SciELO - Scientific Electronic Library Online

vol.18 issue3Applications of Voronoi and Delaunay Diagrams in the solution of the geodetic boundary value problemThe map of the courts and the Brazilian Borders author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand




Related links


Boletim de Ciências Geodésicas

On-line version ISSN 1982-2170


RESENDE, Marcos Ribeiro; BERNUCCI, Liedi Légi Barianni  and  QUINTANILHA, José Alberto. Hybrid classification: pixel by pixel and object based to monitor the surface conditions of road pavements. Bol. Ciênc. Geod. [online]. 2012, vol.18, n.3, pp.397-420. ISSN 1982-2170.

Monitoring every Brazilian road use condition is an expensive and time consuming task. This research deals with new techniques which will yield a quick survey of road surface pavement condition by using hyperspectral images from airborne remote sensing. Recently, an increasing number of images with high spatial resolution has emerged on the world market with the advent of new remote sensing satellites and airborne sensors. Hyperspectral images from digital airborne sensor have been used in this work. A new identification methodology for a pavement surface and also for classification of the main defects of the surface has been devised. The first step of the methodology is the identification of the asphalt surface in the image, by using hybrid classification based on pixel initially and then improved by objects. The second step of the methodology is the identification and classification of the main defects of pavement surface that are observable in high spatial resolution imagery. This step makes intensive use of new techniques for classification of images based on objects. The goal is the generation of pavement surface condition index from the images which can be compared to quality index of pavement surface already managed by the regulatory agency in the country.

Keywords : Remote Sensing; Image Classification; Hyperspectral Image; Pavement Condition; Asphalt.

        · abstract in Portuguese     · text in Portuguese     · Portuguese ( pdf epdf )


Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License