Automatic confidence adjustment of visual cues in model‐based camera tracking

Abstract

Model-based camera tracking is a technology that estimates a precise camera pose based on visual cues (e.g., feature points, edges) extracted from camera images given a 3D scene model and a rough camera pose. This paper proposes an automatic method for flexibly adjusting the confidence of visual cues in model-based camera tracking. The adjustment is based on the conditions of the target object/scene and the reliability of the initial or previous camera pose. Under uncontrolled or less-controlled working environments, the proposed objectadaptive tracking method works flexibly at 20 frames per second on an ultra mobile personal computer (UMPC) with an average tracking error within 3 pixels when the camera image resolution is 320 by 240 pixels. This capability enabled the proposed method to be successfully applied to a mobile augmented reality (AR) guidance system for a museum.

A tracking framework for augmented reality tours on cultural heritage sites

“…Figure 5 shows the workflow of model-based camera track- ing, but as this is an extended version of our tracking method published in [Park et al 2010], this paper does not go into full details, just giving a summary.…”

Subjective Evaluation on Perceptual Tracking Errors from Modeling Errors in Model-Based Tracking

“…In model-based tracking, computational tracking errors can be considered as matching errors between a 3D model and its corresponding features detected in an image; thus, in the evaluation, computational matching errors were evaluated by mean distance errors between boundary edges of the 3D model projected on the rendered image with estimated poses and their corresponding edges detected in the rendered image [11]. Here, the camera calibration was performed offline and an initial pose was given in advance.…”