Abstract | ||
---|---|---|
This paper presents a novel framework for object-based video inpainting. To complete an occluded object, our method first samples a 3-D volume of the video into directional spatio-temporal slices, and then performs patch-based image inpainting to repair the partially damaged object trajectories in the 2-D slices. The completed slices are subsequently combined to obtain a sequence of virtual contours of the damaged object. The virtual contours and a posture sequence retrieval technique are then used to retrieve the most similar sequence of object postures in the available non-occluded postures. Key-posture selection and indexing are performed to reduce the complexity of posture sequence retrieval. We also propose a synthetic posture generation scheme that enriches the collection of key-postures so as to reduce the effect of insufficient key-postures. Our experimental results demonstrate that the proposed method can maintain the spatial consistency and temporal motion continuity of an object simultaneously. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICIP.2009.5414183 | ICIP |
Keywords | Field | DocType |
video signal processing,video object inpainting,virtual contours,damaged object,video inpainitng,posture mapping,object posture,synthetic posture generation scheme,occluded object,object trajectory,spatial consistency,temporal motion continuity,synthetic posture,computer graphics,object postures,image restoration,directional spatio-temporal slices,posture sequence retrieval,available nonoccluded posture,object detection,similar sequence,virtual contour,object-based video inpainting,key-posture selection,posture sequence retrieval technique,nonoccluded postures,object completion,patch-based image inpainting,skeleton,trajectory,shape,indexation,construction industry,databases,feature extraction | Computer vision,Object detection,Pattern recognition,Computer science,Search engine indexing,Inpainting,Feature extraction,Artificial intelligence,Image restoration,Computer graphics,Trajectory,Spatial consistency | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4244-5655-0 | 978-1-4244-5655-0 | 5 |
PageRank | References | Authors |
0.47 | 8 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chih-Hung Ling | 1 | 23 | 2.23 |
Chia-Wen Lin | 2 | 1639 | 120.23 |
Chih-Wen Su | 3 | 170 | 13.94 |
h y m liao | 4 | 2353 | 198.72 |
Yong-Sheng Chen | 5 | 314 | 30.12 |