Supervised image classification by scattering transform with application to weed detection in culture crops of high density - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Remote Sensing Année : 2019

Supervised image classification by scattering transform with application to weed detection in culture crops of high density

Résumé

In this article, we assess the interest of the recently introduced multiscale scattering transform for texture classification applied for the first time in plant science. Scattering transform is shown to outperform monoscale approaches (gray-level co-occurrence matrix, local binary patterns) but also multiscale approaches (wavelet decomposition) which do not include combinatory steps. The regime in which scatter transform also outperforms a standard CNN architecture in terms of data-set size is evaluated ( 104 instances). An approach on how to optimally design the scatter transform based on energy contrast is provided. This is illustrated on the hard and open problem of weed detection in culture crops of high density from the top view in intensity images. An annotated synthetic data-set available under the form of a data challenge and a simulator are proposed for reproducible science (https://uabox.univ-angers.fr/index.php/s/iuj0knyzOUgsUV9). Scatter transform only trained on synthetic data shows an accuracy of 85% when tested on real data.
Fichier principal
Vignette du fichier
remotesensing-11-00249-v2.pdf (4.37 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02307747 , version 1 (15-02-2023)

Identifiants

Citer

Pejman Rasti, Ali Ahmad, Salma Samiei, Etienne Belin, David Rousseau. Supervised image classification by scattering transform with application to weed detection in culture crops of high density. Remote Sensing, 2019, 11 (3), pp.249. ⟨10.3390/rs11030249⟩. ⟨hal-02307747⟩
54 Consultations
15 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More