In this paper an efficient image matching algorithm is presented for use in aircraft navigation. A sequence images with each two successive images partially overlapped is sensed by a monocular optical system. 3D undulation features are recovered from the image pairs, and then matched against a reference undulation feature map. Finally, the aircraft position is estimated by minimizing Hausdorff distance measure. The simulation experiment using real terrain data is reported.
New approach to navigation: matching sequential images to 3D terrain maps
26th AIPR Workshop: Exploiting New Image Sources and Sensors ; 1997 ; Washington,DC,USA
Proc. SPIE ; 3240
1998-03-01
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Review of AUV Underwater Terrain Matching Navigation
Online Contents | 2015
|Matching Terrain-Height Maps For A Robotic Vehicle
NTRS | 1991
|