Semi-Supervised Learning of CNN for Land-Use Classification from Aerial Photograph

Kei HIRASHIMA; Noritaka SHIGEI; Satoshi SUGIMOTO; Yoichi ISHIZUKA; Hiromi MIYAJIMA

doi:10.3156/jsoft.33.1_520

Short Notes

Semi-Supervised Learning of CNN for Land-Use Classification from Aerial Photograph

Kei HIRASHIMA, Noritaka SHIGEI, Satoshi SUGIMOTO, Yoichi ISHIZUKA, Hiromi MIYAJIMA

Author information

Keywords: land-use classification, convolutional neural network, semi-supervised learning, aerial photograph, map symbol

JOURNAL FREE ACCESS

2021 Volume 33 Issue 1 Pages 520-524

DOI https://doi.org/10.3156/jsoft.33.1_520

Details

Abstract

In this study, we consider generating efficiently labeled data from map symbols of GIS data as a means to efficiently increase the data. Further, we propose to perform semi-supervised learning using this method. We demonstrate the effectiveness of the proposed method in 6 classes of land-use classification.

Corresponding author

Funder information

1.Fund name: Japan Society for the Promotion of Science

Register with J-STAGE for free!