Skip to main content

IDENTIFICACION BASADA EN OBJETOS DE CULTIVOS HORTICOLAS BAJO INVERNADERO A PARTIR DE ESTEREO IMAGENES DEL SATELITE WORLDVIEW-3 Y SERIES TEMPORALES DE LANDSAT 8

AGL2014-56017-R

•
Funding agency name Ministerio de Economía y Competitividad
Funding agency acronym MINECO
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos I+D+i Retos de Investigación
Call year 2014
State Plan 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Management unit Secretaría de Estado de Educación, Formación Profesional y Universidades
Beneficiary centre UNIVERSIDAD DE ALMERIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

riUAL. Repositorio Institucional de la Universidad de Almería
Publication Estudio, informe, memoria (Report)

Optimizing multiresolution segmentation for extracting plastic greenhouses from WorldView-3 imagery

  • Aguilar Torres, Manuel Ángel
  • Novelli, Antonio
  • Nemmaoui, Abderrahim
  • Aguilar Torres, Fernando José
  • García Lorca, Andrés Miguel
  • González Yebra, Óscar
Multiresolution segmentation (MRS) has been pointed out as one of the most successful image segmentation algorithms within the object-based image analysis (OBIA) framework. The performance of this algorithm depends on the selection of three tuning parameters (scale, shape and compactness) and the bands combination and weighting considered. In this work, we tested MRS on a WorldView-3 bundle imagery in order to extract plastic green-house polygons. A recently published command line tool created to assess the quality of segmented digital images (AssesSeg), which implements a modified version of the supervised discrepancy measure named Euclidean Distance 2 (ED2), was used to select both the best aforementioned MRS pa-rameters and the optimum image data source derived from WorldView-3 (i.e., panchromatic, multispectral and atmospherically corrected multispectral orthoimages). The best segmentation results were always attained from the atmospherically corrected multispectral WorldView-3 orthoimage.
riUAL. Repositorio Institucional de la Universidad de Almería
Publication Estudio, informe, memoria (Report)

A New Threshold Relative Radiometric Correction Algorithm (TRRCA) of Multiband Satellite Data

  • Novelli, Antonio
  • Aguilar Torres, Manuel Ángel
  • Tarantino, Eufemia
It is well known that remote sensed scenes could be affected by many factors and, for optimum change detection, these unwanted effects must be removed. In this study a new algorithm is proposed for PIF (Pseudo Invariant Features) extraction and relative radiometric normalization. The new algorithm can be labeled as a supervised one and combines three methods for the detection of PIFs: Moment distance index (MDI), Normalized Difference Vegetation Index (NDVI) masks morphological erosion and dilate operators. In order to prove its effectiveness, the algorithm was tested by using Landsat 8 scenes of the “Mar de Plstico” landscape of the Andalusian Almer´ıa. Many tests were performed in order to provide a set of valid input parameters for the chosen environments. Lastly, the results were statistically assessed with parametric and non-parametric tests showing very good and stable results in the four different study areas