Toward interactive search in remote sensing imagery
Abstract
To move from data to information in almost all science and defense applications requires a human-in-the-loop to validate information products, resolve inconsistencies, and account for incomplete and potentially deceptive sources of information. This is a key motivation for visual analytics which aims to develop techniques that complement and empower human users. By contrast, the vast majority of algorithms developed in machine learning aim to replace human users in data exploitation. In this paper we describe a recently introduced machine learning problem, called rare category detection, which may be a better match to visual analytic environments. We describe a new design criteria for this problem, and present comparisons to existing techniques with both synthetic and real-world datasets. We conclude by describing an application in broad-area search of remote sensing imagery.
- Authors:
-
- Los Alamos National Laboratory
- Publication Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 993113
- Report Number(s):
- LA-UR-10-01385; LA-UR-10-1385
Journal ID: ISSN 0277-786X; TRN: US201023%%233
- DOE Contract Number:
- AC52-06NA25396
- Resource Type:
- Conference
- Resource Relation:
- Journal Volume: 7709; Conference: SPIE Defense, Security and Sensing 2010 ; April 5, 2010 ; Orlando, FL
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 99 GENERAL AND MISCELLANEOUS; ALGORITHMS; DESIGN; DETECTION; LEARNING; REMOTE SENSING; SECURITY
Citation Formats
Porter, Reid B, Hush, Do, Harvey, Neal, and Theile, James. Toward interactive search in remote sensing imagery. United States: N. p., 2010.
Web. doi:10.1117/12.850787.
Porter, Reid B, Hush, Do, Harvey, Neal, & Theile, James. Toward interactive search in remote sensing imagery. United States. https://doi.org/10.1117/12.850787
Porter, Reid B, Hush, Do, Harvey, Neal, and Theile, James. 2010.
"Toward interactive search in remote sensing imagery". United States. https://doi.org/10.1117/12.850787. https://www.osti.gov/servlets/purl/993113.
@article{osti_993113,
title = {Toward interactive search in remote sensing imagery},
author = {Porter, Reid B and Hush, Do and Harvey, Neal and Theile, James},
abstractNote = {To move from data to information in almost all science and defense applications requires a human-in-the-loop to validate information products, resolve inconsistencies, and account for incomplete and potentially deceptive sources of information. This is a key motivation for visual analytics which aims to develop techniques that complement and empower human users. By contrast, the vast majority of algorithms developed in machine learning aim to replace human users in data exploitation. In this paper we describe a recently introduced machine learning problem, called rare category detection, which may be a better match to visual analytic environments. We describe a new design criteria for this problem, and present comparisons to existing techniques with both synthetic and real-world datasets. We conclude by describing an application in broad-area search of remote sensing imagery.},
doi = {10.1117/12.850787},
url = {https://www.osti.gov/biblio/993113},
journal = {},
issn = {0277-786X},
number = ,
volume = 7709,
place = {United States},
year = {Fri Jan 01 00:00:00 EST 2010},
month = {Fri Jan 01 00:00:00 EST 2010}
}