Abstract
In recent years, many studies have addressed interactive services in smart TV context. For example, any interactive service should be able to allow users to create annotations in collaborative environments. This paper proposes a system architecture that can provide augmented information (interactive content) synchronized with video content in collaborative video annotation environments. The paper also proposes the dynamic sampling-based cubic spline interpolation (DSCSI) algorithm, a method for efficiently storing moving trajectories (x- and y-coordinates) and object shapes (width and height). A collaborative video annotation competition is organized using the closed beta service to evaluate the performance of the proposed system. The experimental results based on metadata obtained from the participants demonstrate that the proposed method can successfully reduce up to 74% of the size of trajectory data with an average error of 1.23. pixels.
Original language | English |
---|---|
Pages (from-to) | 291-300 |
Number of pages | 10 |
Journal | Neurocomputing |
Volume | 146 |
DOIs | |
State | Published - 25 Dec 2014 |
Bibliographical note
Funding Information:This work was supported by the National Research Foundation of Korea grant funded by the Korea government (MEST) (No. 2011-0015484 ).
Keywords
- Collaborative video annotation
- Dynamic sampling-based cubic spline interpolation
- Interactive TV service