Plant Height
Max Plant Height: This trait refers to the max height recorded within the plot. It is computed using a 3D point cloud of the microplot and maximum is defined as the 99% percentile of the height of each point among plot point cloud. On request, we can compute Max Plant height only on a sub...
Case study →
Plant Height Heterogeneity
Max Plant Height Heterogeneity: This trait refers to the heterogeneity measured from the max plant height calculation. The plot studied is first sliced into ~30cm patches, the trait is processed per slice and we compute a coefficient of variation (standard deviation among slices divided by mean value of the plot). Mean Plant Height Heterogeneity: This trait...
Case study →
Plant Biovolume Heterogeneity
This trait refers to the heterogeneity measured from the biovolume calculation. The plot studied is first sliced into ~30cm patches, the trait is processed per slice and we compute a coefficient of variation (standard deviation among slices divided by mean value of the plot).
Case study →
NDRE
The Normalized Difference Red-Edge Index is based on the red-edge band which is very sensitive to medium to high levels of chlorophyll content. Hence, it is a good indicator of crop health in the mid to late stage crops where the chlorophyll concentration is relatively higher. Also, the NDRE could be used to map the...
Case study →
NDVI
The Normalized Difference Vegetation Index is one of the most commonly used indices for monitoring the percentage of green cover in a projected surface. It takes as an input the reflectance dataset, specifically the Near Infra-Red (NIR) and Red bands. NDVI helps to monitor crop development throughout its growth cycle. It is computed as follows:...
Case study →
Simple Ratio
Simple Ratio is indeed the simplest vegetation index calculated by dividing reflectance recorded in the Near Infra-Red (NIR) by that recorded in Red bands. Hence, SR = ρ850 / ρ675. It is a quick way to distinguish green leaves from other objects in the scene and estimate the relative biomass present in the image. Also,...
Case study →
Flower Fraction Heterogeneity
This trait refers to the heterogeneity measured from Flower Fraction. The plot studied is first sliced into ~30cm patches, the trait is processed per slice and we compute a coefficient of variation (standard deviation among slices divided by mean value of the plot)
Case study →
Green Cover
Green Cover: This trait refers to the surface of green pixels within the plot. It is expressed as a percentage of vegetation pixels divided by all plot pixels. It is a good proxy of the vegetation development and the capacity of the plant to make photosynthesis. Green Cover can be influenced by weeds or strong...
Case study →
Green Cover Heterogeneity
This trait refers to the heterogeneity measured from the Green Cover calculation. The plot studied is first sliced into ~30cm patches, the trait is processed per slice and we compute a coefficient of variation (standard deviation among slices divided by mean value of the plot).
Case study →
Greenness
Greenness (excess green): This trait refers to the intensity of green within the vegetation mask identified from the Green Cover. Many indices are able to summarize the greenness, we propose three : vari / excess green and green on red. Greenness (excess green) Heterogeneity: This trait refers to the heterogeneity measured from the Greenness (excess...
Case study →
Border Effect
Border Effect: Computed at plant emergence, this trait measures the possibility that a plot development is influenced by plant gaps from adjacent plots. Based on the results of the plant gap identified per row, this trait helps to assess the border effect impacting crop productivity. Border Effect Percentage: Computed at plant emergence, this trait measures...
Case study →
Plant Count Heterogeneity
This trait refers to the heterogeneity measured from the plant count. The plot studied is first sliced into ~30cm patches, the trait is processed per slice and we compute a coefficient of variation (standard deviation among slices divided by mean value of the plot).
Case study →
