Open AccessProceedings Article
Automatic object segmentation algorithms for sprite coding using MPEG-4
Andreas Krutz,Alexander Glantz,Thomas Sikora,Paulo Nunes,F. Pereira +4 more
- 01 Sep 2008
- Vol. 2, pp 459-462
TL;DR: This work considers sprite coding which increases significantly the objective as well as the subjective quality of the coded video, and evaluates automatic object segmentation methods based on global motion estimation and background sprite generation using the standardized MPEG-4 visual main profile.
read more
Abstract: Object-based video coding, as standardized in MPEG-4 Part 2, can result in superior performance in comparison to common hybrid motion-compensated DCT-based approaches. We consider sprite coding which increases significantly the objective as well as the subjective quality of the coded video. The main challenge of this approach is the pre-segmentation of the video and the video content itself. To apply sprite coding, the input video has to be firstly segmented into foreground and background objects. We evaluate automatic object segmentation methods based on global motion estimation and background sprite generation. These algorithms are evaluated using the standardized MPEG-4 visual main profile (sprite coding).
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Automatic MPEG-4 sprite coding--Comparison of integrated object segmentation algorithms
TL;DR: This work considers sprite coding, which significantly increases the objective as well as the subjective quality of coded video content, and evaluates automatic object segmentation methods based on global motion estimation and background sprite generation.
Sprite generation using sprite fusion
TL;DR: A novel sprite fusion method is introduced that blends two sprites and produces good results for tracking videos and does not require object segmentation.
6
Hybrid model-and-object-based real-time conversational video coding
Yang Li,Xiaoming Tao,Jianhua Lu +2 more
TL;DR: This paper proposes a low bit-rate coding method for typical conversational video by combining two-dimensional model-based coding of face regions and object- based coding of non-face head-shoulder regions, achieving high-quality face reconstruction and low overall bit-rates.
5
Transform-domain super resolution for improved motion-compensated prediction
Nafisa Tarannum,Mark R. Pickering,Michael R. Frater,John F. Arnold +3 more
- 03 Aug 2010
TL;DR: Experimental results show that the two-way motion compensation provides a better coding gain compared with a standard motion compensation approach and moreover, in the process of super resolution mosaic construction, the robust global motion estimation process outperforms other recent motion estimation techniques when utilizing the same compression framework.
3
•Dissertation
Coding of depth maps by elastic deformations of curves
Marco Calemme
- 20 Sep 2016
TL;DR: A subjective quality assessment test is conducted to compare an object-based technique and a hybrid block-based techniques for the coding of depth maps, based on the elastic deformation of curves.
1
References
Overview of the H.264/AVC video coding standard
TL;DR: An overview of the technical features of H.264/AVC is provided, profiles and applications for the standard are described, and the history of the standardization process is outlined.
•Book
The MPEG-4 Book
Fernando Pereira,Touradj Ebrahimi +1 more
- 20 Jul 2002
TL;DR: A comprehensive, targeted guide to the MPEG-4 standardand its use in cutting-edge applications, Fernando Pereira and Touradj Ebrahimi demonstrate how MPEG- 4 addresses tomorrow's multimedia applications more successfully than any previous standard.
369
Long-term global motion estimation and its application for sprite coding, content description, and segmentation
TL;DR: The presented results indicate that the proposed technique is a very accurate and robust approach for long-term global motion estimation, which can be used for applications such as MPEG-4 sprite coding or MPEG-7 motion description, and the efficiency of globalmotion estimation can be significantly increased if a higher order motion model is applied.
168
A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera
R. Mech,Michael Wollborn +1 more
TL;DR: An algorithm for automatic, noise robust 2D shape estimation of moving objects in video sequences is presented, which considers a moving camera, and the resulting object shapes look subjectively much better than those from the reference algorithm.
146
Windowed Image Registration for Robust Mosaicing of Scenes with Large Background Occlusions
Andreas Krutz,Michael R. Frater,Matthias Kunter,Thomas Sikora +3 more
- 01 Oct 2006
TL;DR: In this article, an enhanced window-based approach is proposed for robust video mosaicing in scenes with arbitrarily moving foreground objects, which can estimate accurately the image transformation without any pre-segmentation even if large background regions are occluded.
40