DMCA
Semi-Autonomous Generation of Appearance-based Edge Models from Image Sequences
| Citations: | 6 - 0 self |
BibTeX
@MISC{Neubert_semi-autonomousgeneration,
author = {Jeremiah Neubert and John Pretlove and Tom Drummond},
title = {Semi-Autonomous Generation of Appearance-based Edge Models from Image Sequences},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Figure 1: Creation of 3D edge models directly from image sequences. The user indicates planar regions of an object to generate a polygon in (a). The planar regions are reconstructed, keyframes, consisting of sets of edgels (white lines) inside the planar region, are selected to capture viewpoint related changes in appearance (b). The resulting model is used to track the object in real-time (c). Many of the robust visual tracking techniques utilized by augmented reality applications rely on 3D models and information extracted from images. Models enhanced with image information make it possible to initialize tracking and detect poor registration. Unfortunately, generating 3D CAD models and registering them to image information can be a time consuming operation. Regularly the process requires multiple trips between the site being modeled and the workstation used to create the model. The system presented in this work eliminates the need for a separately generated 3D model by utilizing modern structure-from-motion techniques to extract the model and associated image information directly from an image sequence. The technique can be implemented on any handheld device instrumented with a camera and network connection. The process of creating the model requires minimal user interaction in the form of a few cues to identify planar regions on the object of interest. In addition the system selects a set of keyframes for each region to capture viewpoint based appearance changes. This work also presents a robust tracking framework to take advantage of these new edge models. Performance of both the modeling technique and the tracking system are verified on several different objects.
Keyphrases
image sequence planar region semi-autonomous generation appearance-based edge model image information tracking system modern structure-from-motion technique new edge model augmented reality application detect poor registration handheld device multiple trip robust tracking framework modeling technique edge model network connection several different object minimal user interaction appearance change cad model white line
