Design of benchmark imagery for validating facility annotation algorithms

Randy S. Roberts; Paul A. Pope; Raju R. Vatsavai; Ming Jiang; Lloyd F. Arrowood; Timothy G. Trucano; Shaun Gleason; Anil Cheriyadat; Alex Sorokine; Aggelos K. Katsaggelos; Thrasyvoulos N. Pappas; Lucinda R. Gaines; Lawrence K. Chilton

doi:10.1109/IGARSS.2011.6049340

Design of benchmark imagery for validating facility annotation algorithms

Randy S. Roberts, Paul A. Pope, Raju R. Vatsavai, Ming Jiang, Lloyd F. Arrowood, Timothy G. Trucano, Shaun Gleason, Anil Cheriyadat, Alex Sorokine, Aggelos K. Katsaggelos, Thrasyvoulos N. Pappas, Lucinda R. Gaines, Lawrence K. Chilton

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

The design of benchmark imagery for validation of image annotation algorithms is considered. Emphasis is placed on imagery that contains industrial facilities, such as chemical refineries. An application-level facility ontology is used as a means to define salient objects in the benchmark imagery. In-strinsic and extrinsic scene factors important for comprehensive validation are listed, and variability in the benchmarks discussed. Finally, the pros and cons of three forms of benchmark imagery: real, composite and synthetic, are delineated.

Original language	English
Title of host publication	2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings
Pages	1453-1456
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2011.6049340
State	Published - 2011
Event	2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Vancouver, BC, Canada Duration: Jul 24 2011 → Jul 29 2011

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)

Conference

Conference	2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011
Country/Territory	Canada
City	Vancouver, BC
Period	07/24/11 → 07/29/11

Keywords

Algorithm validation
Benchmark imagery
Benchmark variability
Ontology
Real annotated imagery
Validation using synthetic imagery

Access to Document

10.1109/IGARSS.2011.6049340

Cite this

Roberts, R. S., Pope, P. A., Vatsavai, R. R., Jiang, M., Arrowood, L. F., Trucano, T. G., Gleason, S., Cheriyadat, A., Sorokine, A., Katsaggelos, A. K., Pappas, T. N., Gaines, L. R., & Chilton, L. K. (2011). Design of benchmark imagery for validating facility annotation algorithms. In 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings (pp. 1453-1456). Article 6049340 (International Geoscience and Remote Sensing Symposium (IGARSS)). https://doi.org/10.1109/IGARSS.2011.6049340

@inproceedings{3dbd1c784b4e41a1895ac3a634a23385,

title = "Design of benchmark imagery for validating facility annotation algorithms",

abstract = "The design of benchmark imagery for validation of image annotation algorithms is considered. Emphasis is placed on imagery that contains industrial facilities, such as chemical refineries. An application-level facility ontology is used as a means to define salient objects in the benchmark imagery. In-strinsic and extrinsic scene factors important for comprehensive validation are listed, and variability in the benchmarks discussed. Finally, the pros and cons of three forms of benchmark imagery: real, composite and synthetic, are delineated.",

keywords = "Algorithm validation, Benchmark imagery, Benchmark variability, Ontology, Real annotated imagery, Validation using synthetic imagery",

author = "Roberts, {Randy S.} and Pope, {Paul A.} and Vatsavai, {Raju R.} and Ming Jiang and Arrowood, {Lloyd F.} and Trucano, {Timothy G.} and Shaun Gleason and Anil Cheriyadat and Alex Sorokine and Katsaggelos, {Aggelos K.} and Pappas, {Thrasyvoulos N.} and Gaines, {Lucinda R.} and Chilton, {Lawrence K.}",

year = "2011",

doi = "10.1109/IGARSS.2011.6049340",

language = "English",

isbn = "9781457710056",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

pages = "1453--1456",

booktitle = "2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings",

note = "2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 ; Conference date: 24-07-2011 Through 29-07-2011",

}

Roberts, RS, Pope, PA, Vatsavai, RR, Jiang, M, Arrowood, LF, Trucano, TG, Gleason, S, Cheriyadat, A, Sorokine, A, Katsaggelos, AK, Pappas, TN, Gaines, LR & Chilton, LK 2011, Design of benchmark imagery for validating facility annotation algorithms. in 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings., 6049340, International Geoscience and Remote Sensing Symposium (IGARSS), pp. 1453-1456, 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011, Vancouver, BC, Canada, 07/24/11. https://doi.org/10.1109/IGARSS.2011.6049340

Design of benchmark imagery for validating facility annotation algorithms. / Roberts, Randy S.; Pope, Paul A.; Vatsavai, Raju R. et al.
2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings. 2011. p. 1453-1456 6049340 (International Geoscience and Remote Sensing Symposium (IGARSS)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Design of benchmark imagery for validating facility annotation algorithms

AU - Roberts, Randy S.

AU - Pope, Paul A.

AU - Vatsavai, Raju R.

AU - Jiang, Ming

AU - Arrowood, Lloyd F.

AU - Trucano, Timothy G.

AU - Gleason, Shaun

AU - Cheriyadat, Anil

AU - Sorokine, Alex

AU - Katsaggelos, Aggelos K.

AU - Pappas, Thrasyvoulos N.

AU - Gaines, Lucinda R.

AU - Chilton, Lawrence K.

PY - 2011

Y1 - 2011

N2 - The design of benchmark imagery for validation of image annotation algorithms is considered. Emphasis is placed on imagery that contains industrial facilities, such as chemical refineries. An application-level facility ontology is used as a means to define salient objects in the benchmark imagery. In-strinsic and extrinsic scene factors important for comprehensive validation are listed, and variability in the benchmarks discussed. Finally, the pros and cons of three forms of benchmark imagery: real, composite and synthetic, are delineated.

AB - The design of benchmark imagery for validation of image annotation algorithms is considered. Emphasis is placed on imagery that contains industrial facilities, such as chemical refineries. An application-level facility ontology is used as a means to define salient objects in the benchmark imagery. In-strinsic and extrinsic scene factors important for comprehensive validation are listed, and variability in the benchmarks discussed. Finally, the pros and cons of three forms of benchmark imagery: real, composite and synthetic, are delineated.

KW - Algorithm validation

KW - Benchmark imagery

KW - Benchmark variability

KW - Ontology

KW - Real annotated imagery

KW - Validation using synthetic imagery

UR - http://www.scopus.com/inward/record.url?scp=80955149460&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2011.6049340

DO - 10.1109/IGARSS.2011.6049340

M3 - Conference contribution

AN - SCOPUS:80955149460

SN - 9781457710056

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 1453

EP - 1456

BT - 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings

T2 - 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011

Y2 - 24 July 2011 through 29 July 2011

ER -

Roberts RS, Pope PA, Vatsavai RR, Jiang M, Arrowood LF, Trucano TG et al. Design of benchmark imagery for validating facility annotation algorithms. In 2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings. 2011. p. 1453-1456. 6049340. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS.2011.6049340

Design of benchmark imagery for validating facility annotation algorithms

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this