Crop detection from remote sensed images is of major interest for land use and land cover mapping. Classification techniques often require multi-temporal images. However, most of these techniques assume that the cultural cycle occurs at the same dates across plots or for a given crop and do not take into account the sensitivity to initial conditions of the dynamical behaviors. Such hypotheses are not well adapted when a wide diversity of practices is observed for the same crops from one crop field to another, which is often the case in tropical context. To cope with these difficulties, a new classification technique based on the global modeling technique is introduced in this paper. It is first applied to a case study based on chaotic oscillators. It is then tested on crop classification observed from satellite data. The Berambadi watershed (South India) is taken as a case study to test this new classification approach. Crop classification is a difficult problem in Southern India where optical satellite images are scarce during the monsoon season due to cloud cover, and where crop land is divided in parcels (i.e. crop fields) of very small sizes with diversified crops. The Landsat-8 images were used to monitor an ensemble of 104 parcels of ten different crops (irrigated and non-irrigated). Using global modeling, a bank of crop models was first obtained for the ten crops considered in the study. A metric is introduced to compare the observed signal to the obtained crop-models used as reference for each crop dynamic. Based on this metric, the possibility to use global models as references for distinguishing crops is investigated. The results provide a good proof-of-concept and show promising potential for crop classification.
Can the global modeling technique be used for crop classification?
Résumé
en
Crop detection from remote sensed images is of major interest for land use and land cover mapping. Classification techniques often require multi-temporal images. However, most of these techniques assume that the cultural cycle occurs at the same dates across plots or for a given crop and do not take into account the sensitivity to initial conditions of the dynamical behaviors. Such hypotheses are not well adapted when a wide diversity of practices is observed for the same crops from one crop field to another, which is often the case in tropical context. To cope with these difficulties, a new classification technique based on the global modeling technique is introduced in this paper. It is first applied to a case study based on chaotic oscillators. It is then tested on crop classification observed from satellite data. The Berambadi watershed (South India) is taken as a case study to test this new classification approach. Crop classification is a difficult problem in Southern India where optical satellite images are scarce during the monsoon season due to cloud cover, and where crop land is divided in parcels (i.e. crop fields) of very small sizes with diversified crops. The Landsat-8 images were used to monitor an ensemble of 104 parcels of ten different crops (irrigated and non-irrigated). Using global modeling, a bank of crop models was first obtained for the ten crops considered in the study. A metric is introduced to compare the observed signal to the obtained crop-models used as reference for each crop dynamic. Based on this metric, the possibility to use global models as references for distinguishing crops is investigated. The results provide a good proof-of-concept and show promising potential for crop classification.
Auteur(s)
Sylvain Mangiarotti1
, A. K. Sharma2, 1
, Samuel Corgne2
, Laurence Hubert-Moy2
, Laurent Ruiz3
, M. Sekhar4
, Yann H. Kerr1
1
CESBIO -
Centre d'études spatiales de la biosphère
( 615 )
- bpi 2801 18 Av Edouard Belin 31401 TOULOUSE CEDEX 4
- France
Institut de Recherche pour le Développement ( 67872 )
;
Université Toulouse III - Paul Sabatier ( 217752 )
;
Université de Toulouse ( 443875 )
;
Institut national des sciences de l'Univers ( 300045 )
;
Observatoire Midi-Pyrénées ( 302940 )
;
Institut de Recherche pour le Développement ( 67872 )
;
Université Toulouse III - Paul Sabatier ( 217752 )
;
Université de Toulouse ( 443875 )
;
Institut national des sciences de l'Univers UAR 831 ( 300045 )
;
Centre National d'Études Spatiales [Toulouse] ( 307314 )
;
Centre National de la Recherche Scientifique UAR 831 ( 441569 )
;
Météo-France ( 1079823 )
;
Centre National d'Études Spatiales [Toulouse] ( 307314 )
;
Centre National de la Recherche Scientifique UMR5126 ( 441569 )
;
Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement USC1439 ( 577435 )
2
UR2 -
Université de Rennes 2
( 406201 )
- Place du recteur Henri Le Moal - CS 24307 - 35043 Rennes cedex
- France
3
SAS -
Sol Agro et hydrosystème Spatialisation
( 138970 )
- UMR 1069, Sol Agro et Hydrosystème Spatialisation, Batiment 13, Agrocampus Ouest, 65 rue de Saint Brieuc CS 84215 35042 Rennes CEDEX
- France
Institut National de la Recherche Agronomique UMR1069 ( 92114 )
;
AGROCAMPUS OUEST ( 108028 )
4
IISc -
Indian Institute of Science
( 367783 )
- C V Raman Ave, Bengaluru Karnataka 560012
- Inde
Public visé
Scientifique
Vulgarisation
Non
Sous-type de document pour les Articles
Research article
Nom de la revue
Chaos, Solitons & Fractals
(ISSN : 0960-0779, ISSN électronique : 1873-2887)
Publié par Elsevier
Revue non référencée dans Sherpa-Romeo
Comité de lecture
Oui
Audience
Internationale
Licence
Paternité - Pas d'utilisation commerciale - Pas de modification
Date de publication
2018-01
Date de publication électronique
2018-12-18
Volume
106
Page/Identifiant
363-378
Langue du document
Anglais
Domaine(s)
Sciences du Vivant [q-bio]
Informatique [cs]
Informatique [cs]/Traitement du signal et de l'image [eess.SP]
Sciences de l'environnement
Sciences de l'environnement/Environnement et Société
Sylvain Mangiarotti, A. K. Sharma, Samuel Corgne, Laurence Hubert-Moy, Laurent Ruiz, et al.. Can the global modeling technique be used for crop classification?. Chaos, Solitons & Fractals, 2018, 106, pp.363-378. ⟨10.1016/j.chaos.2017.12.003⟩. ⟨hal-02621829⟩