A Geometry-Based Point Cloud Reduction Method for MobileAugmented Reality System

摘要

In this paper, a geometry-based point cloud reduction method is proposed, and a real-time mobile augmentedreality system is explored for applications in urban environments. We formulate a new objective function which combinesthe point reconstruction errors and constraints on spatial point distribution. Based on this formulation, a mixed integerprogramming scheme is utilized to solve the points reduction problem. The mobile augmented reality system explored inthis paper is composed of the ofttine and online stages. At the offline stage, we build up the localization database usingstructure from motion and compress the point cloud by the proposed point cloud reduction method. While at the onlinestage, we compute the camera pose in real time by combining an image-based localization algorithm and a continuous posetracking algorithm. Experimental results on benchmark and real data show that compared with the existing methods, thisgeometry-based point cloud reduction method selects a point cloud subset which helps the image-based localization methodto achieve higher success rate. Also, the experiments conducted on a mobile platform show that the reduced point cloud notonly reduces the time consuming for initialization and re-initialization, but also makes the memory footprint small, resultinga scalable and real-time mobile augmented reality system.