&lt;title&gt;Characterization of ATR systems&lt;/title&gt;

Zelnio, Edmund G.; Garber, Frederick; Westerkamp, Lori A.; Worrell, Steven W.; Westerkamp, John J.; Jarratt, Mary; Deardorf, Catherine E.; Ryan, Patricia A.

doi:10.1117/12.281560

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1997 paper by a host of SNA affiliated researchers. 2 The five issues developed here are not comprehensive nor even the top five, but perhaps they are of some importance and identifying them will help draw the attention of those better equipped to resolve them. Statistical Pattern Recognition (SPR) provides a broad foundation for an ATR Theory, but does not provide the basis for ATR work in near the same way that, for example, estimation theory does tracking.…”

Section: Introductionmentioning

confidence: 97%

“…We call these "monolithic architecture (MA)-ATR" theories as a minor generalization of what was referred to as SPR in Zelnio'97. 2,3 The first issue, that an extensive, sophisticated and highly applicable body of foundational theories exists and should be fully exploited for ATR Theory, is developed in Section 2. We are also interested in what we call "aggregate architecture (AA)-ATR", where sensor, target, and environment modeling are used within a search paradigm to construct an ATR.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

<title>ATR theory issues</title>

Ross

2004

SPIE Proceedings

View full text Add to dashboard Cite

Issues in ATR Theory emerge by considering three levels of the ATR problem. The term "monolithic architecture (MA)-ATR" is used for problems of standard classification theory. The MA-ATR level has seen recent unification of theories that should be aggressively applied. Modern ATR systems include standard classification theoretic subsystems (e.g., feature extraction, matching, and discrimination); however they also add modeling within a search paradigm. These "aggregate architecture (AA)-ATRs" allow more direct inclusion of application-specific prior (non-sample) knowledge. Greater theoretical support is needed for analyzing AA-ATRs at the system level and integrating the strong MA-ATR theories. The third level of the ATR problem returns to the MA-ATR problem and below. The strongest elements of the MA-ATR theories deal with the stochastic aspects of the ATR problem. Structural aspects of ATRs are an important weak link in the MA-ATR theories. Function decomposition provides an "atom" towards a structural theory. Decomposition provides robustness by constructing the MA-ATR's structure from samples, but is intractable. Standard MA-ATR design is tractable, but is brittle because of an ad hoc structure selection. The key issue in either case is to make explicit use of non-sample (typically structural) knowledge in selecting or, better yet, constructing the MA-ATR's structure.

show abstract

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

<title>ATR theory issues</title>

Ross

2004

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…Subsequently there is dramatic reduction in the related ATR performance which does not degrade gracefully. These are referred to as Extended Operating Conditions (EOC) [11] and the related technical challenge is the development of robust ATR systems [16] [21].…”

Section: Introductionmentioning

confidence: 99%

XCS for robust automatic target recognition

Ravichandran

Gandhe

Smith

2005

Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

A primary strength of the XCS approach is its ability to create maximally accurate general rules. In automatic target recognition (ATR) there is a need for robust performance beyond so-called standard operating conditions (SOCs, those conditions for which training data is available) to extended operating conditions (EOCs, conditions of known targets that cannot be foreseen and trained for). EOCs include things like vehicle-specific variations, environmental effects (mud, etc.), unanticipated viewing angles, and articulation of components of the target (hatches, turrets, etc.). This paper presents experiments where XCS addresses structural generalization over global and local features normally used in ATR classification. In many SOCs, these features are adequate for target recognition. Our goal with XCS is to form generalized rules that utilize these features for effective ATR in EOCs. Results show that XCS is effective in this generalization task. Conclusions and future directions for research are discussed.

show abstract

“…The issue of the target signature set has been well documented. 24 These requirements then imply the generation of a library of IR imagery, which is, typically, classified. Not only is the imagery classified, but the sensor parameters for the gathering device are classified.…”

Section: Imagery Data Setmentioning

confidence: 99%

Review of current aided/automatic target acquisition technology for military target acquisition tasks

Ratches

2011

Opt. Eng

View full text Add to dashboard Cite

Abstract. Aided and automatic target recognition (Ai/ATR) capability is a critical technology needed by the military services for modern combat. However, the current level of performance that is available is largely deficient compared to the requirements. This is largely due to the difficulty of acquiring targets in realistic environments but has also been due to the difficulty in getting new concepts from, for example, the academic community, due to limitations for distribution of classified data. The difficulty of the performance required has limited the fulfillment of the promise that is so anticipated by the war fighter. We review the metrics, imagery data bases, and sensors associated with Ai/ATR performance and suggest possible technical approaches that could enable new advancements in military-relevant performance. C 2011 Society of Photo-Optical Instrumentation Engineers (SPIE).

show abstract

<title>Characterization of ATR systems</title>

Cited by 3 publications

References 0 publications

<title>ATR theory issues</title>

<title>ATR theory issues</title>

XCS for robust automatic target recognition

Review of current aided/automatic target acquisition technology for military target acquisition tasks

Contact Info

Product

Resources

About