Adaptive procedure of RS images classification with use of extended feature space

Abstract

The paper proposes an idea of the adaptive classification procedure (ACP) making the process of remotely sensed (RS) data classification more flexible and efficient in comparison with existing recognition methods. The ACP employs an improved scheme of forming feature space and adaptive decision rule allowing an optimal imagery classification method to be chosen during thematic processing. In the paper the basic principles of the ACP design and the results of its classification methods efficiency research are considered. Also the results of the ACP application for solving problems of landscape-ecological mapping of Lake Chani area (Omsk region, Russia) and Pervomayskoe oil field (Tomsk region, Russia) using multispectral images from Russia satellite RESURS-O1 are shown.

Original language	English
Pages (from-to)	489-500
Number of pages	12
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	4885
DOIs	https://doi.org/10.1117/12.468219
Publication status	Published - 1 Dec 2002
Event	Image and Signal Processing for Remote Sensing VII - Agia Pelagia, Greece Duration: 24 Sep 2002 → 27 Sep 2002

Keywords

Digital image analysis
Neural networks
Nonparametric statistics
Pattern recognition
Texture analysis

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.468219

Fingerprint Dive into the research topics of 'Adaptive procedure of RS images classification with use of extended feature space'. Together they form a unique fingerprint.

Cite this

@article{c0af287d326c4b4dad687c543e4ffa60,

title = "Adaptive procedure of RS images classification with use of extended feature space",

abstract = "The paper proposes an idea of the adaptive classification procedure (ACP) making the process of remotely sensed (RS) data classification more flexible and efficient in comparison with existing recognition methods. The ACP employs an improved scheme of forming feature space and adaptive decision rule allowing an optimal imagery classification method to be chosen during thematic processing. In the paper the basic principles of the ACP design and the results of its classification methods efficiency research are considered. Also the results of the ACP application for solving problems of landscape-ecological mapping of Lake Chani area (Omsk region, Russia) and Pervomayskoe oil field (Tomsk region, Russia) using multispectral images from Russia satellite RESURS-O1 are shown.",

keywords = "Digital image analysis, Neural networks, Nonparametric statistics, Pattern recognition, Texture analysis",

author = "Markov, {Nikolay G.} and Napryushkin, {Alexandr A.} and Zamyatin, {Alexandr V.} and Vertinskaya, {Evgenia V.}",

year = "2002",

month = dec,

day = "1",

doi = "10.1117/12.468219",

language = "English",

volume = "4885",

pages = "489--500",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Image and Signal Processing for Remote Sensing VII ; Conference date: 24-09-2002 Through 27-09-2002",

}

TY - JOUR

T1 - Adaptive procedure of RS images classification with use of extended feature space

AU - Markov, Nikolay G.

AU - Napryushkin, Alexandr A.

AU - Zamyatin, Alexandr V.

AU - Vertinskaya, Evgenia V.

PY - 2002/12/1

Y1 - 2002/12/1

N2 - The paper proposes an idea of the adaptive classification procedure (ACP) making the process of remotely sensed (RS) data classification more flexible and efficient in comparison with existing recognition methods. The ACP employs an improved scheme of forming feature space and adaptive decision rule allowing an optimal imagery classification method to be chosen during thematic processing. In the paper the basic principles of the ACP design and the results of its classification methods efficiency research are considered. Also the results of the ACP application for solving problems of landscape-ecological mapping of Lake Chani area (Omsk region, Russia) and Pervomayskoe oil field (Tomsk region, Russia) using multispectral images from Russia satellite RESURS-O1 are shown.

AB - The paper proposes an idea of the adaptive classification procedure (ACP) making the process of remotely sensed (RS) data classification more flexible and efficient in comparison with existing recognition methods. The ACP employs an improved scheme of forming feature space and adaptive decision rule allowing an optimal imagery classification method to be chosen during thematic processing. In the paper the basic principles of the ACP design and the results of its classification methods efficiency research are considered. Also the results of the ACP application for solving problems of landscape-ecological mapping of Lake Chani area (Omsk region, Russia) and Pervomayskoe oil field (Tomsk region, Russia) using multispectral images from Russia satellite RESURS-O1 are shown.

KW - Digital image analysis

KW - Neural networks

KW - Nonparametric statistics

KW - Pattern recognition

KW - Texture analysis

UR - http://www.scopus.com/inward/record.url?scp=0038627485&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038627485&partnerID=8YFLogxK

U2 - 10.1117/12.468219

DO - 10.1117/12.468219

M3 - Conference article

AN - SCOPUS:0038627485

VL - 4885

SP - 489

EP - 500

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

T2 - Image and Signal Processing for Remote Sensing VII

Y2 - 24 September 2002 through 27 September 2002

ER -