2009
DOI: 10.1007/978-3-642-03061-1_2
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: Fig. 1. Optical flow for the backyard and mini cooper scene of the Middlebury optical flow benchmark. Optical flow captures the dynamics of a scene by estimating the motion of every pixel between two frames of an image sequence. The displacement of every pixel is shown as displacement vectors on top of the commonly used flow color scheme (see Figure 5). Abstract.A look at the Middlebury optical flow benchmark [5] reveals that nowadays variational methods yield the most accurate optical flow fields between two … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

2
226
0

Year Published

2010
2010
2023
2023

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 320 publications
(228 citation statements)
references
References 30 publications
2
226
0
Order By: Relevance
“…In this section, we evaluate the motion estimation and occlusion detection performance of our approach on this dataset and on the well-known Flower Garden sequence. We have also compared our algorithm to Wedel et al (2008), Black and Anandan (1996) and Kolmogorov and Zabih (2001) quantitatively. To handle the large motion, we run our method on a Gaussian pyramid with a scale factor 0.5 up to 5 levels.…”
Section: Methodsmentioning
confidence: 99%
See 4 more Smart Citations
“…In this section, we evaluate the motion estimation and occlusion detection performance of our approach on this dataset and on the well-known Flower Garden sequence. We have also compared our algorithm to Wedel et al (2008), Black and Anandan (1996) and Kolmogorov and Zabih (2001) quantitatively. To handle the large motion, we run our method on a Gaussian pyramid with a scale factor 0.5 up to 5 levels.…”
Section: Methodsmentioning
confidence: 99%
“…For the re-weighting step, we have also fixed the coefficient to 0.001. In our experiments, we also use a non-linear pre-filtering of the images to reduce the influence of illumination changes (Rudin et al 1992;Wedel et al 2008;Sun et al 2010) to initialize the reweighting stage with an accurate flow field. However, during the re-weighting steps we use the original images since prefiltering reduces the occlusion detection accuracy.…”
Section: Methodsmentioning
confidence: 99%
See 3 more Smart Citations