講演抄録/キーワード |
講演名 |
2019-11-01 10:20
Study on Land Use Classification of PolSAR Data by Using Convolutional Neural Network ○Nanako Saito・Masanori Gocho・Hiroyoshi Yamada・Ryoichi Sato・Yoshio Yamaguchi(Niigata Univ.) SANE2019-63 |
抄録 |
(和) |
Polarimetric Synthetic Aperture Radar (PolSAR) has been attracting attention in ground target detection and classification. This is because it can observe wide area regardless of time zone and weather, and analyze in detail by using polarimetric information. Various methods, such as model-based scattering power decomposition, eigenvalue analysis and so forth, have been proposed for the analysis of PolSAR data. Recently, classification techniques by using machine learning have been intensively studied to reduce misclassification and improve classification accuracy. In this paper, we present some experimental results of land use classification of ALOS-2/PALSAR-2 data by using convolutional neural network (CNN), and compare classification performance with the case of scattering power decomposition and support vector machine (SVM). |
(英) |
Polarimetric Synthetic Aperture Radar (PolSAR) has been attracting attention in ground target detection and classification. This is because it can observe wide area regardless of time zone and weather, and analyze in detail by using polarimetric information. Various methods, such as model-based scattering power decomposition, eigenvalue analysis and so forth, have been proposed for the analysis of PolSAR data. Recently, classification techniques by using machine learning have been intensively studied to reduce misclassification and improve classification accuracy. In this paper, we present some experimental results of land use classification of ALOS-2/PALSAR-2 data by using convolutional neural network (CNN), and compare classification performance with the case of scattering power decomposition and support vector machine (SVM). |
キーワード |
(和) |
/ / / / / / / |
(英) |
Polarimetric Synthetic Aperture Radar (PolSAR) / ALOS-2 / Convolutional neural network / Support vector machine / Land use map / / / |
文献情報 |
信学技報, vol. 119, no. 255, SANE2019-63, pp. 77-82, 2019年10月. |
資料番号 |
SANE2019-63 |
発行日 |
2019-10-24 (SANE) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
SANE2019-63 |
|