Kalman Filter for Hybrid Tracking Technique in Augmented Reality

Abstract

Augmented reality started to emerge as a promising visualization technique that tracks real objects and adds virtual content into real world context using camera view. Many augmented reality solutions are based on computer vision techniques to identify and track objects. Problems that must be solved are image transformations, chaotic environment, lighting condition and occlusion from users' or objects in the environment, which causes virtual content to disappear. This has a negative impact for augmented reality usability, therefore, object recognition and tracking in real-time becomes difficult and sometimes an impossible task. In this research orientationposition information acquisition using computer vision and sensor fusion techniques are analysed. Experiments are accomplished with predefined assumptions and simulated orientation-position information. Conditions for optimal orientation-position estimates are introduced. Research results are compared and supplementary properties are presented of a proposed hybrid tracking technique using Kalman filter.

Kalman Filtresi ile Ayrık Zamanlı Durum Tahmini ve Zamanla Değişen Doğrusal Bir Sistemin Adaptif LQR Kontrolü

“…Accordingly, the Kalman filters are expressed as the mathematical method that can minimize the disruptive effects and estimate the states by reducing the root-mean-square error. This filter structure is especially used in space and military technology [4], robotics and trajectory control applications [5], hybrid tracking technique [6], dynamic data processing [7], navigation sensors data fusion [8], Mobile Radio Link Adaptation by Radio Channel State Prediction [9], artificial neural networks [10], and different hybrid controller designs [11]. Accurately estimating the dynamic states (such as position, speed, and current) of a system such as a DC Motor is a very important element in terms of system stability [12].…”