Algorithm of semi-supervised classification for remotely sensed images with restricted training data
Project/Area Number |
25330199
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Perceptual information processing
|
Research Institution | Nagasaki University |
Principal Investigator |
KIYASU Senya 長崎大学, 工学研究科, 教授 (20234388)
|
Co-Investigator(Kenkyū-buntansha) |
SAKAI Tomoya 長崎大学, 工学研究科, 准教授 (30345003)
SONODA Kotaro 長崎大学, 工学研究科, 助教 (90415852)
|
Project Period (FY) |
2013-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2014: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2013: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
Keywords | 半教師付き分類 / リモートセンシング / マルチスペクトル画像 / 半教師つき分類 |
Outline of Final Research Achievements |
We developed a method of semi-supervised classification for remotely sensed multispectral images to improve the accuracy of classification. The method includes expansion of training data based on clustering, classification considering the variation of spectral characteristics according to the location in the image, and classification considering the characteristics of spatial distribution of each category of objects in the image. We confirmed the validity of the method using remotely sensed data observed from satellites.
|
Report
(4 results)
Research Products
(8 results)