A 3-Dimensional Object Recognition Method Using SHOT and Relationship of Distances and Angles in Feature Points

Abstract

In recent years, a human support robot has been receiving attention. This robot is required to perform various tasks to support humans. Especially the object recognition task, which is important when people request the robot to transport and rearrange objects. Object recognition methods, especially using the 3D sensor are also receiving attention. As conventional object recognition methods using 3dimensional information, Signature of Histogram of OrienTations (SHOT) is commonly used. SHOT performs highly accurate object recognition since SHOT descriptor is represented by 352 dimensions. However SHOT misrecognizes objects which have the same feature but which are not the same objects and if there is occlusion in the 3-dimensional object. As a solution, I would like to propose the object recognition method with high quality by using the positive part of SHOT.