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: ¥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.

Research Products

• [Journal Article] Semi-Supervised Land Cover Classification of Remotely Sensed Image with k-menas++ Clustering (2016)
  • Author(s): Senya Kiyasu, Daichi Maruyama, Kotaro Sonoda
  • Journal Title: Proc. of the 37th RESES Symposium Volume: ― Pages: 52-57
• [Journal Article] Semi-Supervised Land Cover Classification of Remotely Sensed Image with Improved Clustering Seeds Initialization (2014)
  • Author(s): Senya Kiyasu, Daichi Maruyama, Kotaro Sonoda
  • Journal Title: Proceedings of SICE Annual Conference 2014 Volume: - Pages: 101-104
  • Peer Reviewed
• [Journal Article] マルチテンポラ画像を教師データとする衛星画像のカゴリー分類 (2014)
  • Author(s): 堀多恵美，馬場涼介，薗田光太郎，酒井智弥，喜安千弥
  • Journal Title: 電子情報通信学会九州支部 第22回学生会講演会 講演論文集 Volume: -
• [Journal Article] 土地被覆の連続性を考慮した衛星画像の半教師付き分類 (2013)
  • Author(s): 馬場涼介，薗田光太郎，酒井智弥，喜安千弥
  • Journal Title: 電子情報通信学会九州支部 第21回学生会講演会 講演論文集 Volume: -
• [Presentation] Semi-Supervised Land Cover Classification of Remotely Sensed Image with k-menas++ Clustering (2015)
  • Author(s): Senya Kiyasu
  • Organizer: the 37th RESES Symposium
  • Place of Presentation: やすらぎ伊王島（長崎県・長崎市）
  • Year and Date: 2015-09-06
• [Presentation] マルチテンポラ画像を教師データとする衛星画像のカゴリー分類 (2014)
  • Author(s): 堀多恵美，馬場涼介，薗田光太郎，酒井智弥，喜安千弥
  • Organizer: 電子情報通信学会九州支部 第22回学生会講演会
  • Place of Presentation: 鹿児島大学（鹿児島市）
  • Year and Date: 2014-09-20
• [Presentation] Semi-Supervised Land Cover Classification of Remotely Sensed Image with Improved Clustering Seeds Initialization (2014)
  • Author(s): Senya Kiyasu, Daichi Maruyama, Kotaro Sonoda
  • Organizer: SICE Annual Conference 2014
  • Place of Presentation: 北海道大学（札幌市）
  • Year and Date: 2014-09-10
• [Presentation] 土地被覆の連続性を考慮した衛星画像の半教師付き分類
  • Author(s): 馬場涼介，薗田光太郎，酒井智弥，喜安千弥
  • Organizer: 電子情報通信学会九州支部 第21回学生会講演会
  • Place of Presentation: 熊本大学（熊本県熊本市）