Automatic camera pose initialization, using scale, rotation and luminance invariant natural feature tracking

Abstract

The solution to the camera registration and tracking problem serves Augmented Reality, in order to provide an enhancement to the user’s cognitive perception of the real world and his/her situational awareness. By analyzing the five most representative tracking and feature detection techniques, we have concluded that the Camera Pose Initialization (CPI) problem, a relevant sub-problem in the overall camera tracking problem, is still far from being solved using straightforward and non-intrusive methods. The assessed techniques often use user inputs (i.e. mouse clicking) or auxiliary artifacts (i.e. fiducial markers) to solve the CPI problem. This paper presents a novel approach to real-time scale, rotation and luminance invariant natural feature tracking, in order to solve the CPI problem using totally automatic procedures. The technique is applicable for the case of planar objects with arbitrary topologies and natural textures, and can be used in Augmented Reality. We also present a heuristic method for feature clustering, which has revealed to be efficient and reliable. The presented work uses this novel feature detection technique as a baseline for a real-time and robust planar texture tracking algorithm, which combines optical flow, backprojection and template matching techniques. The paper presents also performance and precision results of the proposed technique.