information extracted by a CNN with priors on objects within a Markov Marked Point Process framework. We also propose a method to learn the parameters of this Energy-Based Model. We apply this model to the detection of small vehicles in optical satellite imagery, where the image information needs to be complemented with object interaction priors because of noise and small object sizes.
Fichier principal
Vignette du fichier
remotesensing-2876874-english.pdf (11.31 Mo) Télécharger le fichier
graphical_abstract.pdf (1001.7 Ko) Télécharger le fichier
Origine : Publication financée par une institution
Licence : CC BY - Paternité
Licence : CC BY - Paternité

Dates et versions

hal-04250540 , version 1 (19-10-2023)
hal-04250540 , version 2 (14-03-2024)

Licence

Paternité

Identifiants

Citer

Jules Mabon, Mathias Ortner, Josiane Zerubia. Learning Point Processes and Convolutional Neural Networks for Object Detection in Satellite Images. Remote Sensing, 2024, 16 (6), ⟨10.3390/rs16061019⟩. ⟨hal-04250540v2⟩
77 Consultations
11 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More