Supervised Classification of Spectral Signatures from Agricultural Land-Cover in Panama Using the Spectral Angle Mapper Algorithm

In this article the development of a database of referenced spectral signatures from agricultural land-cover for the Republic of Panama is presented. This database consists of reflectance spectra measured on crops and low vegetation, such as: rice, chili, onion, watermelon, maize and bare soil and o...

Full description

Saved in:
Bibliographic Details
Published in:2019 XLV Latin American Computing Conference (CLEI) pp. 1 - 7
Main Authors: Sanchez-Galan, Javier E., Reyes, Jorge Serrano, Jimenez, Jose Ulises, Quiros-McIntire, Evelyn Itzel, Fabrega, Jose R.
Format: Conference Proceeding
Language:English
Published: IEEE 01.09.2019
Subjects:
agricultural landcover
Agriculture
Biomedical imaging
Instruments
remote sensing
satellite image
Satellites
Software
Soil
Spectral library
spectral signature
supervised classification
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this article the development of a database of referenced spectral signatures from agricultural land-cover for the Republic of Panama is presented. This database consists of reflectance spectra measured on crops and low vegetation, such as: rice, chili, onion, watermelon, maize and bare soil and of satellite images of their plots. Details of the integration process of the database and software developed for the manipulation of spectral signatures, are described. The Spectral Angle Mapping algorithm (SAM) is used for the supervised classification of the agricultural coverages in the database. On the one hand, results indicate the possibility of using this classification technique for the automatic determination of crops and even different phenological stages in a crop via a satellite image. On the other hand, results highlight the limitations of using this technique on recently planted crops and soil flooded by rain or with soil cultivated with a low agricultural cover crop. We foresee the use of this methodology and database for agricultural land surveys, crop management or used in the general organization of the territory.
DOI:10.1109/CLEI47609.2019.235101