Preliminary study for weed biomass prediction combining visible images to a plant-growth model - Institut Agro Dijon Accéder directement au contenu
Proceedings/Recueil Des Communications Année : 2019

Preliminary study for weed biomass prediction combining visible images to a plant-growth model

Annabelle Larmure
Christelle Gée

Résumé

This preliminary study was designed to test an image approach (RGB images) to estimate crop and weed aerial biomass (BM) and predict their growths. From an image processing, based on crop/weed discrimination, a calibration was done between photographed leaf area (PLA) and BM deduced from a standard (destructive) approach. Then, a plant growth model component (AZODYN) was used with PLA as input, considering wheat and weeds separately. For wheat, the results confirm that to initialize the model, the image approach may replace the standard one with no impact on the values of predicted BM whereas weed results are more mixed.
Fichier non déposé

Dates et versions

hal-02788513 , version 1 (05-06-2020)

Identifiants

Citer

Josselin Merienne, Annabelle Larmure, Christelle Gée. Preliminary study for weed biomass prediction combining visible images to a plant-growth model. Wageningen Academics Publishers, pp.597-603, 2019, 978-90-8686-337-2 978-90-8686-888-9. ⟨10.3920/978-90-8686-888-9_74⟩. ⟨hal-02788513⟩
65 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More