Presentation 2019-06-07
Development and evaluation of habitat observation system of wild bird using UAV and machine learning technologies
Yoshihiro Higashiura, Hiroshi Yamamoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In recent years, agricultural, forestry and fishery are be harmed by wild birds and it has become a significant problem. To prevent and solve this problem, we need a technology to support coexistence rather than repell wild birds from the point of view of ecosystem conservation. Therefore, it has been studied technologies that detect presence of wild birds by analyzing voice data. These voice data is collected by microphones and analyzed by using machine learning. In addition, to verify the ecosystem of wild birds, it requires vocal and visual observation in the field. However, frequent access to the mountain and forest area to collect voice data is a heavy burden for observers. Therefore, in this research, we develop a new observation system that can collect voice data by using UAV(Unmanned Aerial Vehicle) and estimate species and position of wild birds by using machine learning in the embedded system. The embedded system has a microphones that are attached to the UAV that can move freely in a hazardous place. In addition, the estimation accuracy of the position and the species of the wild birds is evaluated by experimental evaluation in a field.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Localization / Machine Learning / Unmanned Aerial Vehicle / Sound Source Localization
Paper # IA2019-4,ICSS2019-4
Date of Issue 2019-05-30 (IA, ICSS)

Conference Information
Committee IA / ICSS
Conference Date 2019/6/6(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Research Institute for Electrical Communication, Tohoku University
Topics (in Japanese) (See Japanese page)
Topics (in English) Internet Security, etc.
Chair Hiroyuki Osaki(Kwansei Gakuin Univ.) / Hiroki Takakura(NII)
Vice Chair Rei Atarashi(IIJ) / Toru Kondo(Hiroshima Univ.) / Hiroshi Yamamoto(Ritsumeikan Univ.) / Katsunari Yoshioka(Yokohama National Univ.) / Kazunori Kamiya(NTT)
Secretary Rei Atarashi(Kwansei Gakuin Univ.) / Toru Kondo(KDDI Research) / Hiroshi Yamamoto(NEC) / Katsunari Yoshioka(NICT) / Kazunori Kamiya(KDDI labs.)
Assistant Kenji Ohira(Tokushima Univ.) / Daiki Nobayashi(Kyushu Inst. of Tech.) / Ryohei Banno(Tokyo Inst. of Tech.) / Keisuke Kito(Mitsubishi Electric) / Toshihiro Yamauchi(Okayama Univ.)

Paper Information
Registration To Technical Committee on Internet Architecture / Technical Committee on Information and Communication System Security
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Development and evaluation of habitat observation system of wild bird using UAV and machine learning technologies
Sub Title (in English)
Keyword(1) Localization
Keyword(2) Machine Learning
Keyword(3) Unmanned Aerial Vehicle
Keyword(4) Sound Source Localization
1st Author's Name Yoshihiro Higashiura
1st Author's Affiliation Ritsumeikan University(Ritsumeikan Univ.)
2nd Author's Name Hiroshi Yamamoto
2nd Author's Affiliation Ritsumeikan University(Ritsumeikan Univ.)
Date 2019-06-07
Paper # IA2019-4,ICSS2019-4
Volume (vol) vol.119
Number (no) IA-69,ICSS-70
Page pp.pp.15-20(IA), pp.15-20(ICSS),
#Pages 6
Date of Issue 2019-05-30 (IA, ICSS)