SciELO - Scientific Electronic Library Online

 
 número102Una aproximación cartográfica al análisis de los vertidos de metales pesados en EspañaDinámica espacio-temporal de uso, cambio de uso y cobertura de suelo en la región centro de la Sierra Madre Oriental: implicaciones para una estrategia REDD+ (Reducción de Emisiones por la Deforestación y Degradación) índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados

Revista

Articulo

Indicadores

Links relacionados

  • No hay artículos similaresSimilares en SciELO

Compartir


Revista cartográfica

versión On-line ISSN 2663-3981versión impresa ISSN 0080-2085

Resumen

MURILLO CASTANEDA, Raúl Alejandro. Implementation of the vector support machines method in spatial databases for supervised classification analysis in remote sensor images. Rev. cartogr. [online]. 2021, n.102, pp.27-42.  Epub 14-Mar-2022. ISSN 2663-3981.  https://doi.org/10.35424/rcarto.i102.830.

This article is oriented to the development of an application that implements the method of supervised classification of vector support machines (MSV) on images from remote sensors, whether active or passive that are stored in a spatial database. of a relational type that allows contributing and supporting the classification of images, according to normality and abnormality parameters, where it is also possible to store these results within the same database management system. Given that the MSV supervised classification algorithm is widely accepted by the scientific community as one of the best classification techniques, since it allows very good accuracy in diagnosing the different coverings present in the soil. Since it seeks not only to find a dissociation between these, but to achieve a separation between the elements to be classified, it will be implemented as a classification technique. The application is designed for the end user, which allows not only obtaining support and sustenance when making decisions, but also facilitating the updating of the database, the inclusion or deletion of information from it, as well as the possibility of choosing the main characteristics that must be taken into account during the classification process. This utility is of great value, since when working with images with similar characteristics, the possibility of establishing dissociation ranges or weights for the different coverages directly affects the expected result. Finally, a case study related to deforestation in the Colombian Amazon will be presented, where the utility of the application will be demonstrated by means of a supervised classification, which will be compared with the classification module of some software that currently implements it.

Palabras llave : classification; spatial database; confusion matrix; Colombian Amazon; ENVI.

        · resumen en Español     · texto en Español