A synthetic dataset for evaluating soft and hard fusion algorithms

Jacob L. Graham, David L. Hall, Jeffrey Rimland

Research output: Chapter in Book/Report/Conference proceedingConference contribution

22 Citations (Scopus)

Abstract

There is an emerging demand for the development of data fusion techniques and algorithms that are capable of combining conventional "hard" sensor inputs such as video, radar, and multispectral sensor data with "soft" data including textual situation reports, open-source web information, and "hard/soft" data such as image or video data that includes human-generated annotations. New techniques that assist in sense-making over a wide range of vastly heterogeneous sources are critical to improving tactical situational awareness in counterinsurgency (COIN) and other asymmetric warfare situations. A major challenge in this area is the lack of realistic datasets available for test and evaluation of such algorithms. While "soft" message sets exist, they tend to be of limited use for data fusion applications due to the lack of critical message pedigree and other metadata. They also lack corresponding hard sensor data that presents reasonable "fusion opportunities" to evaluate the ability to make connections and inferences that span the soft and hard data sets. This paper outlines the design methodologies, content, and some potential use cases of a COIN-based synthetic soft and hard dataset created under a United States Multi-disciplinary University Research Initiative (MURI) program funded by the U.S. Army Research Office (ARO). The dataset includes realistic synthetic reports from a variety of sources, corresponding synthetic hard data, and an extensive supporting database that maintains "ground truth" through logical grouping of related data into "vignettes."The supporting database also maintains the pedigree of messages and other critical metadata.

Original languageEnglish (US)
Title of host publicationDefense Transformation and Net-Centric Systems 2011
DOIs
StatePublished - Jun 27 2011
EventDefense Transformation and Net-Centric Systems 2011 - Orlando, FL, United States
Duration: Apr 27 2011Apr 28 2011

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8062
ISSN (Print)0277-786X

Other

OtherDefense Transformation and Net-Centric Systems 2011
CountryUnited States
CityOrlando, FL
Period4/27/114/28/11

Fingerprint

messages
metadata
Fusion
fusion
multisensor fusion
Data fusion
Metadata
sensors
Sensors
annotations
warfare
video data
situational awareness
ground truth
Military operations
inference
Pedigree
radar
emerging
Data Fusion

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Graham, J. L., Hall, D. L., & Rimland, J. (2011). A synthetic dataset for evaluating soft and hard fusion algorithms. In Defense Transformation and Net-Centric Systems 2011 [80620F] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8062). https://doi.org/10.1117/12.884042
Graham, Jacob L. ; Hall, David L. ; Rimland, Jeffrey. / A synthetic dataset for evaluating soft and hard fusion algorithms. Defense Transformation and Net-Centric Systems 2011. 2011. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{86e893fffd464e04b4567b24278b79f1,
title = "A synthetic dataset for evaluating soft and hard fusion algorithms",
abstract = "There is an emerging demand for the development of data fusion techniques and algorithms that are capable of combining conventional {"}hard{"} sensor inputs such as video, radar, and multispectral sensor data with {"}soft{"} data including textual situation reports, open-source web information, and {"}hard/soft{"} data such as image or video data that includes human-generated annotations. New techniques that assist in sense-making over a wide range of vastly heterogeneous sources are critical to improving tactical situational awareness in counterinsurgency (COIN) and other asymmetric warfare situations. A major challenge in this area is the lack of realistic datasets available for test and evaluation of such algorithms. While {"}soft{"} message sets exist, they tend to be of limited use for data fusion applications due to the lack of critical message pedigree and other metadata. They also lack corresponding hard sensor data that presents reasonable {"}fusion opportunities{"} to evaluate the ability to make connections and inferences that span the soft and hard data sets. This paper outlines the design methodologies, content, and some potential use cases of a COIN-based synthetic soft and hard dataset created under a United States Multi-disciplinary University Research Initiative (MURI) program funded by the U.S. Army Research Office (ARO). The dataset includes realistic synthetic reports from a variety of sources, corresponding synthetic hard data, and an extensive supporting database that maintains {"}ground truth{"} through logical grouping of related data into {"}vignettes.{"}The supporting database also maintains the pedigree of messages and other critical metadata.",
author = "Graham, {Jacob L.} and Hall, {David L.} and Jeffrey Rimland",
year = "2011",
month = "6",
day = "27",
doi = "10.1117/12.884042",
language = "English (US)",
isbn = "9780819486363",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Defense Transformation and Net-Centric Systems 2011",

