Full Text Views
55
In this paper, we improve upon the automatic building extraction method, which uses a variational inference Gaussian mixture model for performing color clustering, by accelerating its computational speed. The improved method decreases the computational time using an image with reduced resolution upon applying color clustering. According to our experiment, in which we used 106 scenery images, the improved method could extract buildings at a rate 86.54% faster than that of the conventional methods. Furthermore, the improved method significantly increased the extraction accuracy by 1.8% or more by preventing over-clustering using the reduced image, which also had a reduced number of the colors.
Masakazu IWAI
Osaka Electro-Communication University
Takuya FUTAGAMI
Osaka University
Noboru HAYASAKA
Osaka Electro-Communication University
Takao ONOYE
Osaka University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Masakazu IWAI, Takuya FUTAGAMI, Noboru HAYASAKA, Takao ONOYE, "Acceleration of Automatic Building Extraction via Color-Clustering Analysis" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 12, pp. 1599-1602, December 2020, doi: 10.1587/transfun.2020SML0004.
Abstract: In this paper, we improve upon the automatic building extraction method, which uses a variational inference Gaussian mixture model for performing color clustering, by accelerating its computational speed. The improved method decreases the computational time using an image with reduced resolution upon applying color clustering. According to our experiment, in which we used 106 scenery images, the improved method could extract buildings at a rate 86.54% faster than that of the conventional methods. Furthermore, the improved method significantly increased the extraction accuracy by 1.8% or more by preventing over-clustering using the reduced image, which also had a reduced number of the colors.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2020SML0004/_p
Copy
@ARTICLE{e103-a_12_1599,
author={Masakazu IWAI, Takuya FUTAGAMI, Noboru HAYASAKA, Takao ONOYE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Acceleration of Automatic Building Extraction via Color-Clustering Analysis},
year={2020},
volume={E103-A},
number={12},
pages={1599-1602},
abstract={In this paper, we improve upon the automatic building extraction method, which uses a variational inference Gaussian mixture model for performing color clustering, by accelerating its computational speed. The improved method decreases the computational time using an image with reduced resolution upon applying color clustering. According to our experiment, in which we used 106 scenery images, the improved method could extract buildings at a rate 86.54% faster than that of the conventional methods. Furthermore, the improved method significantly increased the extraction accuracy by 1.8% or more by preventing over-clustering using the reduced image, which also had a reduced number of the colors.},
keywords={},
doi={10.1587/transfun.2020SML0004},
ISSN={1745-1337},
month={December},}
Copy
TY - JOUR
TI - Acceleration of Automatic Building Extraction via Color-Clustering Analysis
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1599
EP - 1602
AU - Masakazu IWAI
AU - Takuya FUTAGAMI
AU - Noboru HAYASAKA
AU - Takao ONOYE
PY - 2020
DO - 10.1587/transfun.2020SML0004
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2020
AB - In this paper, we improve upon the automatic building extraction method, which uses a variational inference Gaussian mixture model for performing color clustering, by accelerating its computational speed. The improved method decreases the computational time using an image with reduced resolution upon applying color clustering. According to our experiment, in which we used 106 scenery images, the improved method could extract buildings at a rate 86.54% faster than that of the conventional methods. Furthermore, the improved method significantly increased the extraction accuracy by 1.8% or more by preventing over-clustering using the reduced image, which also had a reduced number of the colors.
ER -