Título: International Journal of Remote SensingImportada do Authenticus Pesquisar Publicações da Revista

Vol. 29 Nº 12

Páginas: 593-607

ISSN: 0143-1161

Editora: Taylor & Francis

ISI Web of Knowledge - 41 Citações

ISI Web of Science

Scopus - 45 Citações

Current Contents

FOS: Ciências da engenharia e tecnologias > Engenharia do ambiente

CORDIS: Ciências Naturais ; Ciências Tecnológicas

ID Authenticus: P-004-3Q1

DOI: 10.1080/01431160701281015

Abstract (EN): The use of black white (BW) air photographs for the production of historic land cover maps can be done by image classification, using additional texture features. In this paper we evaluate the importance of a number of parameters in the image classification process based on texture, such as the window size, angle and distance used to produce the texture features, the number of features used, the image quantization level and its spatial resolution. The evaluation was performed using five photographs from the 1950s. The influence of the classification method, the number of classes searched for in the images and the post-processing tasks were also investigated. The effect of each of these parameters for the classification accuracy was evaluated by cross-validation. The selection of the best parameters was performed based on the validation results, and also on the computation load involved for each case and the end user requirements. The final classification results were good (average accuracy of 85.7%, k=0.809) and the method has proven to be useful for the production of historic land cover maps from BW air photographs.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Contacto: andre.marcal@fc.up.pt

Nº de páginas: 15