Vector distance algorithm for optimal segmentation scale selection of object-oriented remote sensing image classification

Huan Yu; Shuqing Zhang; Bo Kong

doi:10.1109/GEOINFORMATICS.2009.5293457

Vector distance algorithm for optimal segmentation scale selection of object-oriented remote sensing image classification

Huan Yu^*
, Shuqing Zhang
, Bo Kong

^*Corresponding author for this work

CAS - Northeast Institute of Geography and Agricultural Ecology
CAS - Institute of Mountain Hazards and Environment

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

3 Scopus citations

Abstract

Aiming at the optimal segmentation scale selection for object-oriented remote sensing image classification, thesis brought forward a new method named vector distance index. Research verified the validity and applicability of this method by carrying out experiment at wetland area with China Brazil Earth Resource Satellite image. Both two experiment showed that it could realize the optimal segmentation scale selection for object-oriented remote sensing image classification. Based on the basic theory of vector distance method, aiming at "submergence" and "fragmentation" phenomenon, research further brought forward a scale index, which could reflect the segmentation scale status for given object type, and provided a quantitative tool for assessing conflict degree between the two situations.

Original language	English
Title of host publication	2009 17th International Conference on Geoinformatics, Geoinformatics 2009
DOIs	https://doi.org/10.1109/GEOINFORMATICS.2009.5293457
State	Published - 2009
Externally published	Yes
Event	2009 17th International Conference on Geoinformatics, Geoinformatics 2009 - Fairfax, VA, United States Duration: 12 Aug 2009 → 14 Aug 2009

Publication series

Name	2009 17th International Conference on Geoinformatics, Geoinformatics 2009

Conference

Conference	2009 17th International Conference on Geoinformatics, Geoinformatics 2009
Country/Territory	United States
City	Fairfax, VA
Period	12/08/09 → 14/08/09

Keywords

Object-oriented classification
Scale
Segmentation
Vector distance index
Wetland

Access to Document

10.1109/GEOINFORMATICS.2009.5293457

Cite this

Yu, H., Zhang, S., & Kong, B. (2009). Vector distance algorithm for optimal segmentation scale selection of object-oriented remote sensing image classification. In 2009 17th International Conference on Geoinformatics, Geoinformatics 2009 Article 5293457 (2009 17th International Conference on Geoinformatics, Geoinformatics 2009). https://doi.org/10.1109/GEOINFORMATICS.2009.5293457

@inproceedings{85091187f46a45dbaad929010bc705c8,

title = "Vector distance algorithm for optimal segmentation scale selection of object-oriented remote sensing image classification",

abstract = "Aiming at the optimal segmentation scale selection for object-oriented remote sensing image classification, thesis brought forward a new method named vector distance index. Research verified the validity and applicability of this method by carrying out experiment at wetland area with China Brazil Earth Resource Satellite image. Both two experiment showed that it could realize the optimal segmentation scale selection for object-oriented remote sensing image classification. Based on the basic theory of vector distance method, aiming at {"}submergence{"} and {"}fragmentation{"} phenomenon, research further brought forward a scale index, which could reflect the segmentation scale status for given object type, and provided a quantitative tool for assessing conflict degree between the two situations.",

keywords = "Object-oriented classification, Scale, Segmentation, Vector distance index, Wetland",

author = "Huan Yu and Shuqing Zhang and Bo Kong",

year = "2009",

doi = "10.1109/GEOINFORMATICS.2009.5293457",

language = "英语",

isbn = "9781424445639",

series = "2009 17th International Conference on Geoinformatics, Geoinformatics 2009",

booktitle = "2009 17th International Conference on Geoinformatics, Geoinformatics 2009",

note = "2009 17th International Conference on Geoinformatics, Geoinformatics 2009 ; Conference date: 12-08-2009 Through 14-08-2009",

}

Yu, H, Zhang, S & Kong, B 2009, Vector distance algorithm for optimal segmentation scale selection of object-oriented remote sensing image classification. in 2009 17th International Conference on Geoinformatics, Geoinformatics 2009., 5293457, 2009 17th International Conference on Geoinformatics, Geoinformatics 2009, 2009 17th International Conference on Geoinformatics, Geoinformatics 2009, Fairfax, VA, United States, 12/08/09. https://doi.org/10.1109/GEOINFORMATICS.2009.5293457

Vector distance algorithm for optimal segmentation scale selection of object-oriented remote sensing image classification. / Yu, Huan; Zhang, Shuqing; Kong, Bo.
2009 17th International Conference on Geoinformatics, Geoinformatics 2009. 2009. 5293457 (2009 17th International Conference on Geoinformatics, Geoinformatics 2009).

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

TY - GEN

T1 - Vector distance algorithm for optimal segmentation scale selection of object-oriented remote sensing image classification

AU - Yu, Huan

AU - Zhang, Shuqing

AU - Kong, Bo

PY - 2009

Y1 - 2009

N2 - Aiming at the optimal segmentation scale selection for object-oriented remote sensing image classification, thesis brought forward a new method named vector distance index. Research verified the validity and applicability of this method by carrying out experiment at wetland area with China Brazil Earth Resource Satellite image. Both two experiment showed that it could realize the optimal segmentation scale selection for object-oriented remote sensing image classification. Based on the basic theory of vector distance method, aiming at "submergence" and "fragmentation" phenomenon, research further brought forward a scale index, which could reflect the segmentation scale status for given object type, and provided a quantitative tool for assessing conflict degree between the two situations.

AB - Aiming at the optimal segmentation scale selection for object-oriented remote sensing image classification, thesis brought forward a new method named vector distance index. Research verified the validity and applicability of this method by carrying out experiment at wetland area with China Brazil Earth Resource Satellite image. Both two experiment showed that it could realize the optimal segmentation scale selection for object-oriented remote sensing image classification. Based on the basic theory of vector distance method, aiming at "submergence" and "fragmentation" phenomenon, research further brought forward a scale index, which could reflect the segmentation scale status for given object type, and provided a quantitative tool for assessing conflict degree between the two situations.

KW - Object-oriented classification

KW - Scale

KW - Segmentation

KW - Vector distance index

KW - Wetland

UR - https://www.scopus.com/pages/publications/74349124565

U2 - 10.1109/GEOINFORMATICS.2009.5293457

DO - 10.1109/GEOINFORMATICS.2009.5293457

M3 - 会议稿件

AN - SCOPUS:74349124565

SN - 9781424445639

T3 - 2009 17th International Conference on Geoinformatics, Geoinformatics 2009

BT - 2009 17th International Conference on Geoinformatics, Geoinformatics 2009

T2 - 2009 17th International Conference on Geoinformatics, Geoinformatics 2009

Y2 - 12 August 2009 through 14 August 2009

ER -

Vector distance algorithm for optimal segmentation scale selection of object-oriented remote sensing image classification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this