Overhead-Based Image and Video Geo-Localization Framework (Open Access)

reportActive / Technical Report | Accession Number: AD1039707 | Open PDF

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 CoverUse 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 squared in the USA.

Author(s):
Hammoud, Riad I. ; Kuzdeba, Scott A. ; Berard, Brian ; Tom, Victor ; Ivey, Richard ; Bostwick, Renu ; Handuber, Jason ; Vinciguerra, Lori ; Shnidman, Nathan ; Smiley, Byron
Author Organization(s):
BAE Systems Burlington United States
Descriptive Note:
Conference Paper
Supplementary Note:
2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) , 23 Jun 2013, 28 Jun 2013,
Pagination:
0008

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release;

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
IARPA/DC
 Subject Terms
Joint Capability Areas:
JCA_5_Command and Control; JCA_5.2.2_Develop Knowledge and Situational Awareness; JCA_5.2_Understand; JCA_3.2_Engagement; JCA_3_Force Application; JCA_5.6.1_Assess Compliance with Guidance; JCA_5.6_Monitor; JCA_1.2.5_Lessons Learned; JCA_3.2.1_Kinetic Means; JCA_5.3_Planning
Modernization Areas:
AI and Machine Learning
Communities of Interest:
No COI(s) Identified
Descriptor(s):
computer vision, pattern recognition, atmospheric attenuation, mountains, elevation, probability, classification, coastal regions, attenuation, kernel functions, data mining, impedance, knowledge based systems, image processing, data fusion, laser radar, cameras, BUILDINGS AND STRUCTURES, DIGITAL MAPS
Field(s)/Group(s):
Cybernetics, Cartography and Aerial Photography
Keyword(s):
IARPA Collection, impedance matching, search, geo localization
Report Date:
2013 Sep 12
Creation Date:
2017 Oct 30