Probabilistic land cover classification approach toward knowledge-based satellite data interpretations

Shutaro Hashimoto; Takeo Tadono; Masahiko Onosato; Masahiro Hori; Takashi Moriyama

doi:10.1109/IGARSS.2012.6351247

Probabilistic land cover classification approach toward knowledge-based satellite data interpretations

Shutaro Hashimoto^*, Takeo Tadono, Masahiko Onosato, Masahiro Hori, Takashi Moriyama

^*Corresponding author for this work

Earth System Science

Research output: Contribution to conference › Paper › peer-review

2 Scopus citations

Abstract

The recognition of concepts that we human beings are able to locate within satellite imagery requires analysis based on the particular context using knowledge. In this paper, we present a supervised pixel-based classification approach toward utilization of the classification results in knowledge-based satellite data interpretation system. The proposed approach is based upon a generative model, which is able to output the classification results with their probabilities and subsequently utilize them in detailed analysis. The experiment of classification was performed to demonstrate characteristics of the approach.

Original language	English
Pages	1513-1516
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2012.6351247
State	Published - 2012
Event	2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 - Munich, Germany Duration: 2012/07/22 → 2012/07/27

Conference

Conference	2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012
Country/Territory	Germany
City	Munich
Period	2012/07/22 → 2012/07/27

Keywords

generative model
knowledge-based system
land cover classification
machine learning
probabilistic inference

ASJC Scopus subject areas

Computer Science Applications
General Earth and Planetary Sciences

Access to Document

10.1109/IGARSS.2012.6351247

Cite this

@conference{639c5e1244ec4e91bc102c0f33a409ca,

title = "Probabilistic land cover classification approach toward knowledge-based satellite data interpretations",

abstract = "The recognition of concepts that we human beings are able to locate within satellite imagery requires analysis based on the particular context using knowledge. In this paper, we present a supervised pixel-based classification approach toward utilization of the classification results in knowledge-based satellite data interpretation system. The proposed approach is based upon a generative model, which is able to output the classification results with their probabilities and subsequently utilize them in detailed analysis. The experiment of classification was performed to demonstrate characteristics of the approach.",

keywords = "generative model, knowledge-based system, land cover classification, machine learning, probabilistic inference",

author = "Shutaro Hashimoto and Takeo Tadono and Masahiko Onosato and Masahiro Hori and Takashi Moriyama",

year = "2012",

doi = "10.1109/IGARSS.2012.6351247",

language = "英語",

pages = "1513--1516",

note = "2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 ; Conference date: 22-07-2012 Through 27-07-2012",

}

Hashimoto, S, Tadono, T, Onosato, M, Hori, M & Moriyama, T 2012, 'Probabilistic land cover classification approach toward knowledge-based satellite data interpretations', Paper presented at 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012, Munich, Germany, 2012/07/22 - 2012/07/27 pp. 1513-1516. https://doi.org/10.1109/IGARSS.2012.6351247

TY - CONF

T1 - Probabilistic land cover classification approach toward knowledge-based satellite data interpretations

AU - Hashimoto, Shutaro

AU - Tadono, Takeo

AU - Onosato, Masahiko

AU - Hori, Masahiro

AU - Moriyama, Takashi

PY - 2012

Y1 - 2012

N2 - The recognition of concepts that we human beings are able to locate within satellite imagery requires analysis based on the particular context using knowledge. In this paper, we present a supervised pixel-based classification approach toward utilization of the classification results in knowledge-based satellite data interpretation system. The proposed approach is based upon a generative model, which is able to output the classification results with their probabilities and subsequently utilize them in detailed analysis. The experiment of classification was performed to demonstrate characteristics of the approach.

AB - The recognition of concepts that we human beings are able to locate within satellite imagery requires analysis based on the particular context using knowledge. In this paper, we present a supervised pixel-based classification approach toward utilization of the classification results in knowledge-based satellite data interpretation system. The proposed approach is based upon a generative model, which is able to output the classification results with their probabilities and subsequently utilize them in detailed analysis. The experiment of classification was performed to demonstrate characteristics of the approach.

KW - generative model

KW - knowledge-based system

KW - land cover classification

KW - machine learning

KW - probabilistic inference

UR - http://www.scopus.com/inward/record.url?scp=84873197965&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2012.6351247

DO - 10.1109/IGARSS.2012.6351247

M3 - 学会論文

AN - SCOPUS:84873197965

SP - 1513

EP - 1516

T2 - 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012

Y2 - 22 July 2012 through 27 July 2012

ER -

Probabilistic land cover classification approach toward knowledge-based satellite data interpretations

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this