 |
    |
GPS-Based Multi-viewpoint Integration for Anticipative Scene Analysis
Kohji Kamejima
Osaka Institute of Technology, Faculty of Information Science and Technology, 1-79-1 Kitayama, Hirakata 573-0196, Japankamejima@is.oit.ac.jp
http://www.is.oit.ac.jp/~kamejima
Abstract. A multi-viewpoint integration scheme is introduced to recognize scene features prior to physical access. In this schematics, chromatic complexity of vehicle’s- and bird’s-eye-views of roadway scenes are matched to extend GPS tracks towards possible destinations. Saliency patterns arising in destination images are anticipatively extracted to control the focus of inherent and machine vision to what to be analyzed.
Keywords: Multi-viewpoint Image, Scene Analysis, Chromatic Complexity, GPS Signal Processing, Image Saliency
LNCS 7585, p. 375 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012