}

Graham, JL, Hall, DL & Rimland, J 2011, A synthetic dataset for evaluating soft and hard fusion algorithms. in Defense Transformation and Net-Centric Systems 2011., 80620F, Proceedings of SPIE - The International Society for Optical Engineering, vol. 8062, Defense Transformation and Net-Centric Systems 2011, Orlando, FL, United States, 4/27/11. https://doi.org/10.1117/12.884042

A synthetic dataset for evaluating soft and hard fusion algorithms. / Graham, Jacob L.; Hall, David L.; Rimland, Jeffrey.

Defense Transformation and Net-Centric Systems 2011. 2011. 80620F (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8062).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A synthetic dataset for evaluating soft and hard fusion algorithms

AU - Graham, Jacob L.

AU - Hall, David L.

AU - Rimland, Jeffrey

PY - 2011/6/27

Y1 - 2011/6/27

N2 - There is an emerging demand for the development of data fusion techniques and algorithms that are capable of combining conventional "hard" sensor inputs such as video, radar, and multispectral sensor data with "soft" data including textual situation reports, open-source web information, and "hard/soft" data such as image or video data that includes human-generated annotations. New techniques that assist in sense-making over a wide range of vastly heterogeneous sources are critical to improving tactical situational awareness in counterinsurgency (COIN) and other asymmetric warfare situations. A major challenge in this area is the lack of realistic datasets available for test and evaluation of such algorithms. While "soft" message sets exist, they tend to be of limited use for data fusion applications due to the lack of critical message pedigree and other metadata. They also lack corresponding hard sensor data that presents reasonable "fusion opportunities" to evaluate the ability to make connections and inferences that span the soft and hard data sets. This paper outlines the design methodologies, content, and some potential use cases of a COIN-based synthetic soft and hard dataset created under a United States Multi-disciplinary University Research Initiative (MURI) program funded by the U.S. Army Research Office (ARO). The dataset includes realistic synthetic reports from a variety of sources, corresponding synthetic hard data, and an extensive supporting database that maintains "ground truth" through logical grouping of related data into "vignettes."The supporting database also maintains the pedigree of messages and other critical metadata.

AB - There is an emerging demand for the development of data fusion techniques and algorithms that are capable of combining conventional "hard" sensor inputs such as video, radar, and multispectral sensor data with "soft" data including textual situation reports, open-source web information, and "hard/soft" data such as image or video data that includes human-generated annotations. New techniques that assist in sense-making over a wide range of vastly heterogeneous sources are critical to improving tactical situational awareness in counterinsurgency (COIN) and other asymmetric warfare situations. A major challenge in this area is the lack of realistic datasets available for test and evaluation of such algorithms. While "soft" message sets exist, they tend to be of limited use for data fusion applications due to the lack of critical message pedigree and other metadata. They also lack corresponding hard sensor data that presents reasonable "fusion opportunities" to evaluate the ability to make connections and inferences that span the soft and hard data sets. This paper outlines the design methodologies, content, and some potential use cases of a COIN-based synthetic soft and hard dataset created under a United States Multi-disciplinary University Research Initiative (MURI) program funded by the U.S. Army Research Office (ARO). The dataset includes realistic synthetic reports from a variety of sources, corresponding synthetic hard data, and an extensive supporting database that maintains "ground truth" through logical grouping of related data into "vignettes."The supporting database also maintains the pedigree of messages and other critical metadata.

UR - http://www.scopus.com/inward/record.url?scp=79959402935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959402935&partnerID=8YFLogxK

U2 - 10.1117/12.884042

DO - 10.1117/12.884042

M3 - Conference contribution

AN - SCOPUS:79959402935

SN - 9780819486363

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Defense Transformation and Net-Centric Systems 2011

ER -

Graham JL, Hall DL, Rimland J. A synthetic dataset for evaluating soft and hard fusion algorithms. In Defense Transformation and Net-Centric Systems 2011. 2011. 80620F. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.884042