A Fully automated design of binary decision tree for land cover classification

Masanobu Yoshikawa, Hisakazu Shindo, Ryuei Nishii, Shojiro Tanaka

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

3 Citations (Scopus)

Abstract

A fully automated design method of binary decision tree is proposed for land cover classification of remote sensing data. The proposed method has the following features: (1) all possible binary combinations of identification classes are tested as splitting pattern of classes; (2) additional variables by linear combination of paired bands are applied in data segmentation; (3) Automatic Interaction Detector technique is utilized to divide the data set into binary tree nodes. Completely enumerated Landsat MSS data with land-cover data are used for the test of the method and classification accuracy. Our new method is compared with Bayesian discriminant classifier in terms of accuracy and training sample set sizes.

Original languageEnglish
Title of host publicationInternational Geoscience and Remote Sensing Symposium (IGARSS)
Editors Anon
PublisherIEEE
Pages1921-1923
Number of pages3
Volume3
Publication statusPublished - 1995
Externally publishedYes
EventProceedings of the 1995 International Geoscience and Remote Sensing Symposium. Part 3 (of 3) - Firenze, Italy
Duration: Jul 10 1995Jul 14 1995

Other

OtherProceedings of the 1995 International Geoscience and Remote Sensing Symposium. Part 3 (of 3)
CityFirenze, Italy
Period7/10/957/14/95

Fingerprint

Decision trees
land cover
Binary trees
Remote sensing
Classifiers
Detectors
Landsat multispectral scanner
design method
segmentation
remote sensing
decision
method

All Science Journal Classification (ASJC) codes

  • Software
  • Geology

Cite this

Yoshikawa, M., Shindo, H., Nishii, R., & Tanaka, S. (1995). A Fully automated design of binary decision tree for land cover classification. In Anon (Ed.), International Geoscience and Remote Sensing Symposium (IGARSS) (Vol. 3, pp. 1921-1923). IEEE.

A Fully automated design of binary decision tree for land cover classification. / Yoshikawa, Masanobu; Shindo, Hisakazu; Nishii, Ryuei; Tanaka, Shojiro.

International Geoscience and Remote Sensing Symposium (IGARSS). ed. / Anon. Vol. 3 IEEE, 1995. p. 1921-1923.

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

Yoshikawa, M, Shindo, H, Nishii, R & Tanaka, S 1995, A Fully automated design of binary decision tree for land cover classification. in Anon (ed.), International Geoscience and Remote Sensing Symposium (IGARSS). vol. 3, IEEE, pp. 1921-1923, Proceedings of the 1995 International Geoscience and Remote Sensing Symposium. Part 3 (of 3), Firenze, Italy, 7/10/95.
Yoshikawa M, Shindo H, Nishii R, Tanaka S. A Fully automated design of binary decision tree for land cover classification. In Anon, editor, International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 3. IEEE. 1995. p. 1921-1923
Yoshikawa, Masanobu ; Shindo, Hisakazu ; Nishii, Ryuei ; Tanaka, Shojiro. / A Fully automated design of binary decision tree for land cover classification. International Geoscience and Remote Sensing Symposium (IGARSS). editor / Anon. Vol. 3 IEEE, 1995. pp. 1921-1923
@inproceedings{9a8cf650b9014a22bd7ae00281189053,
title = "A Fully automated design of binary decision tree for land cover classification",
abstract = "A fully automated design method of binary decision tree is proposed for land cover classification of remote sensing data. The proposed method has the following features: (1) all possible binary combinations of identification classes are tested as splitting pattern of classes; (2) additional variables by linear combination of paired bands are applied in data segmentation; (3) Automatic Interaction Detector technique is utilized to divide the data set into binary tree nodes. Completely enumerated Landsat MSS data with land-cover data are used for the test of the method and classification accuracy. Our new method is compared with Bayesian discriminant classifier in terms of accuracy and training sample set sizes.",
author = "Masanobu Yoshikawa and Hisakazu Shindo and Ryuei Nishii and Shojiro Tanaka",
year = "1995",
language = "English",
volume = "3",
pages = "1921--1923",
editor = "Anon",
booktitle = "International Geoscience and Remote Sensing Symposium (IGARSS)",
publisher = "IEEE",

}

TY - GEN

T1 - A Fully automated design of binary decision tree for land cover classification

AU - Yoshikawa, Masanobu

AU - Shindo, Hisakazu

AU - Nishii, Ryuei

AU - Tanaka, Shojiro

PY - 1995

Y1 - 1995

N2 - A fully automated design method of binary decision tree is proposed for land cover classification of remote sensing data. The proposed method has the following features: (1) all possible binary combinations of identification classes are tested as splitting pattern of classes; (2) additional variables by linear combination of paired bands are applied in data segmentation; (3) Automatic Interaction Detector technique is utilized to divide the data set into binary tree nodes. Completely enumerated Landsat MSS data with land-cover data are used for the test of the method and classification accuracy. Our new method is compared with Bayesian discriminant classifier in terms of accuracy and training sample set sizes.

AB - A fully automated design method of binary decision tree is proposed for land cover classification of remote sensing data. The proposed method has the following features: (1) all possible binary combinations of identification classes are tested as splitting pattern of classes; (2) additional variables by linear combination of paired bands are applied in data segmentation; (3) Automatic Interaction Detector technique is utilized to divide the data set into binary tree nodes. Completely enumerated Landsat MSS data with land-cover data are used for the test of the method and classification accuracy. Our new method is compared with Bayesian discriminant classifier in terms of accuracy and training sample set sizes.

UR - http://www.scopus.com/inward/record.url?scp=0029214351&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029214351&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029214351

VL - 3

SP - 1921

EP - 1923

BT - International Geoscience and Remote Sensing Symposium (IGARSS)

A2 - Anon, null

PB - IEEE

ER -