Hyperspectral image classification by recursive spatial boosting based on the bootstrap method

Shuji Kawaguchi; Ryuei Nishii

doi:10.1109/IGARSS.2007.4423158

Hyperspectral image classification by recursive spatial boosting based on the bootstrap method

Shuji Kawaguchi, Ryuei Nishii

Division of Advanced Mathematics Technology

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

Abstract

We consider contextual classification of hyperspectral data based on the boosting method. Bootstrap AdaBoost proposed by Kawaguchi and Nishii (2006) is applied to Spatial Boosting for contextual classification. The paper proposes a recursive version of Spatial Boosting. Posterior probabilities of each pixel are updated by the contextual classification function derived from Spatial Boosting and this is repeated. The proposed method with random stumps shows excellent performance for classification of AVIRIS data. Furthermore, it is superior to other well-known contextual classification methods including MRF-based classifiers.

Original language	English
Title of host publication	2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007
Pages	1751-1754
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2007.4423158
Publication status	Published - 2007
Event	2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007 - Barcelona, Spain Duration: Jun 23 2007 → Jun 28 2007

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)

Other

Other	2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007
Country/Territory	Spain
City	Barcelona
Period	6/23/07 → 6/28/07

All Science Journal Classification (ASJC) codes

Computer Science Applications
Earth and Planetary Sciences(all)

Access to Document

10.1109/IGARSS.2007.4423158

Cite this

Hyperspectral image classification by recursive spatial boosting based on the bootstrap method. / Kawaguchi, Shuji; Nishii, Ryuei.

2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007. 2007. p. 1751-1754 4423158 (International Geoscience and Remote Sensing Symposium (IGARSS)).

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

Kawaguchi, S & Nishii, R 2007, Hyperspectral image classification by recursive spatial boosting based on the bootstrap method. in 2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007., 4423158, International Geoscience and Remote Sensing Symposium (IGARSS), pp. 1751-1754, 2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007, Barcelona, Spain, 6/23/07. https://doi.org/10.1109/IGARSS.2007.4423158

@inproceedings{18147566619b4a7a9d1752b91ffe055d,

title = "Hyperspectral image classification by recursive spatial boosting based on the bootstrap method",

abstract = "We consider contextual classification of hyperspectral data based on the boosting method. Bootstrap AdaBoost proposed by Kawaguchi and Nishii (2006) is applied to Spatial Boosting for contextual classification. The paper proposes a recursive version of Spatial Boosting. Posterior probabilities of each pixel are updated by the contextual classification function derived from Spatial Boosting and this is repeated. The proposed method with random stumps shows excellent performance for classification of AVIRIS data. Furthermore, it is superior to other well-known contextual classification methods including MRF-based classifiers.",

author = "Shuji Kawaguchi and Ryuei Nishii",

year = "2007",

doi = "10.1109/IGARSS.2007.4423158",

language = "English",

isbn = "1424412129",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

pages = "1751--1754",

booktitle = "2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007",

note = "2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007 ; Conference date: 23-06-2007 Through 28-06-2007",

}

TY - GEN

T1 - Hyperspectral image classification by recursive spatial boosting based on the bootstrap method

AU - Kawaguchi, Shuji

AU - Nishii, Ryuei

PY - 2007

Y1 - 2007

N2 - We consider contextual classification of hyperspectral data based on the boosting method. Bootstrap AdaBoost proposed by Kawaguchi and Nishii (2006) is applied to Spatial Boosting for contextual classification. The paper proposes a recursive version of Spatial Boosting. Posterior probabilities of each pixel are updated by the contextual classification function derived from Spatial Boosting and this is repeated. The proposed method with random stumps shows excellent performance for classification of AVIRIS data. Furthermore, it is superior to other well-known contextual classification methods including MRF-based classifiers.

AB - We consider contextual classification of hyperspectral data based on the boosting method. Bootstrap AdaBoost proposed by Kawaguchi and Nishii (2006) is applied to Spatial Boosting for contextual classification. The paper proposes a recursive version of Spatial Boosting. Posterior probabilities of each pixel are updated by the contextual classification function derived from Spatial Boosting and this is repeated. The proposed method with random stumps shows excellent performance for classification of AVIRIS data. Furthermore, it is superior to other well-known contextual classification methods including MRF-based classifiers.

UR - http://www.scopus.com/inward/record.url?scp=82355165154&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82355165154&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2007.4423158

DO - 10.1109/IGARSS.2007.4423158

M3 - Conference contribution

AN - SCOPUS:82355165154

SN - 1424412129

SN - 9781424412129

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 1751

EP - 1754

BT - 2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007

T2 - 2007 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2007

Y2 - 23 June 2007 through 28 June 2007

ER -

Hyperspectral image classification by recursive spatial boosting based on the bootstrap method

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this