Leaf Area Index evaluation in vineyards using 3D point clouds from UAV imagery

Abstract

The Leaf Area Index (LAI) is an ecophysiology key parameter characterising the canopyatmosphere interface where most of the energy fluxes are exchanged. However, producing maps for managing the spatial and temporal variability of LAI in large croplands with traditional techniques is typically laborious and expensive. The objective of this paper is to evaluate the reliability of LAI estimation by processing dense 3D point clouds as a costeffective alternative to traditional LAI assessments. This would allow for high resolution, extensive and fast mapping of the index, even in hilly and not easily accessible regions. In this setting, the 3D point clouds were generated from UAV-based multispectral imagery and processed by using an innovative methodology presented here. The LAI was estimated by a multivariate linear regression model using crop canopy descriptors derived from the 3D point cloud, which account for canopy thickness, height and leaf density distribution along the wall. For the validation of the estimated LAI, an experiment was conducted in a vineyard in Piedmont: the leaf area of 704 vines was manually measured by the inclined point quadrant approach and six UAV flights were contextually performed to acquire the aerial images. The vineyard LAI estimated by the proposed methodology showed to be correlated with the ones obtained by the traditional manual method. Indeed, the obtained R 2 value of 0.82 can be considered fully adequate, compatible to the accuracy of the reference LAI manual measurement.

Advances in Unmanned Aerial System Remote Sensing for Precision Viticulture

“…The traditional biomass estimation method used by the farmer is often imprecise and time-consuming compared to non-destructive and fast crop surface models (CSMs) estimation by UASs’ imagery. L. Comba et al [ 81 ] have tested the reliability of an estimation process of a dense 3D point cloud as an economical alternative to traditional LAI assessments. The LAI was estimated using a multivariate linear regression model that uses 3D crop crown descriptors (thickness, height, and distribution of leaf density along the wall), showing a high correlation with those obtained with the traditional manual method, even in hilly and difficult-to-access regions.…”

Automatic Grapevine Trunk Detection on UAV-Based Point Cloud

“…However, as final result, only the vineyards and local evaluation of vine rows orientation were retrieved. Comba et al [24] applied a multivariate linear regression model to crop canopy descriptors derived from the 3D point cloud, to estimate vineyard's Leaf Area Index (LAI). Marie Weiss and Frédéric Baret [17], applied a SfM algorithm to extract 3D dense point cloud over the vineyard and used the terrain altitude, extracted from the dense point cloud, to get the 2D distribution of height of the vineyard.…”

Field assessment of a newly‐designed pneumatic spout to contain spray drift in vineyards: evaluation of canopy distribution and off‐target losses

“…In light of the need described earlier, pesticide application equipment design in recent years has been active. While many developments have focused on sensing module-based precision spraying 15 to maximize treatment efficacy and minimize the risks of pesticide off-target losses, [16][17][18][19][20][21][22][23][24][25][26][27][28][29] very few advances have been made in pesticide application equipment characterized by pneumatic atomization. Despite a reputation for collateral risk from drift and spray losses caused by the fine droplets generated by these sprayers, they remain widely used in the most important wine 30,31 and table grape-producing 32 vineyard areas around the world.…”