Efficient registration of aerial image sequences without camera priors

Authors:
Shobhit Niranjan;Gaurav Gupta;Amitabha Mukerjee;Sumana Gupta
Affiliations:
Indian Institute of Technology Kanpur, India and Aurora Integrated Systems, Kanpur, India;Aurora Integrated Systems, Kanpur, India;Indian Institute of Technology Kanpur, India;Indian Institute of Technology Kanpur, India
Venue:
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Year:
2007

Citing 6
Cited 2

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Using geometric corners to build a 2D mosaic from a set of image

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Models of bottom-up and top-down visual attention

Models of bottom-up and top-down visual attention
Recognising Panoramas

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Automatic Aerial Image RegistrationWithout Correspondence

ICVS '06 Proceedings of the Fourth IEEE International Conference on Computer Vision Systems
A contour-based approach to multisensor image registration

IEEE Transactions on Image Processing

Robust Registration of Aerial Image Sequences

ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
The registration of UAV down-looking aerial images to satellite images with image entropy and edges

ICIRA'10 Proceedings of the Third international conference on Intelligent robotics and applications - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an efficient approach for finding homographies between sequences of aerial images. We propose a two-step approach: a) initially solving for image-plane rotation and scale parameters without using correspondence (under affine assumption), and b) using these parameters to constrain the full homography search, and c) extending the results to full perspective projection. No flight meta-data, camera priors, or any other user defined information is used for the task. Based on the perspective parameters estimated, the aerial images are stitched with the best matching image based on a probabilistic model, to compose a high resolution aerial image mosaic. While retaining the improved asymptotic worst-case complexity of [6], we demonstrate significant performance improvements in practice.