DOI:
https://doi.org/10.14483/23448393.3849Published:
2012-06-29Issue:
Vol. 17 No. 1 (2012): January - JuneSection:
ArticleEvaluación de las Redes Neuronales Artificiales Perceptron Multicapa y Fuzzy-Artmap en la Clasificación de Imágenes Satelitales
Evaluation of Satellite Image Classification using Multilayer Perceptron and Fuzzy-ArtMap models
Keywords:
Clasificación de imágenes satelitales, Fuzzy-Artmap, Perceptron Multicapa. (es).Keywords:
Satellite image classification, Fuzzy-Artmap, Multilayer Perceptron. (en).Downloads
Abstract (es)
Este documento reporta una comparación cuantitativa y cualitativa del desempeño de las redes neuronales artificiales Perceptron Multicapa y Fuzzy-Artmap para clasificación de coberturas del suelo a partir de imágenes satelitales multi-espectrales. Se describen parámetros y condiciones que ayudan a producir imágenes clasificadas con buena exactitud temática. Adicionalmente, se hace una comparación entre los dos modelos de redes neuronales que describen sus ventajas y desventajas.
Abstract (en)
In this paper a quantitative and qualitative comparison between performance of Multilayer Perceptron and Fuzzy-Artmap neural networks for classification of land cover from multispectral satellite images is reported. It describes parameters and conditions that help to produce accurate classified images. Additionally, it makes a comparison between the two types of neural networks models describing both their advantages and disadvantages.References
Bollela, Ana. “Redes Neuronales”. Universidad ORT. Uruguay. 2003
Camara. Gilberto; Vieira, Antonio. “Geocomputation Techniques For Spatial Analysis: Is It Case For Health Data Set?”. Image Processing Division, National Institute for Space Research, Brazil. 2001.
Cardenas, Luis. “Optimal Design of Neural Network for Land-Cover Classification from Multi-spectral Imagery”. Centro de Investigaciones de Geografía y Geomática. México. 2003.
Carpenter, Gail. “Default ARTMAP. Department of Cognitive and Neural System. 2003
Carpenter, Gail. Gopal; Sucharita, Macomber, Scout. Martens, Siegfried, Woodcock, Curtis. “A Neural Network Method for Mixture Estimation for Vegetation Mapping” Remote Sensing Environ. New York 1999
Carpenter, Gail. Gopal; Sucharita, Macomber, Scout. Martens, Siegfried, Woodcock, Curtis. “A Neural Network Method for Efficient Vegetation Mapping” Remote Sensing Environ. New York. 1999
Carpenter, Gail. Grossber, Stephen. Shock, Byron. Woodcock, Curtis. “A Neural Network Method for Land Use Change Classification with Application to the Nile River Delta”. Department of Cognitive and Neural System. 2001
Cepeda Caballero, Jahir. “Redes Neuronales Estáticas –Sistemas Expertos e Inteligencia Artificial”. Corporación Colombiana de Colombia IDEAS. 2002.
Chuvieco, Emilio. “Fundamentos de Teledetección Espacial”. Ediciones Rialp S.A. Reimpresión corregida 568 pp. Madrid, España. Madrid. 2000
Corporación Autónoma Regional (C.A.R). Ecoforest Ltda. Swedforest Scandiaconsult “Inventario y Diagnostico de los Recursos Naturales y Renovables del Área Jurisdiccional de la Corporación Autónoma Regional C.A.R. – Cundinamarca” 1995.
Forero, Maria Cristina. “Levantamiento de Cobertura Terrestre y Uso de la Tierra”. Revista CIAF Volúmen 9.Bogotá, 1984.
Gecek, Deniz. “Improvement of Image Classification with the Integration of Topographical Data. Geodetic and Geographic Information Technology. Ankara. Turkey. 2000”
Jensen, John. “Introductory Digital Image Processing: A Remote Sensing Perspective”. Prentice Hall. Second Edition.1996.
