Development of a model-based 3D object recognition method aiming at construction of a system for supporting human activity

2014 Fiscal Year Final Research Report

• Project/Area Number: 24500209
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Kyushu Institute of Technology
• Principal Investigator: MAEDA Makoto 九州工業大学, 大学院情報工学研究院, 助教 (00274556)
• Co-Investigator(Kenkyū-buntansha): INOUE Katsuhiro 九州工業大学, 大学院情報工学研究院, 教授 (00150516)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 3次元物体認識 / 注視モデリング / 部分グラフ探索 / 形状記述 / 特徴点照合 / ARメガネ / 注目領域選択 / ヘルスケアモニタリング

Outline of Final Research Achievements

An object recognition method and a health-care monitoring method using 3D information (shape and depth) were developed to support human activity and life. Some local feature descriptions such as shape histograms or curvature distribution images were proposed for the object recognition technique, so that the recognition was robustly realized by utilizing a method for detecting dense subgraphs from many matching pairs. In having experimented using all 73 objects which were extracted from various measuring devices and had various sizes and accuracy, we had confirmed that the proposed method was able to achieve about 95% recognition rate.

Free Research Field

コンピュータビジョン