High-speed real-time augmented reality tracking algorithm model of camera based on mixed feature points
- PDF / 1,553,392 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 80 Downloads / 173 Views
SPECIAL ISSUE PAPER
High‑speed real‑time augmented reality tracking algorithm model of camera based on mixed feature points Wei Sun1 · Chengcheng Mo2 Received: 25 February 2020 / Accepted: 6 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract At this stage of augmented reality, simple feature descriptions are mainly used in camera real-time motion tracking, but this is prone to the problem of unstable camera motion tracking. Aiming at the balance between real-time performance and stability, a new method model of real-time camera motion tracking based on mixed features was proposed. By comprehensively using feature points and feature lines as scene features, feature extraction, optimization, and fusion are used to construct hybrid features, and the hybrid features are unified for real-time camera parameter estimation. An image feature optimization method based on scene structure analysis is proposed to meet the computing constraints of mobile terminals. An iterative feature line-screening method is proposed to calculate a stable feature line set, and based on the scene feature composition and feature geometry, a hybrid feature is adaptively constructed to improve the tracking stability of the camera. Based on improved SIFT feature matching target detection and tracking algorithm, a hybrid feature point detection operator detection algorithm is used to achieve rapid feature point extraction, and the speed of descriptor generation is reduced by reducing the feature descriptor vector dimension. The experimental results prove that the proposed target detection and tracking algorithm has good real-time and robustness, and improves the success rate of target detection and tracking. Keywords Mixed feature points · Augmented reality · New tracking model · Real-time estimation · Detection operator
1 Introduction Machine vision-based target detection and tracking technology uses feature matching between video images and targets, so the error range is limited to image coordinates, and the accuracy is up to the pixel level. It is currently the solution adopted by mainstream AR applications. This article mainly introduces target detection and tracking technology based on machine vision. Methods based on visual target detection and tracking can be roughly divided into the following two categories: marker based and non-marker based.
* Chengcheng Mo [email protected] Wei Sun [email protected] 1
School of Literature and Journalism, Hunan University of Technology and Business, Changsha 410205, China
School of Cinema and Television, Sichuan University of Media and Communications, Chengdu 611745, Sichuan, China
2
In recent years, a large number of methods have been proposed regarding the tracking of mixed feature points. At present, the main methods used at home and abroad are divided into three categories: tracking methods based on underlying features, model-based methods, and particle filter-based tracking methods. Methods based on the underlying features mostly use color or texture featur
Data Loading...
