Damage pattern mining in Hurricane image databases

Shu Ching Chen, Mei-Ling Shyu, Chengcui Zhang, Walter Z. Tang, Keqi Zhang

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

4 Citations (Scopus)

Abstract

We present a damage pattern mining framework for hurricane data on residential houses using aerial photographs with 1: 3000 based scale. The vertical photographs are normally collected for an overview of a disaster area or f or more detailed assessment. Damage on roof, especially for shingles torn off, is expected to be discovered in a more efficient and automatic way instead of going through the high-resolution aerial photograph for numerous details. The discovered damage patterns can then be used for hurricane damage assessment and impacts on different geographical areas. Our methodology is: (1) applying a novel and effective segmentation method on each residential house on the aerial photograph of one community, (2) using the segmentation results to obtain a set of indexing parameters for each house representing the damage level of roof cladding as well as the patterns of damage, (3) using these parameters to select several templates representing the damage patterns so that users can issue query-by-example (QBE) queries. The proposed segmentation method is an unsupervised simultaneous partition and class parameter estimation algorithm that considers the problem of segmentation as a joint estimation of the partition and class parameter variables. By utilizing this segmentation method, the indexing parameters can be obtained automatically. The QBE capability can assist in finding similar damage patterns on the roof of the residential houses in different locations in the image databases. Experiments based on the aerial photographs of Hurricane Andrew in 1992 are conducted and analyzed to show the effectiveness of the proposed Hurricane damage pattern mining framework.

Original languageEnglish (US)
Title of host publicationProceedings of the 2003 IEEE International Conference on Information Reuse and Integration, IRI 2003
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages227-234
Number of pages8
ISBN (Print)0780382420, 9780780382428
DOIs
StatePublished - 2003
EventIEEE International Conference on Information Reuse and Integration, IRI 2003 - Las Vegas, United States
Duration: Oct 27 2003Oct 29 2003

Other

OtherIEEE International Conference on Information Reuse and Integration, IRI 2003
CountryUnited States
CityLas Vegas
Period10/27/0310/29/03

Fingerprint

Hurricanes
Roofs
Antennas
Parameter estimation
Disasters
Pattern mining
Damage
Data base
Experiments
Segmentation

Keywords

  • Damage assessment
  • Hurricane Andrew
  • Multimedia data mining
  • QBE (Query by image)
  • Segmentation

ASJC Scopus subject areas

  • Management Information Systems
  • Hardware and Architecture
  • Information Systems
  • Software

Cite this

Chen, S. C., Shyu, M-L., Zhang, C., Tang, W. Z., & Zhang, K. (2003). Damage pattern mining in Hurricane image databases. In Proceedings of the 2003 IEEE International Conference on Information Reuse and Integration, IRI 2003 (pp. 227-234). [1251418] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IRI.2003.1251418

Damage pattern mining in Hurricane image databases. / Chen, Shu Ching; Shyu, Mei-Ling; Zhang, Chengcui; Tang, Walter Z.; Zhang, Keqi.

Proceedings of the 2003 IEEE International Conference on Information Reuse and Integration, IRI 2003. Institute of Electrical and Electronics Engineers Inc., 2003. p. 227-234 1251418.

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

Chen, SC, Shyu, M-L, Zhang, C, Tang, WZ & Zhang, K 2003, Damage pattern mining in Hurricane image databases. in Proceedings of the 2003 IEEE International Conference on Information Reuse and Integration, IRI 2003., 1251418, Institute of Electrical and Electronics Engineers Inc., pp. 227-234, IEEE International Conference on Information Reuse and Integration, IRI 2003, Las Vegas, United States, 10/27/03. https://doi.org/10.1109/IRI.2003.1251418
Chen SC, Shyu M-L, Zhang C, Tang WZ, Zhang K. Damage pattern mining in Hurricane image databases. In Proceedings of the 2003 IEEE International Conference on Information Reuse and Integration, IRI 2003. Institute of Electrical and Electronics Engineers Inc. 2003. p. 227-234. 1251418 https://doi.org/10.1109/IRI.2003.1251418
Chen, Shu Ching ; Shyu, Mei-Ling ; Zhang, Chengcui ; Tang, Walter Z. ; Zhang, Keqi. / Damage pattern mining in Hurricane image databases. Proceedings of the 2003 IEEE International Conference on Information Reuse and Integration, IRI 2003. Institute of Electrical and Electronics Engineers Inc., 2003. pp. 227-234
@inproceedings{f3123cf990644750afbcb19fed1abf3a,
title = "Damage pattern mining in Hurricane image databases",
abstract = "We present a damage pattern mining framework for hurricane data on residential houses using aerial photographs with 1: 3000 based scale. The vertical photographs are normally collected for an overview of a disaster area or f or more detailed assessment. Damage on roof, especially for shingles torn off, is expected to be discovered in a more efficient and automatic way instead of going through the high-resolution aerial photograph for numerous details. The discovered damage patterns can then be used for hurricane damage assessment and impacts on different geographical areas. Our methodology is: (1) applying a novel and effective segmentation method on each residential house on the aerial photograph of one community, (2) using the segmentation results to obtain a set of indexing parameters for each house representing the damage level of roof cladding as well as the patterns of damage, (3) using these parameters to select several templates representing the damage patterns so that users can issue query-by-example (QBE) queries. The proposed segmentation method is an unsupervised simultaneous partition and class parameter estimation algorithm that considers the problem of segmentation as a joint estimation of the partition and class parameter variables. By utilizing this segmentation method, the indexing parameters can be obtained automatically. The QBE capability can assist in finding similar damage patterns on the roof of the residential houses in different locations in the image databases. Experiments based on the aerial photographs of Hurricane Andrew in 1992 are conducted and analyzed to show the effectiveness of the proposed Hurricane damage pattern mining framework.",
keywords = "Damage assessment, Hurricane Andrew, Multimedia data mining, QBE (Query by image), Segmentation",
author = "Chen, {Shu Ching} and Mei-Ling Shyu and Chengcui Zhang and Tang, {Walter Z.} and Keqi Zhang",
year = "2003",
doi = "10.1109/IRI.2003.1251418",
language = "English (US)",
isbn = "0780382420",
pages = "227--234",
booktitle = "Proceedings of the 2003 IEEE International Conference on Information Reuse and Integration, IRI 2003",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Damage pattern mining in Hurricane image databases

