Video Coding 1996
DOI: 10.1007/978-1-4613-1337-3_6
|View full text |Cite
|
Sign up to set email alerts
|

Segmentation-Based Motion Estimation for Second Generation Video Coding Techniques

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
14
0

Year Published

1998
1998
2014
2014

Publication Types

Select...
7
2
1

Relationship

1
9

Authors

Journals

citations
Cited by 24 publications
(14 citation statements)
references
References 35 publications
0
14
0
Order By: Relevance
“…The splitting criterion has effects on the relative volumes of DVF and DFD [7]- [12], and may give rise to unstable motion estimates due to an excesive refinement of the quadtree structure [12], [29]. The usefulness of the motion information for higher-level purposes (as in model-based video coding [5], [30], [31]) highly depends on its robustness (absence of false alarms) and hence on the splitting criterion. Motion-based segmentation algorithms [17], [18] require reliable initial motion information, especially when using sparse (nondense) flows such as those given by variable-size BMA.…”
Section: Conventional Techniques For Transform Quantizer Design Amentioning
confidence: 99%
“…The splitting criterion has effects on the relative volumes of DVF and DFD [7]- [12], and may give rise to unstable motion estimates due to an excesive refinement of the quadtree structure [12], [29]. The usefulness of the motion information for higher-level purposes (as in model-based video coding [5], [30], [31]) highly depends on its robustness (absence of false alarms) and hence on the splitting criterion. Motion-based segmentation algorithms [17], [18] require reliable initial motion information, especially when using sparse (nondense) flows such as those given by variable-size BMA.…”
Section: Conventional Techniques For Transform Quantizer Design Amentioning
confidence: 99%
“…Three-dimensional models have also been applied for the detection, segmentation, and tracking of moving objects in different scenarios [25], [59]. Kalman filtering has been proposed as well for allowing object tracking [16]. Last, a very popular approach to the problem of motion spatial segmentation relies on the use of compound Markov random field (MRF) models [21], [9].…”
Section: ) Homogeneity-based Approach To Spatial or Spatio-temporal mentioning
confidence: 99%
“…[2][3][4][5][6] Tracking can also be used to assist estimation of coherent motion trajectories and to support object segmentation (cf. 7 ).…”
Section: Introductionmentioning
confidence: 99%