Design and implementation of an object-based video coder chip set based on syntactic pattern recognition

Author

Martinez-Smith, Alfonso ; Mathew, Sanu K. ; Sridhar, Ramalingam

Author_Institution

Dept. of Electr. & Comput. Eng., State Univ. of New York, Buffalo, NY, USA

fYear

1997

fDate

7-10 Sep 1997

Firstpage

251

Lastpage

255

Abstract

This paper presents the design and partial implementation of a chip set for a new object-based video coding technique. The hardware algorithm uses unsupervised learning of image contents for efficient second-generation coding of video. Computational complexity is controlled by storing a minimum feature set, upon which higher level contents are defined. Numerical results for test video sequences are given

Keywords

CMOS digital integrated circuits; VLSI; application specific integrated circuits; computational complexity; digital signal processing chips; image sequences; motion estimation; pattern recognition; unsupervised learning; video coding; computational complexity control; image content; minimum feature set; object-based video coder chip set; second-generation coding; syntactic pattern recognition; unsupervised learning; video sequences; Bit rate; Computational complexity; Hardware; Image coding; MPEG 4 Standard; Multimedia communication; Multimedia databases; Pattern recognition; Streaming media; Video coding;

fLanguage

English

Publisher

ieee

Conference_Titel

ASIC Conference and Exhibit, 1997. Proceedings., Tenth Annual IEEE International

Conference_Location

Portland, OR

ISSN

1063-0988

Print_ISBN

0-7803-4283-6

Type

conf

DOI

10.1109/ASIC.1997.617016

Filename

617016