AU - Chen, Shu Ching

AU - Shyu, Mei-Ling

AU - Zhang, Chengcui

AU - Tang, Walter Z.

AU - Zhang, Keqi

PY - 2003

Y1 - 2003

N2 - We present a damage pattern mining framework for hurricane data on residential houses using aerial photographs with 1: 3000 based scale. The vertical photographs are normally collected for an overview of a disaster area or f or more detailed assessment. Damage on roof, especially for shingles torn off, is expected to be discovered in a more efficient and automatic way instead of going through the high-resolution aerial photograph for numerous details. The discovered damage patterns can then be used for hurricane damage assessment and impacts on different geographical areas. Our methodology is: (1) applying a novel and effective segmentation method on each residential house on the aerial photograph of one community, (2) using the segmentation results to obtain a set of indexing parameters for each house representing the damage level of roof cladding as well as the patterns of damage, (3) using these parameters to select several templates representing the damage patterns so that users can issue query-by-example (QBE) queries. The proposed segmentation method is an unsupervised simultaneous partition and class parameter estimation algorithm that considers the problem of segmentation as a joint estimation of the partition and class parameter variables. By utilizing this segmentation method, the indexing parameters can be obtained automatically. The QBE capability can assist in finding similar damage patterns on the roof of the residential houses in different locations in the image databases. Experiments based on the aerial photographs of Hurricane Andrew in 1992 are conducted and analyzed to show the effectiveness of the proposed Hurricane damage pattern mining framework.

AB - We present a damage pattern mining framework for hurricane data on residential houses using aerial photographs with 1: 3000 based scale. The vertical photographs are normally collected for an overview of a disaster area or f or more detailed assessment. Damage on roof, especially for shingles torn off, is expected to be discovered in a more efficient and automatic way instead of going through the high-resolution aerial photograph for numerous details. The discovered damage patterns can then be used for hurricane damage assessment and impacts on different geographical areas. Our methodology is: (1) applying a novel and effective segmentation method on each residential house on the aerial photograph of one community, (2) using the segmentation results to obtain a set of indexing parameters for each house representing the damage level of roof cladding as well as the patterns of damage, (3) using these parameters to select several templates representing the damage patterns so that users can issue query-by-example (QBE) queries. The proposed segmentation method is an unsupervised simultaneous partition and class parameter estimation algorithm that considers the problem of segmentation as a joint estimation of the partition and class parameter variables. By utilizing this segmentation method, the indexing parameters can be obtained automatically. The QBE capability can assist in finding similar damage patterns on the roof of the residential houses in different locations in the image databases. Experiments based on the aerial photographs of Hurricane Andrew in 1992 are conducted and analyzed to show the effectiveness of the proposed Hurricane damage pattern mining framework.

KW - Damage assessment

KW - Hurricane Andrew

KW - Multimedia data mining

KW - QBE (Query by image)

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=70450254778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450254778&partnerID=8YFLogxK

U2 - 10.1109/IRI.2003.1251418

DO - 10.1109/IRI.2003.1251418

M3 - Conference contribution

AN - SCOPUS:70450254778

SN - 0780382420

SN - 9780780382428

SP - 227

EP - 234

BT - Proceedings of the 2003 IEEE International Conference on Information Reuse and Integration, IRI 2003

PB - Institute of Electrical and Electronics Engineers Inc.

ER -