Paper Info
Title
Motion vector refinement for FRUC using saliency and 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. An algorithm is proposed for improving both the objective and subjective quality of MCFI by refining the motion vector field. A Discriminant Saliency classifier is employed to determine regions of the motion field which are most important to a human observer. These regions are refined using a multi-stage motion vector refinement which promotes candidates based on their likelihood given a local neighborhood. For regions which fall below the saliency threshold, frame segmentation is used to locate regions of homogeneous color and texture via Normalized Cuts. Motion vectors are promoted such that each homogeneous region has a consistent motion. Experimental results demonstrate an improvement over previous methods in both objective and subjective picture quality.
Year
DOI
Venue
2010
10.1109/ICME.2010.5582574
Multimedia and Expo
Keywords
Field
DocType
image motion analysis,image segmentation,image sequences,frame rate up-conversion,motion segmentation,motion vector refinement,motion-compensated frame interpolation,repetitive structure,saliency,temporal frequency,video sequence,Discriminant Saliency,Frame Rate Up-Conversion (FRUC),Motion Compensated Frame Interpolation (MCFI),Motion Refinement,Motion Segmentation
Computer vision,Quarter-pixel motion,Motion field,Pattern recognition,Salience (neuroscience),Computer science,Interpolation,Image segmentation,Artificial intelligence,Motion interpolation,Motion estimation,Motion vector
Conference
ISSN
ISBN
Citations 
1945-7871
978-1-4244-7491-2
2
PageRank 
References 
Authors
0.39
7
5
Name
Order
Citations
PageRank
Natan Jacobson1443.65
Yen-Lin Lee2474.03
Vijay Mahadevan3106335.39
Nuno Vasconcelos45410273.99
Truong Q. Nguyen51402136.69