@InProceedings{ColtriCoSoRoZuTrTr:2011:ClÁrCa,
author = "Coltri, Priscila Pereira and Cordeiro, Robson Leonardo Ferreira
and Souza, Tamires Tessarolli de and Romani, Luciana Alvim Santos
and Zullo J{\'u}nior, Jurandir and Traina J{\'u}nior, Caetano
and Traina, Agma Juci Machado",
affiliation = "{Cepagri / Feagri – Unicamp} and {Universidade de S{\~a}o Paulo –
USP/ICMC} and {Universidade de S{\~a}o Paulo – USP/ICMC} and
{Embrapa Inform{\'a}tica Agropecu{\'a}ria} and {Cepagri / Feagri
– Unicamp} and {Universidade de S{\~a}o Paulo – USP/ICMC} and
{Universidade de S{\~a}o Paulo – USP/ICMC}",
title = "Classifica{\c{c}}{\~a}o de {\'a}reas de caf{\'e} em Minas
Gerais por meio do novo algoritmo QMAS em imagem espectral
Geoeye-1",
booktitle = "Anais...",
year = "2011",
editor = "Epiphanio, Jos{\'e} Carlos Neves and Galv{\~a}o, L{\^e}nio
Soares",
pages = "539--546",
organization = "Simp{\'o}sio Brasileiro de Sensoriamento Remoto, 15. (SBSR).",
publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
address = "S{\~a}o Jos{\'e} dos Campos",
keywords = "coffee crops, spectral pattern, QMAS classification algorithm,
cafeicultura, padr{\~a}o espectral, algoritmo de
classifica{\c{c}}{\~a}o QMAS.",
abstract = "Although there exist different image processing techniques that
can be used to discover knowledge from satellite images of coffee
crops, there are still many issues to be addressed. One of them is
that automatic image classification techniques usually have
problems to recognize patterns from images of coffee crops, due to
their spatial variability and planting characteristics. In this
context, we present a comparison of two different methods for the
task of classifying a Geoye-1 image of coffee fields from the
South of the state of Minas Gerais, in Brazil. The compared
methods are: QMAS, a new algorithm for image classification, and
MAXVER, a traditional method commonly used by agronomists to
classify satellite images. The overall statistical results were
reasonable for the traditional MAXVER method. Nevertheless, it has
presented 30% in average of misclassification between the classes:
Coffee and Forest. The majority of the areas in which the
misclassification occurred refer to the middle of the coffee
field, which complicates the process of post-classification. On
the other hand, the QMAS algorithm presented better results, being
more efficient especially for the coffee classification, since it
did not present classificatory confusion in the middle of the
coffee area. Between all the coffee fields classified by QMAS,
only one was wrongly recognized as forest. In addition, the QMAS
method was able to classify a forest fragment in the middle of the
coffee plantation. Thus, we conclude that the QMAS algorithm is a
viable alternative for the classification of remote sensing images
from coffee producing regions.",
conference-location = "Curitiba",
conference-year = "30 abr. - 5 maio 2011",
isbn = "{978-85-17-00056-0 (Internet)} and {978-85-17-00057-7 (DVD)}",
language = "pt",
organisation = "Instituto Nacional de Pesquisas Espaciais (INPE)",
ibi = "3ERPFQRTRW/3A22M2S",
url = "http://urlib.net/ibi/3ERPFQRTRW/3A22M2S",
targetfile = "p0993.pdf",
type = "Agricultura",
urlaccessdate = "18 jun. 2024"
}