Title :
VORTEX: video retrieval and tracking from compressed multimedia databases
Author :
Schonfeld, Dan ; Lelescu, Dan
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Illinois Univ., Chicago, IL, USA
Abstract :
A novel algorithm for video retrieval and tracking from compressed multimedia databases is proposed. Our approach exploits the structure of video compression standards in order to perform object matching directly on the compressed video data. This is achieved by utilizing motion compensation-a critical prediction filter embedded in video compression standards-to estimate and interpolate the desired method for template matching
Keywords :
data compression; image matching; image retrieval; multimedia databases; video coding; VORTEX; compressed multimedia databases; compressed video data; critical prediction filter; motion compensation; object matching; template matching; video compression standards; video retrieval; video tracking; Image coding; Image retrieval; Image segmentation; Information retrieval; Layout; Matched filters; Motion compensation; Motion estimation; Multimedia databases; Tracking; Video compression; Visual databases;
Conference_Titel :
Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on
Print_ISBN :
0-8186-8821-1
DOI :
10.1109/ICIP.1998.727149
