Carlos Frederico de Sá Volotão

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
This work presents a method to detect linear features in remote sensing images using feed-forward neural network and pixel contextual information. The net is trained using a 5x5 window. The input layer includes information extracted from the pixel and its neighborhood, including geometric details. A CCD/CBERS-2 band has been tested. The results indicate the(More)
In this paper we establish the relation between camera calibration and the generation of horizontal stereoscopic images. After that, we introduce a new method that handles the problem of generating stereoscopic pairs without using calibration patterns, instead we use the correspondence of homologous points. The method is based on the optimization of a(More)
  • 1