TY - JOUR
T1 - ARKTOS
T2 - An intelligent system for SAR sea ice image classification
AU - Soh, Leen Kiat
AU - Tsatsoulis, Costas
AU - Gineris, Denise
AU - Bertoia, Cheryl
N1 - Funding Information:
Manuscript received December 18, 2002; revised June 14, 2003. This work was supported in part by the Naval Research Laboratory under Grant N00014-95-C-6038. L.-K. Soh is with the Department of Computer Science and Engineering, University of Nebraska, Lincoln, NE 68588-0115 USA (e-mail: [email protected]). C. Tsatsoulis is with the Department of Electrical Engineering and Computer Science, Information and Telecommunication Technology Center, University of Kansas, Lawrence, KS 66045 USA. D. Gineris is with Veridian Systems Division, Inc., Ann Arbor, MI 48113 USA. C. Bertoia is with the National Ice Center, Washington, DC 20395 USA. Digital Object Identifier 10.1109/TGRS.2003.817819
PY - 2004/1
Y1 - 2004/1
N2 - We present an intelligent system for satellite sea ice image analysis named Advanced Reasoning using Knowledge for Typing Of Sea ice (ARKTOS). ARKTOS performs fully automated analysis of synthetic aperture radar (SAR) sea ice images by mimicking the reasoning process of sea ice experts. ARKTOS automatically segments a SAR image of sea ice, generates descriptors for the segments of the image, and then uses expert system rules to classify these sea ice features. ARKTOS also utilizes multisource data fusion to improve classification and performs belief handling using Dempster-Shafer. As a software package, ARKTOS comprises components in image processing, rule-based classification, multisource data fusion, and graphical user interface-based knowledge engineering and modification. As a research project over the past ten years, ARKTOS has undergone phases such as knowledge acquisition, prototyping, refinement, evaluation, deployment, and operationalization at the U.S. National Ice Center. In this paper, we focus on the methodology, evaluations, and classification results of ARKTOS.
AB - We present an intelligent system for satellite sea ice image analysis named Advanced Reasoning using Knowledge for Typing Of Sea ice (ARKTOS). ARKTOS performs fully automated analysis of synthetic aperture radar (SAR) sea ice images by mimicking the reasoning process of sea ice experts. ARKTOS automatically segments a SAR image of sea ice, generates descriptors for the segments of the image, and then uses expert system rules to classify these sea ice features. ARKTOS also utilizes multisource data fusion to improve classification and performs belief handling using Dempster-Shafer. As a software package, ARKTOS comprises components in image processing, rule-based classification, multisource data fusion, and graphical user interface-based knowledge engineering and modification. As a research project over the past ten years, ARKTOS has undergone phases such as knowledge acquisition, prototyping, refinement, evaluation, deployment, and operationalization at the U.S. National Ice Center. In this paper, we focus on the methodology, evaluations, and classification results of ARKTOS.
KW - Data fusion
KW - Dempster-Shafer belief theory
KW - Intelligent image analysis
KW - Rule-based system
KW - Sea ice classification
UR - http://www.scopus.com/inward/record.url?scp=1242331303&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=1242331303&partnerID=8YFLogxK
U2 - 10.1109/TGRS.2003.817819
DO - 10.1109/TGRS.2003.817819
M3 - Article
AN - SCOPUS:1242331303
SN - 0196-2892
VL - 42
SP - 229
EP - 248
JO - IEEE Transactions on Geoscience and Remote Sensing
JF - IEEE Transactions on Geoscience and Remote Sensing
IS - 1
ER -