Overhead-Based Image and Video Geo-localization Framework

Riad I. Hammoud, Scott A. Kuzdeba, Brian Berard, Victor Tom, Richard Ivey, Renu Bostwick, Jason HandUber, Lori Vinciguerra, Nathan Shnidman, Byron Smiley; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2013, pp. 320-327

Abstract


This paper presents a geo-localization framework of street-level outdoor images using multiple sources of overhead reference imagery including LIDAR, Digital Elevation Maps and Multi-Spectral Land Cover/Use imagery. We describe five different matchers and an adaptive linear fusion process which combines individual matchers' probability maps into a single map. These matchers exploit mountain elevation profiles, rendered camera views, landmarks, landuse classes and building heights. We successfully validated our framework on 100 queries with geographic truth in two world regions (each of 10, 000km hg) in the USA.

Related Material


[pdf]
[bibtex]
@InProceedings{Hammoud_2013_CVPR_Workshops,
author = {Hammoud, Riad I. and Kuzdeba, Scott A. and Berard, Brian and Tom, Victor and Ivey, Richard and Bostwick, Renu and HandUber, Jason and Vinciguerra, Lori and Shnidman, Nathan and Smiley, Byron},
title = {Overhead-Based Image and Video Geo-localization Framework},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2013}
}