Temporal frame interpolation for stereoscopic sequences using object-based motion estimation and occlusion detection
Image Processing, International Conference on (1995)
Oct. 23, 1995 to Oct. 26, 1995
N. Grammalidis , Inf. Processing Lab., Aristotelian Univ. of Thessaloniki, Greece
D. Tzovarns , Inf. Processing Lab., Aristotelian Univ. of Thessaloniki, Greece
M.G. Strintzis , Inf. Processing Lab., Aristotelian Univ. of Thessaloniki, Greece
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.
stereo image processing; image sequences; motion estimation; image segmentation; image reconstruction; motion compensation; prediction theory; signal detection; interpolation; temporal frame interpolation; stereoscopic sequences; object based motion estimation; occlusion detection; object based algorithm; 3D motion estimation; joint estimation-segmentation algorithm; displaced frame difference; motion compensated prediction; depth information; occlusion information; reconstruction quality; interpolated frames; experimental results; performance evaluation
M. Strintzis, D. Tzovarns and N. Grammalidis, "Temporal frame interpolation for stereoscopic sequences using object-based motion estimation and occlusion detection," Image Processing, International Conference on(ICIP), Washington D.C., 1995, pp. 2382.