Share Email Print
cover

Proceedings Paper

Aerial image registration incorporating GPS/IMU data
Author(s): Keith A. Redmill; John I. Martin; Umit Ozguner
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We describe a methodology for multiframe image registration of airborne high resolution, multi-camera imagery. In the absence of predetermined camera and lens models, parameters are optimally determined from imagery and known ground reference locations. GPS and IMU data collected from the sensor platform and the identified camera model parameters are used to perform an initial orthorectification and georeferencing of each image. Multiple KLT, Sift, or featureless point-match correspondences are identified and validated using RANSAC techniques. Affine transform hypothesis are then generated, inconsistent hypothesis are removed using a RANSAC approach, and a final optimal transform is generated as the least squares optimal fit of the remaining correspondences. To eliminate long-term drift, key frames are selected and cross-registered. Performance improvements can also be demonstrated using a mask to eliminate correspondences not on the ground plane. This approach is illustrated using the 2007 AFRL Columbus Large Image Format dataset.

Paper Details

Date Published: 29 April 2009
PDF: 15 pages
Proc. SPIE 7347, Evolutionary and Bio-Inspired Computation: Theory and Applications III, 73470H (29 April 2009); doi: 10.1117/12.820201
Show Author Affiliations
Keith A. Redmill, The Ohio State Univ. (United States)
John I. Martin, The Ohio State Univ. (United States)
Umit Ozguner, The Ohio State Univ. (United States)


Published in SPIE Proceedings Vol. 7347:
Evolutionary and Bio-Inspired Computation: Theory and Applications III
Teresa H. O'Donnell; Misty Blowers; Kevin L. Priddy, Editor(s)

© SPIE. Terms of Use
Back to Top