UM MÉTODO DE MODELAGEM DO CONHECIMENTO MULTITEMPORAL PARA A INTERPRETAÇÃO AUTOMÁTICA DE IMAGENS DE SENSORES REMOTOS / AN APPROACH TO MODEL MULTITEMPORAL KNOWLEDGE IN AUTOMATIC INTERPRETATION PROCESS OF REMOTELY SENSED IMAGES

AUTOR(ES)

VANESSA DE OLIVEIRA CAMPOS

DATA DE PUBLICAÇÃO

2005

RESUMO

The present work presents a methodology to model the multitemporal knowledge for the automatic interpretation of remotely sensed images. The used interpretation procedure combines the multitemporal and spectral knowledge using fuzzy logic techniques. This method uses state transition diagrams to represent the possibilities of class changes within a given time interval. The change possibilities are estimated based on historical data by using genetic algorithms. The method was validated by experiments using a set of Landsat-5 images of the Rio de Janeiro City, Brazil, acquired at 5 dates separated by approximately 4 years. The experimental results indicated that the use of the multitemporal knowledge as modeled by the proposed method brings an important performance improvement in comparison with the pure spectral classification.

ASSUNTO(S)

sensoriamento remoto image digital processing processamento digital de imagem knowledge based interpretation remote sensing interpretacao baseada em conhecimento genetic algorithms algoritmos geneticos

Documentos Relacionados

• KNOWLEDGE-BASED INTERPRETATION OF HIGH RESOLUTION REMOTE SENSING IMAGES
• INTERPRETAÇÃO BASEADA EM CONHECIMENTO APLICADA A IMAGENS MULTITEMPORAIS DE SATÉLITE DE BAIXA RESOLUÇÃO
• UMA ABORDAGEM BASEADA EM CONHECIMENTO PARA A INTERPRETAÇÃO AUTOMÁTICA DE DADOS DE SENSORIAMENTO REMOTO MULTI-DATA
• Método automático para calibração polarimétrica de imagens SAR
• Automatic approach to polarimetric calibration of SAR images