Year: 2015
Type: review
Study design: Systematic Review
Abstract: In this paper, we review the advances of monocular model-based tracking for \nlast ten years period until 2014. In 2005, Lepetit, et. al, [19] reviewed the status \nof monocular model based rigid body tracking. Since then, direct 3D tracking has \nbecome quite popular research area, but monocular model-based tracking should \nstill not be forgotten. We mainly focus on tracking, which could be applied to aug- \nmented reality, but also some other applications are covered. Given the wide subject \narea this paper tries to give a broad view on the research that has been conducted, \ngiving the reader an introduction to the different disciplines that are tightly related \nto model-based tracking. The work has been conducted by searching through well \nknown academic search databases in a systematic manner, and by selecting certain \npublications for closer examination. We analyze the results by dividing the found \npapers into different categories by their way of implementation. The issues which \nhave not yet been solved are discussed. We also discuss on emerging model-based \nmethods such as fusing different types of features and region-based pose estimation \nwhich could show the way for future research in this subject.
Source: UTUPub (University of Turku)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: Tekes, Turun Yliopisto, Lloyd's Register
OpenAlex ID: W1817373104