Robust plane recognition for large scale 3D data

2014 Fiscal Year Final Research Report

• Project/Area Number: 24500198
• 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: Tokyo University of Agriculture and Technology
• Principal Investigator: SHIMIZU Ikuko 東京農工大学, 工学(系)研究科(研究院), 准教授 (70312915)
• Research Collaborator: MIYATAKE Takahisa ; SHIKANAI Yuko
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 3次元データ / 平面認識

Outline of Final Research Achievements

In this research, we developed a method for plane recognition using large scale 3D data obtained by 3D scanner. Plane recognition is one of the most important algorithms for 3D data processing. To cope with the large scale data, we proposed a local plane recognition method based on local plane patterns which uses a point and its few neighboring points. In addition, to cope with the ununiformity of the data, our local plane patterns's relationship between multiple resolutions are clearly defined.
In our algorithm, we proofed that the discrete model we used in our method is invariant under multiple resolution and we generated discrete plane patterns. Our implementation is based on bit operation by representing plane patterns and point coordinates using bit expression,

Free Research Field

知能情報処理