Motion estimation with object based regularisation
S. Panis,John Cosmas +1 more
TL;DR: In this paper, a dynamic programming based matching method for motion estimation is presented, which optimises a Bayesian maximum likelihood function in a 3D optimisation space, consisting of a matching cost and an object based 2D regularisation cost.
read more
Abstract: A dynamic programming based matching method for motion estimation. That optimises a Bayesian maximum likelihood function in a 3-D optimisation space, is presented. The Bayesian function consists of a matching cost and an object based 2-D regularisation cost. The method gives results more accurate than block-based matching since the motion boundaries are close to the actual object boundaries.
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
Extrapolation-free arbitrary-shape motion estimation using phase correlation
Vasileios Argyriou,T. Vlachos +1 more
TL;DR: It is demonstrated that the proposed frequency domain scheme based on phase correlation and the shape adaptive discrete Fourier transform outperforms in terms of subpixel accuracy and motion-compensated prediction error both conventional phase correlation but also shape adaptive techniques operating in the frequency domain and requiring extrapolation.
7
•Dissertation
Advanced motion estimation algorithms in the frequency domain for digital video applications.
Vasileios. Argyriou
- 01 Jan 2006
TL;DR: Two fast dense motion estimation methods operating in the frequency domain are presented based either on texture segmentation or multi overlapped correlation, utilising either weighted averages or the novel gradient normalised convolution to restore missing motion vectors of the resulting dense vector field, requiring significant lower computational power compared to spatial and robust algorithms.
3
References
Occlusions and Binocular Stereo
Davi Geiger,Bruce Ladendorf,Alan L. Yuille +2 more
- 19 May 1992
TL;DR: In this paper, the authors show that occlusions can help stereo computation by providing cues for depth discontinuities, which can be used to improve the performance of stereo estimation.
Occlusions and binocular stereo
TL;DR: A theory for stereo is described based on the Bayesian approach, using adaptive windows and a prior weak smoothness constraint, which incorporates occlusion, and it is shown that occlusions can help stereo computation by providing cues for depth discontinuities.
280