Title :
A novel motion estimation technique: patch-matching
Author :
Liu, Tianming ; Qi, Feihu ; Zhan, Yiqiang
Author_Institution :
Dept. of Comput. Sci. & Eng., Shanghai Jiaotong Univ., China
Abstract :
The emerging MPEG-4 and MPEG-7 content-based facilities demands segmentation of moving semantic objects in video sequences. Motion is one of main information sources that segmentation algorithms can rely on. In this paper, the authors propose a novel motion estimation technique: patch-matching (PM). The motion of image patches of piecewise smooth intensity is modeled by two parameters and estimated using SAD-based matching. Simple-parametric-motion-model-and-small-support-region is preferred here to complex-parametric-motion-model-and-large-support-region. Both forward and backward PMs are performed to discriminate occlusion regions. Experiment results show the performance of the technique
Keywords :
image matching; image segmentation; image sequences; motion estimation; video signal processing; MPEG-4 content-based facilities; MPEG-7 content-based facilities; SAD-based matching; backward patch-matching; forward patch-matching; image patch motion; information sources; motion estimation; moving semantic objects; occlusion regions; parametric-motion-model; piecewise smooth intensity; segmentation algorithms; small support region; video sequences; Image motion analysis; Image segmentation; MPEG 4 Standard; MPEG 7 Standard; Motion estimation; Optical computing; Parameter estimation; Parametric statistics; Streaming media; Video sequences;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.891728
