Title :
A fast feature matching algorithm of multi-resolution motion estimation
Author :
Lee, Xiaobing ; Leon-Garcia, A.
Author_Institution :
Dept. of Eng., Toronto Univ., Ont., Canada
Abstract :
A multiresolution motion estimation (MRME) algorithm based on the feature representation of image data, is developed. The sign truncated feature (STF) vector is derived for the feature matching phase of the motion estimation process. MRME can be performed on the STF vectors in full range motion search without the need for a search window control. The MRME algorithm is suitable for real-time VLSI pipeline and parallel processing, implementations with large searching windows for full search motion compensation. It needs 160% extra frame memory for the feature pyramid buffer. It can be more than ten times faster than conventional pixel-by-pixel intensity matching schemes, if a parallel 20-bit template matching operator is used
Keywords :
feature extraction; motion estimation; feature matching algorithm; feature pyramid buffer; feature representation; frame memory; image data; multiresolution motion estimation; parallel processing; range motion search; real time VLSI pipeline processing; search motion compensation; searching windows; sign truncated feature vector; Bandwidth; Data buses; Economic forecasting; Motion estimation; Pins; Satellite broadcasting; TV; Very large scale integration; Video codecs; Video compression;
Conference_Titel :
Global Telecommunications Conference, 1992. Conference Record., GLOBECOM '92. Communication for Global Users., IEEE
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-0608-2
DOI :
10.1109/GLOCOM.1992.276471
