Using Agents and Unsupervised Learning for Counting Objects in Images with Spatial Organization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Using Agents and Unsupervised Learning for Counting Objects in Images with Spatial Organization

Résumé

This paper addresses the problem of counting objects from aerial images. Classical approaches either consider the task as a regression problem or view it as a recognition problem of the objects in a sliding window over the images, with, in each case, the need of a lot of labeled images and careful adjustments of the parameters of the learning algorithm. Instead of using a supervised learning approach, the proposed method uses unsupervised learning and an agent-based technique which relies on prior detection of the relationships among objects. The method is demonstrated on the problem of counting plants where it achieves state of the art performance when the objects are well separated and tops the best known performances when the objects overlap. The description of the method underlines its generic nature as it could also be used to count objects organized in a geometric pattern, such as spectators in a performance hall.
Fichier principal
Vignette du fichier
ICAART_2021_81(authors)-v1.pdf (5.56 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03650255 , version 1 (24-04-2022)

Identifiants

Citer

Eliott Jacopin, Naomie Berda, Léa Courteille, William Grison, Lucas Mathieu, et al.. Using Agents and Unsupervised Learning for Counting Objects in Images with Spatial Organization. 13th International Conference on Agents and Artificial Intelligence, Feb 2021, Online Streaming, Austria. pp.688-697, ⟨10.5220/0010228706880697⟩. ⟨hal-03650255⟩
68 Consultations
33 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More