Crop recognition at orchard level in Mediterranean conditions using time series of Sentinel-2 spectral indices
The Valencian agricultural landscape is made up of a multitude of small-sized plots. Most remote sensing research has been focused on the discrimination of the large-scale land covers or uses, however, in Spain, crop recognition at plot level is crucial to develop management policies at different sc...
| Main Authors: | , |
|---|---|
| Format: | conferenceObject |
| Language: | Inglés |
| Published: |
Wageningen Academic Publishers
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/20.500.11939/8682 https://www.wageningenacademic.com/doi/abs/10.3920/978-90-8686-947-3_121 |
| Summary: | The Valencian agricultural landscape is made up of a multitude of small-sized plots. Most remote sensing research has been focused on the discrimination of the large-scale land covers or uses, however, in Spain, crop recognition at plot level is crucial to develop management policies at different scales. This work describes preliminary work for constructing and validating a classification model for automatic identification of crops in an agricultural zone where different species of fruit trees are cultivated. The model is based on the analysis of time series of two spectral indices obtained from Sentinel-2 images and using a Fourier decomposition approach. A two-step classification procedure is proposed: a random forest classifier at pixel level, followed by a plot classification. The overall accuracy achieved was 84.18% and the Kappa index was 0.71. |
|---|