Object detection in remote sensing images with center only - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Object detection in remote sensing images with center only

Résumé

There are a lot of works aiming to reduce the need of human annotations for object detection: self supervised training, interactive verification instead of annotation or weakly supervised training. For example, only pointing object centres is a faster to annotate but weaker ground truth than providing bounding boxes or detailed segmentation mask. Although not usable for large areas such as roads, vegetation and buildings, centers can be used to learn adequate detectors and segmentors. We perform a comparative analysis on four public remote sensing datasets on the task of vehicle detection and show that centre annotations is a competitive baseline compared to other more sophisticated annotations.
Fichier principal
Vignette du fichier
raw.pdf (1004.04 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01412086 , version 1 (07-12-2016)
hal-01412086 , version 2 (17-07-2017)
hal-01412086 , version 3 (31-07-2017)
hal-01412086 , version 4 (18-10-2017)
hal-01412086 , version 5 (14-12-2017)
hal-01412086 , version 6 (15-12-2017)

Identifiants

Citer

Adrien Chan-Hon-Tong, Nicolas Audebert. Object detection in remote sensing images with center only. IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018, Valence, Spain. ⟨10.1109/IGARSS.2018.8517860⟩. ⟨hal-01412086v6⟩
294 Consultations
395 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More