2010
DOI: 10.1109/tip.2010.2050928
|View full text |Cite
|
Sign up to set email alerts
|

A Novel Approach to FRUC Using Discriminant Saliency and Frame Segmentation

Abstract: Motion-compensated frame interpolation (MCFI) is a technique used extensively for increasing the temporal frequency of a video sequence. In order to obtain a high quality interpolation, the motion field between frames must be well-estimated. However, many current techniques for determining the motion are prone to errors in occlusion regions, as well as regions with repetitive structure. We propose an algorithm for improving both the objective and subjective quality of MCFI by refining the motion vector field. … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
14
0
2

Year Published

2011
2011
2022
2022

Publication Types

Select...
6
2
1

Relationship

1
8

Authors

Journals

citations
Cited by 48 publications
(16 citation statements)
references
References 33 publications
0
14
0
2
Order By: Relevance
“…FRUC is employed at the mobile device in order to re-establish the original frame rate of the sequence. The proposed FRUC algorithm, based on the work of [4], is outlined in Fig. 2.…”
Section: Frame Rate Up-conversionmentioning
confidence: 99%
See 1 more Smart Citation
“…FRUC is employed at the mobile device in order to re-establish the original frame rate of the sequence. The proposed FRUC algorithm, based on the work of [4], is outlined in Fig. 2.…”
Section: Frame Rate Up-conversionmentioning
confidence: 99%
“…The FRUC method described in Section 3 is examined using our scale-aware saliency maps. Results are compared with previous work due to Multi-scale Successive Elimination Algorithm (MSEA) [5], Multiscale Motion Vector Processing (MMVP) [9], as well as the saliency-based approach of [4]. These are shown in Table 2 using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) as performance metrics.…”
Section: Fruc Applicationmentioning
confidence: 99%
“…Applications of image segmentation are numerous: from remote sensing [1] and video processing [2] to non-destructive testing [3]. Within the biomedical field, segmentation is used with diverse imaging modalities such as MRI [4], both light microscopy [5]- [7] and electron microscopy [8], ultrasound [9], and many others to identify regions at all scales from organelles to organisms.…”
Section: Introductionmentioning
confidence: 99%
“…Instead of employing a single uniquely optimal motion, Liu et al [11] proposed a multiple hypotheses Bayesian scheme, which obtain the multiple motion fields by progressively reducing the size of matching block. In the work by Jacobson et al [12], the visually important regions in a scene were first detected by a discriminant saliency classifier. The MVs of these regions were then refined using multiple block sizes to improve the frame interpolation process.…”
Section: Introductionmentioning
confidence: 99%