Horizon detection from pseudo spectra images of water scenes

Abstract

Horizon detection is a pre-cursor to vision processing in air and water robotics. This paper makes three contributions to horizon detection. First, a theoretical framework for generating pseudo spectra images (PSI), from spectrum analysis of XYZ color-space is presented. Second, wavelengths in the visible spectrum are identified, at which the PSI has similar intensities for sky and clouds. Generating PSI at these wavelengths minimizes artifacts due to clouds in the sky, resulting in well defined horizon. Third, fitting ellipses are presented as an alternate to Hough Transform for horizon detection. Ellipses have lower computational complexity than Hough Transform and can accommodate curved edges as candidates for horizon.