Table 1
Pixel distribution for each testing dataset of the two-class and three-class segmentation models. Mean pixel class share of the N images with standard deviation for each testing dataset of the two-class and three-class segmentation models. Mono: monocrop, Int: intercropping systems without buckwheat, InterBw: intercropping systems with buckwheat, N: number of images per subset, OSR stage: oilseed rape growth stage based on the BBCH scale (Lancashire et al., 1991).
| Dataset | two-class segmentation | three-class segmentation | |||||
|---|---|---|---|---|---|---|---|
| N | soil (%) | vegetation (%) | N | soil (%) | other plants (%) | oilseed rape (%) | |
| Sown mixtures | |||||||
| Mono | 20 | 55.6 ±3.4 | 44.4 ±3.4 | 10 | 56.3 ±4.2 | 1.3 ±0.3 | 42.3 ±4.2 |
| Inter | 20 | 44.9 ±3.8 | 55.2 ±3.8 | 10 | 53.6 ±5.1 | 10.5 ±1.1 | 35.9 ±4.4 |
| InterBw | 20 | 41.9 ±3.5 | 58.1 ±3.5 | 10 | 44.9 ±5.5 | 28.1 ±3.4 | 26.9 ±2.5 |
| Canopy coverage | |||||||
| LC | 17 | 84.7 ±1.6 | 15.3 ±1.6 | 8 | 87.5 ±2.1 | 3.1 ±0.6 | 9.4 ±2.0 |
| IC | 25 | 51.9 ± 1.0 | 48.1 ±1.0 | 12 | 53.3 ±1.2 | 11.3 ±1.4 | 35.4 ±1.7 |
| HC | 18 | 18.9 ± 1.1 | 81.1 ±1.1 | 10 | 20.9 ±1.8 | 24.0 ±4.0 | 55.1 ±3.0 |
| OSR stage | |||||||
| 12 | 6 | 94.6 ±0.6 | 5.4 ±0.6 | 4 | 94.8 ±0.8 | 2.2 ±0.7 | 3.0 ±0.2 |
| 14 | 7 | 67.0 ±4.2 | 33.0 ±4.2 | 3 | 67.6 ±5.7 | 9.1 ±3.4 | 23.3 ±3.7 |
| 15 | 14 | 58.6 ±2.5 | 41.4 ±2.5 | 8 | 57.4 ±3.6 | 10.4 ±1.5 | 32.2 ±3.2 |
| 16 | 13 | 47.0 ±3.2 | 53.0 ±3.2 | 6 | 55.2 ±1.8 | 9.1 ±1.6 | 35.7 ±2.6 |
| 17 | 10 | 16.2 ±1.6 | 83.8 ±1.6 | 4 | 18.2 ±2.5 | 35.9 ±6.7 | 45.9 ±4.4 |
| 18 | 10 | 21.7 ±1.9 | 78.3 ±1.9 | 5 | 20.6 ±2.5 | 16.6 ±4.8 | 62.8 ±3.8 |
Les statistiques affichées correspondent au cumul d'une part des vues des résumés de l'article et d'autre part des vues et téléchargements de l'article plein-texte (PDF, Full-HTML, ePub... selon les formats disponibles) sur la platefome Vision4Press.
Les statistiques sont disponibles avec un délai de 48 à 96 heures et sont mises à jour quotidiennement en semaine.
Le chargement des statistiques peut être long.