A 3D Real Object Recognition and Localization on SLAM based Augmented Reality Environment

Abstract

this paper introduces a method for recognizing real world objects in AR(Augmented Reality) environment and visualizing virtual information based on the objects. Existing AR shows high dependence on markers. The use range of the virtual space is limited to narrow marker space and the placement and tracking of virtual objects in a 3D is also limited to the space centered on the marker. The method constructs a map of the space in the form of a point cloud using SLAM, and performs real-world object recognition of the constructed wide AR space in real time. As a result, the degree of freedom of space utilization increases, and it is helpful in applying AR such as information display of real-world objects by accurately recognizing and localizing the location of objects existing in the real-world space.