Plane detection is a prerequisite to a wide variety of vision tasks. RANdomSAmple Consensus (RANSAC) algorithm is widely used for plane detectionin point cloud data. Minimum description length (MDL) principle is used todeal with several competing hypothesis. This paper presents a new approachto the plane detection by integrating RANSAC and MDL. The method couldavoid detecting wrong planes due to the complex geometry of the 3D data.The paper tests the performance of proposed method on both synthetic andreal data.
|Place of Publication||Bonn|
|Publisher||University of Bonn|
|Number of pages||16|
|Publication status||Published - 2010|
|Name||IGG : Technical Report |
|Publisher||Institute of Geodesy and Geoinformation (IGG)|