Automatic detection and agronomic characterization of olive groves using high-resolution imagery and LIDAR data

Abstract

The Common Agricultural Policy of the European Union grants subsidies for olive production. Areas of intensified olive farming will be of major importance for the increasing demand for oil production of the next decades, and countries with a high ratio of intensively and super-intensively managed olive groves will be more competitive than others, since they are able to reduce production costs.It can be estimated that about 25-40% of the Sicilian oliviculture must be defined as "marginal". Modern olive cultivation systems, which permit the mechanization of pruning and harvest operations, are limited.Agronomists, landscape planners, policy decision-makers and other professionals have a growing need for accurate and cost-effective information on land use in general and agronomic parameters in the particular. The availability of high spatial resolution imagery has enabled researchers to propose analysis tools on agricultural parcel and tree level.In our study, we test the performance of WorldView-2 imagery relative to the detection of olive groves and the delineation of olive tree crowns, using an object-oriented approach of image classification in combined use with LIDAR data.We selected two sites, which differ in their environmental conditions and in their agronomic parameters of olive grove cultivation. The main advantage of the proposed methodology is the low necessary quantity of data input and its automatibility. However, it should be applied in other study areas to test if the good results of accuracy assessment can be confirmed.Data extracted by the proposed methodology can be used as input data for decision-making support systems for olive grove management.

Detection of Very Small Tree Plantations and Tree-Level Characterization Using Open-Access Remote-Sensing Databases

“…Some other studies have addressed tree plantation detection by combining structural and spectral data obtaining high accuracy levels as well. However, they mainly use high-resolution Satellite data [77][78][79]. The necessity of acquiring high-resolution multispectral data, with its associated costs, could hinder the possibility of performing such studies at a regional or national level.…”

A geospatial decision support system to assist olive growing at the landscape scale

“…This multifunctional role requires appropriate support in order to attain the planning and management of sustainable high-quality olive sustainable approaches (La Scalia et al, 2016;Russo et al, 2015;Caruso et al, 2014), (ii) pest management by webGIS application, DSS and olive fly modelling (Zaza et al, 2018;Doitsidis et al, 2017;Pontikakos et al, 2012). Many of these approaches are based on modelling; models applied to olive grove are typically classified as either empirical/statistical or dynamic.…”