Title :
Temporal frame interpolation for stereoscopic sequences using object-based motion estimation and occlusion detection
Author :
Grammalidis, N. ; Tzovarns, D. ; Strintzis, M.G.
Author_Institution :
Inf. Processing Lab., Aristotelian Univ. of Thessaloniki, Greece
Abstract :
Temporal frame interpolation techniques are presented, based on an object-based algorithm for 3-D motion estimation. This algorithm uses a joint estimation-segmentation scheme to minimize the displaced frame difference between a frame and its motion compensated prediction from the previous frame. Depth information is estimated beforehand from each stereo pair. Special attention is paid to the exploitation of occlusion information so as to improve the reconstruction quality of the interpolated frames. Experimental results are used to evaluate the performance of the proposed methods and to compare with more conventional frame interpolation techniques
Keywords :
image reconstruction; image segmentation; image sequences; interpolation; motion compensation; motion estimation; prediction theory; signal detection; stereo image processing; 3D motion estimation; depth information; displaced frame difference; experimental results; interpolated frames; joint estimation-segmentation algorithm; motion compensated prediction; object based algorithm; object based motion estimation; occlusion detection; occlusion information; performance evaluation; reconstruction quality; stereoscopic sequences; temporal frame interpolation; Bit rate; HDTV; Image reconstruction; Image segmentation; Information processing; Interpolation; Laboratories; Motion detection; Motion estimation; Pixel;
Conference_Titel :
Image Processing, 1995. Proceedings., International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-8186-7310-9
DOI :
10.1109/ICIP.1995.537495