Title :
MPEG-4 based modifications for an CNN segmentation chip
Author :
Koskinen, Lauri ; Laiho, Mika ; Paasio, Art ; Halonen, Kart
Author_Institution :
Electron. Circuit Design Lab., Helsinki Univ. of Technol., Finland
Abstract :
The suitability of an existing cellular nonlinear network (CNN) chip for MPEG-4 core profile shape segmentation is investigated. The chip and the algorithm it is based on are found to be suitable for shape segmentation and additional templates are proposed to enhance the chip´s MPEG-4 suitability. Additional uses for the CNN chip are found in MPEG-4 encoder computational power demand reduction.
Keywords :
cellular neural nets; image segmentation; motion estimation; neural chips; video signal processing; MPEG-4 core profile shape segmentation; MPEG-4 encoder computational power demand reduction; algorithm; cellular nonlinear network segmentation chip; templates; 3G mobile communication; Cellular networks; Cellular neural networks; Computer architecture; Energy consumption; Image segmentation; MPEG 4 Standard; Motion detection; Shape control; Video sequences;
Conference_Titel :
Cellular Neural Networks and Their Applications, 2002. (CNNA 2002). Proceedings of the 2002 7th IEEE International Workshop on
Print_ISBN :
981-238-121-X
DOI :
10.1109/CNNA.2002.1035037
