Share Email Print

Proceedings Paper

Semantically enabled image similarity search
Author(s): May V. Casterline; Timothy Emerick; Kolia Sadeghi; C. Alec Gosse; Brent Bartlett; Jason Casey
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Georeferenced data of various modalities are increasingly available for intelligence and commercial use, however effectively exploiting these sources demands a unified data space capable of capturing the unique contribution of each input. This work presents a suite of software tools for representing geospatial vector data and overhead imagery in a shared high-dimension vector or embedding" space that supports fused learning and similarity search across dissimilar modalities. While the approach is suitable for fusing arbitrary input types, including free text, the present work exploits the obvious but computationally difficult relationship between GIS and overhead imagery. GIS is comprised of temporally-smoothed but information-limited content of a GIS, while overhead imagery provides an information-rich but temporally-limited perspective. This processing framework includes some important extensions of concepts in literature but, more critically, presents a means to accomplish them as a unified framework at scale on commodity cloud architectures.

Paper Details

Date Published: 21 May 2015
PDF: 15 pages
Proc. SPIE 9473, Geospatial Informatics, Fusion, and Motion Video Analytics V, 94730I (21 May 2015); doi: 10.1117/12.2177409
Show Author Affiliations
May V. Casterline, Commonwealth Computer Research, Inc. (United States)
Timothy Emerick, Commonwealth Computer Research, Inc. (United States)
Kolia Sadeghi, Commonwealth Computer Research, Inc. (United States)
C. Alec Gosse, Commonwealth Computer Research, Inc. (United States)
Brent Bartlett, Eidetic Technologies, LLC (United States)
Jason Casey, Eidetic Technologies, LLC (United States)

Published in SPIE Proceedings Vol. 9473:
Geospatial Informatics, Fusion, and Motion Video Analytics V
Matthew F. Pellechia; Kannappan Palaniappan; Peter J. Doucette; Shiloh L. Dockstader; Gunasekaran Seetharaman; Paul B. Deignan, Editor(s)

© SPIE. Terms of Use
Back to Top