Development of image information analysis infrastructure in navigation and classification of human behavior

2020 Fiscal Year Final Research Report

• Project Area: Systems Science of Bio-navigation
• Project/Area Number: 16H06540
• Research Category: Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area)
• Allocation Type: Single-year Grants
• Review Section: Complex systems
• Research Institution: Nagoya Institute of Technology (2020); Hiroshima University (2016-2019)
• Principal Investigator: Toru Tamaki 名古屋工業大学, 工学(系)研究科(研究院), 教授 (10333494)
• Co-Investigator(Kenkyū-buntansha): 藤吉 弘亘 中部大学, 工学部, 教授 (20333172)
• Project Period (FY): 2016-06-30 – 2021-03-31
• Keywords: ナビゲーション / 軌跡 / 行動認識 / 深層学習 / 機械学習

Outline of Final Research Achievements

The purpose of this research is to develop stable and robust recognition technology for images and videos including self-movement, obtained from cameras attached to wild animals and pets, taken by humans, which are difficult to handle by conventional methods, and to establish technology foundation for image and video information analysis. As the results of our research, we developed methods for recognizing video and GPS records attached to wild animals, a highly accurate method for human action recognition, a method for analyzing human behavior, and a method for localization from multichannel signals.

Free Research Field

知覚情報処理

Academic Significance and Societal Importance of the Research Achievements

開発したGPS軌跡の解析手法はこれまでにない方法論による新たなものであり，野生生物の内的動機の分析など新たな生物学的知見へとつながることが期待される．また人物行動軌跡の解析手法は人流を解析して分類・分割を行う新たなツールとして様々な分野へ応用することが可能である．