Overhead-Based Image and Video Geo-localization Framework

Author

Hammoud, Riad I. ; Kuzdeba, Scott A. ; Berard, Brian ; Tom, Victor ; Ivey, Richard ; Bostwick, Renu ; HandUber, Jason ; Vinciguerra, Lori ; Shnidman, Nathan ; Smiley, Byron

Author_Institution

BAE Syst., Burlington, MA, USA

fYear

2013

fDate

23-28 June 2013

Firstpage

320

Lastpage

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, 000km²) in the USA.

Keywords

digital elevation models; geographic information systems; geophysical image processing; optical radar; probability; rendering (computer graphics); terrain mapping; video signal processing; LIDAR; adaptive linear fusion process; building heights; digital elevation maps; individual matcher probability maps; landmarks; landuse classes; mountain elevation profiles; multispectral land cover/use imagery; overhead reference imagery; overhead-based image geo-localization; overhead-based video geo-localization framework; rendered camera views; street-level outdoor images; Buildings; Cameras; Data mining; Impedance matching; Kernel; Knowledge based systems; Laser radar; fusion; geo-localization; image search; matching;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition Workshops (CVPRW), 2013 IEEE Conference on

Conference_Location

Portland, OR

Type

conf

DOI

10.1109/CVPRW.2013.55

Filename

6595894