Localization of Flying Bats from Multichannel Audio Signals by Estimating Location Map with Convolutional Neural Networks

• Fujimori Kazuki

  Hiroshima University

• Raytchev Bisser

  Hiroshima University

• Kaneda Kazufumi

  Hiroshima University

• Yamada Yasufumi

  Hiroshima University

• Teshima Yu

  Doshisha University

• Fujioka Emyo

  Doshisha University

• Hiryu Shizuko

  Doshisha University

• Tamaki Toru

  Nagoya Institute of Technology

Abstract

We propose a method that uses ultrasound audio signals from a multichannel microphone array to estimate the positions of flying bats. The proposed model uses a deep convolutional neural network that takes multichannel signals as input and outputs the probability maps of the locations of bats. We present experimental results using two ultrasound audio clips of different bat species and show numerical simulations with synthetically generated sounds.

Journal

• Journal of Robotics and Mechatronics

  Journal of Robotics and Mechatronics 33 (3), 515-525, 2021-06-20

  Fuji Technology Press Ltd.

Keywords

• bat
• multichannel
• ultrasound signal
• CNN
• location estimation

Details

• CRID: 1390006973362975488
• NII Article ID: 130008054333
• NII Book ID: AA10809998
• DOI: 10.20965/jrm.2021.p0515
• ISSN: 18838049
• ISSN: 09153942
• NDL BIB ID: 031511571
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I031511571
• Web Site: https://www.fujipress.jp/main/wp-content/themes/Fujipress/phyosetsu.php?ppno=ROBOT003300030008
• Text Lang: en
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed