The advent of affordable drones capable of taking high resolution images of agricultural fields creates new challenges and opportunities in aerial scene understanding. This paper tackles the problem of recognizing crop types from aerial imagery and proposes a new hybrid neural network architecture which combines histograms and convolutional units. We evaluate the performance of the proposed model on a 23-class classification task and compare it to other models. The result is an improvement of the classification performance.
Détails
Titre
Augmenting a convolutional neural network with local histograms : a case study in crop classification from high-resolution UAV imagery
Auteur(s)/ trice(s)
Rebetez, Julien (School of Engineering and Management Vaud, HES-SO, University of Applied Sciences and Arts Western Switzerland) Satizábal, Héctor F. (School of Engineering and Management Vaud, HES-SO, University of Applied Sciences and Arts Western Switzerland) Mota, Matteo (School of Viticulture and Enology, HES-SO University of Applied Sciences Western Switzerland) Noll, Dorothea (School of Viticulture and Enology, HES-SO University of Applied Sciences Western Switzerland) Büchi, Lucie (Agroscope, Institut for Plant Production Sciences, Nyon, Switzerland) Wendling, Marina (Agroscope, Institut for Plant Production Sciences, Nyon, Switzerland) Cannelle, Bertrand (School of Engineering and Management Vaud, HES-SO, University of Applied Sciences and Arts Western Switzerland) Perez-Uribe, Andres (School of Engineering and Management Vaud, HES-SO, University of Applied Sciences and Arts Western Switzerland) Burgos, Stéphane (Bern University of Applied Sciences, School of Agricultural, Forest and Food Sciences HAFL, Zollikofen, Switzerland)
Date
2016-04
Publié dans
Proceedings of ESANN 2016, European Symposium on artifical neural networks, Computational Intelligence and Machine Learning, 27-29 April 2016, Bruges, Belgium
Volume
2016, Article no. ES2016-74, pp. 515-520
Editeur
Bruges, Belgium, 27-29 April 2016
Pagination
6 p.
Présenté à
European Symposium on Artificial Neural Networks (ESANN), Bruges, Belgium, 2016-04-27, 2016-04-29
Type de papier
full paper
Domaine
Ingénierie et Architecture
Ecole
HEIG-VD Changins
Institut
IICT - Institut des Technologies de l'Information et de la Communication insit - Institut d’ingénierie du territoire