Leica Geosystems. “Erdas Field Guide. Fifth Edition Translation”. Estados Unidos de America. 2000, p 213
Lin, Hue; Chenghu, Zhou. “Geo-Interpretation Model for Land-Cover / Land-Use Classification”. Lab Resource and Environment Information System, CAS, Beijing, China, Department of Geography, Chinese University of Hong Kong. 2000.
Liu, Xiao Hang, “Change Detection for Urban Growth Modeling. An Artificial Neural Network Approach”.4th International Conference on Integrating GIS and Environmental Modeling. Canada. September 2000.
Lizarazo, Iván. Mesa, Samuel, Cuitiva, Ricardo. “Clasificación de la cobertura y del uso del suelo urbano usando imágenes de satélite y algoritmos supervisados de inteligencia artificial”. Revista la UD y la Geomática, Vol. 1, núm. 2, Segundo semestre 2008.
Martens, Siegfried. “ClasserScript Ver. 1.1 User‘s Guide”. Boston University. 2005.
Mas, Jean. “An Artificial neural Networks Approach to Map land Use Land Cover using LANDSAT Imagery and Ancillary Data.” Universidad Autónoma de México. IEEE. 2003
Mendoza, E.H. Santso, J.R. Santa Rosa, A.N.C. “Land Use Land Cover mapping In Brazilian Amazon using Neural Network with Aster Terra Data” INPE.2003.
Nouza, David. Laclir; Verne, Schwab, Matthew. “Using Neural Network to Evaluate Land Use Change”. D. Nouza et al. 2000
Perez, Magda Liliana. “Aporte de las Clasificaciones por Métodos Convencionales, redes Neuronales y Análisis de Texturas en Estudios Geográficos. Caso de Uso “Sinergia entre Imagen Landsat y Radarsat de la Sabana de Bogotá”. Instituto Geográfico Agustín Codazzi. 2003”
Quero Reboul, José Manuel. “Redes Neuronales”. Departamento de Ingeniería Electrónica. Universidad de Sevilla. 2001.
Rajasekaran, S. Vijayalakshimi, Pai. ”Image Recognition Using Simplified Fuzzy-ARTMAP Augmented with a Moment based Feature Extractor. International Journal of Pattern Recognition and Artificial Intelligence.2000”
Schroeder, Thomas. “Input / Output Data Definition Of Artificial Neural Network For Computing Pigment Concentrations From Remote The Sensing Reflectance At Sea Level Above Case-1 Water”. Freie Universitat Berlin. 2003
Shah, S.K. “Image Classification Based On Textural Features Using Artificial Neural Network (Ann)”. Department of Electrical Engineering MS University of Baroda, Kalabhavan. 2003.
Shock, B.M.; Carpenter, G.A.; Gopal, S; Woodcock, C.E. “Artmap Neural Network Classification of Land Use Change”. Proceedings of the World Congress of Computers in Agriculture and Natural Resources. 2002.
Sinha; Ashok. Dudhani, Surekha. ”Fuzzy Neural Network Modeling of Land Use/cover using IRS-1D Image. Galgoita College of Eng & technology. India. 2004”
Tso, Brandt; Mather, Paul. “Classification Methods for Remotely Sensed Data”. First Published by Taylor and Francis. 2001.
Ríos de la Torre, Ignacio; Calderón Osorno, José Luis; Durán Camarillo, Edmundo René. Polilibro Redes Neuronales Artificiales 1. http://hugo-inc.net16.net/RNA/Unidad%201/1.8.html.
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
From the edition of the V23N3 of year 2018 forward, the Creative Commons License "Attribution-Non-Commercial - No Derivative Works " is changed to the following:
Attribution - Non-Commercial - Share the same: this license allows others to distribute, remix, retouch, and create from your work in a non-commercial way, as long as they give you credit and license their new creations under the same conditions.
2.jpg)
