Developmental analysis of a markerless hybrid tracking technique for mobile augmented reality systems

Abstract

Continuous tracking in Augmented Reality (AR) applications is essential for registering and augmenting the digital content on top of the real world. However, tracking on handheld devices such as PDAs or mobile phones enforces many restrictions and challenges in the form of efficiency and robustness which are the standard performance measures of tracking. This work focuses on the pre-analysis required for the development of an Accelero-Visual Markerless Hybrid Tracking Technique. The technique combines visual feature based tracking with the accelerometer sensor of the smartphones to make the process of tracking more efficient and robust. Pre-Analysis is performed for the visual and sensor based tracking approaches required to design the hybrid tracking technique. For visual tracking, the best keypoint detector and descriptors are analyzed. Careful selection of these visual tracking elements during the analysis stage helps in achieving much efficient and robust markerless augmented reality tracking results on a modern day smartphone.