SciELO - Scientific Electronic Library Online

 
vol.28 número3Modelo de Interdicción de Sistemas de Potencia considerando el Efecto de la Respuesta a la Demanda índice de autoresíndice de assuntospesquisa de artigos
Home Pagelista alfabética de periódicos  

Serviços Personalizados

Journal

Artigo

Indicadores

Links relacionados

  • Em processo de indexaçãoCitado por Google
  • Não possue artigos similaresSimilares em SciELO
  • Em processo de indexaçãoSimilares em Google

Compartilhar


Información tecnológica

versão On-line ISSN 0718-0764

Resumo

ARISTA-JALIFE, Antonio; CALDERON-AUZA, Gustavo; FIERRO-RADILLA, Atoany  e  NAKANO, Mariko. Classification of Urban Aerial Images: A Comparison between Low-Semantic Descriptors and Deep Learning. Inf. tecnol. [online]. 2017, vol.28, n.3, pp.209-224. ISSN 0718-0764.  http://dx.doi.org/10.4067/S0718-07642017000300021.

This paper presents a comparison between different low-semantic descriptive algorithms coupled with a support vector machine and the deep learning algorithm, for the task of recognition and classification of aerial images. For this task, a database composed of 1200 images is used to fulfill the supervised trainings. The objective consists on classifying images in six categories that are commonly found on urban areas, in order to be used in any part of the world. The results show that with 150 samples of each class, the deep learning algorithm is capable of classifying images of avenues, buildings, industries, natural areas, residential areas and water bodies with an 87% of accuracy. Experimental results also prove that the labeled images as industry and buildings are the most complex ones to distinguish among these two classes, both for low-level descriptors and deep learning techniques.

Palavras-chave : deep learning; support vector machine; aerial images; texture descriptors; database.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )

 

Creative Commons License Todo o conteúdo deste periódico, exceto onde está identificado, está licenciado sob uma Licença Creative Commons