Image-based aircraft pose estimation using moment invariants
conference paper
The problem of estimating aircraft pose information from mono-ocular image data is considered using two different pose estimation algorithms. Both algorithms are based on the rotation invariant moment approach that was introduced by Dudani. The dependence of pose estimation accuracy on image resolution and aspect angle was investigated through simulations using sets of synthetic aircraft images. It is shown that increased pose-estimation accuracy can be obtained by breaking the nearest neighbour search procedure in two parts.
Topics
TNO Identifier
95239
Publisher
SPIE
Source title
Proceedings SPIE - Automatic Target Recognition IX, 7-9 April 1999, Orlando, FL
Editor(s)
Sadjadi, F.A.
Place of publication
Bellingham, WA.
Pages
294-304
Files