A Case Study of Object Identification Using a Kinect Sensor

摘要

The RGB camera and LIDAR have been applied in object identification for robots. However, Kinect has changed this situation. Because of the wide use of three-dimensional (3D) processing, the point cloud library (PCL) now enables people to easily use in a 3D environment. Iterative closest point (ICP) is an ideal method for identifying a target, but it involves first reconstructing an object. Therefore, this paper presents an alternative method using geometry of surface for identifying the features of an object and differentiating it from other objects.