Skip to Main content Skip to Navigation
Theses

Réseaux de neurones convolutionnels profonds pour la détection de petits véhicules en imagerie aérienne

Jean Ogier Du Terrail 1
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : The following manuscript is an attempt to tackle the problem of small vehicles detection in vertical aerial imagery through the use of deep learning algorithms. The specificities of the matter allows the use of innovative techniques leveraging the invariance and self similarities of automobiles/planes vehicles seen from the sky.We will start by a thorough study of single shot detectors. Building on that we will examine the effect of adding multiple stages to the detection decision process. Finally we will try to come to grips with the domain adaptation problem in detection through the generation of better looking synthetic data and its use in the training process of these detectors.
Complete list of metadatas

Cited literature [281 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-02113872
Contributor : Abes Star :  Contact
Submitted on : Monday, April 29, 2019 - 11:23:12 AM
Last modification on : Monday, February 10, 2020 - 4:11:31 PM

File

sygal_fusion_28218-ogier_du_te...
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02113872, version 1

Citation

Jean Ogier Du Terrail. Réseaux de neurones convolutionnels profonds pour la détection de petits véhicules en imagerie aérienne. Réseau de neurones [cs.NE]. Normandie Université, 2018. Français. ⟨NNT : 2018NORMC276⟩. ⟨tel-02113872⟩

Share

Metrics

Record views

498

Files downloads

1092