Title :
MPEG-4 encoder architecture for a shape segmentation CNN chip
Author :
Koskinen, Luuri ; Paasio, Ari ; Kananen, Asko ; Halonen, Kari
Author_Institution :
Electron. Circuit Design Lab., Helsinki Univ. of Technol., Finland
Abstract :
A core of a digital encoder architecture has been simulated to investigate the suitability of a proposed cellular nonlinear network (CNN) algorithm for the video coding standard MPEG-4. The shape segmentation was simulated along with shape-adaptive DCT, motion estimation and motion compensation. The algorithm is found to be very suitable for MPEG-4 arbitrary shape segmentation. To realize the algorithm QCIF-size implementations capable of low-power and real time segmentation have been done
Keywords :
discrete cosine transforms; image segmentation; motion compensation; motion estimation; video coding; MPEG-4 encoder architecture; cellular nonlinear network algorithm; motion compensation; motion estimation; shape segmentation; shape-adaptive DCT; video coding standard; Cellular networks; Cellular neural networks; Concurrent computing; Discrete cosine transforms; Encoding; MPEG 4 Standard; Motion detection; Motion estimation; Shape; Video coding;
Conference_Titel :
MPEG-4. 2001 Proceedings of Workshop and Exhibition on
Conference_Location :
San Jose, CA
Print_ISBN :
0-7803-7165-8
DOI :
10.1109/MPEG.2001.996443
