Object based coding of video sequences at low bit rates using adaptively trained neural networks

Author

Doulamis, Nikolaos D. ; Doulamis, Anastasios D. ; Kollias, Stefanos D.

Author_Institution

Dept. of Electr. & Comput. Eng., Nat. Tech. Univ. of Athens, Greece

Volume

2

fYear

1999

fDate

5-8 Sep 1999

Firstpage

969

Abstract

Unsupervised video object segmentation is proposed in this paper, using an adaptively trained neural network structure followed by a face and body detection scheme. The latter uses probabilistic modeling for applying the face and body detection task. The algorithm is incorporated along with a rate control mechanism, which allocates more bits to regions of importance, such as humans in video conferencing applications than to unimportant ones. The compatibility to block-based encoders, such as the MPEG-1/2 and the H.263, is retained, so that the proposed scheme can further improve their coding efficiency

Keywords

face recognition; image segmentation; image sequences; learning (artificial intelligence); neural nets; teleconferencing; video coding; H.263; MPEG-1/2; adaptively trained neural networks; bit rates; block-based encoders; body detection scheme; coding efficiency; face detection scheme; object based coding; probabilistic modeling; rate control mechanism; unsupervised video object segmentation; video conferencing applications; video sequences; Bit rate; Face detection; Humans; Image coding; Neural networks; Object detection; Object segmentation; Telephony; Video sequences; Videoconference;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Circuits and Systems, 1999. Proceedings of ICECS '99. The 6th IEEE International Conference on

Conference_Location

Pafos

Print_ISBN

0-7803-5682-9

Type

conf

DOI

10.1109/ICECS.1999.813394

Filename

813394