2002
DOI: 10.1117/12.477039
|View full text |Cite
|
Sign up to set email alerts
|

<title>Problem set guidelines to facilitate ATR research, development, and performance assessments</title>

Abstract: In November of 2000, the Deputy Under Secretary of Defense for Science and Technology Sensor Systems (DUSD (S&T/SS)) chartered the Automatic Target Recognizer Working Group (ATRWG) to develop guidelines for sanctioned Problem Sets. Such Problem Sets are intended for development and test of Automatic Target Recognition (ATR) algorithms and contain comprehensive documentation of the data in them. A Problem Set provides a consistent basis for examining ATR performance and growth. Problem Sets will, in general, se… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2002
2002
2011
2011

Publication Types

Select...
2
1

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 0 publications
0
2
0
Order By: Relevance
“…Image sets which could be used by universities, research laboratories, and international partners would facilitate the exploration of new ATR methods. The goal of this effort was to produce a large data set for ATR development and evaluation, conforming to the established standards for an ATR problem set [1]. Important elements of the process are to maintain high level of control over the imaging conditions and provide precise, accurate image truth along with the image set.…”
Section: Introductionmentioning
confidence: 99%
“…Image sets which could be used by universities, research laboratories, and international partners would facilitate the exploration of new ATR methods. The goal of this effort was to produce a large data set for ATR development and evaluation, conforming to the established standards for an ATR problem set [1]. Important elements of the process are to maintain high level of control over the imaging conditions and provide precise, accurate image truth along with the image set.…”
Section: Introductionmentioning
confidence: 99%
“…This is the ATR Working Group. 25 Sanctioned problem sets permit the establishment of universal metrics to assess algorithm performance collectively and scientifically. The same problem set can be used to test any number of candidate algorithms and permits quantifiable difference measurements across all candidates.…”
Section: Imagery Data Setmentioning
confidence: 99%