Low bit-rate coding of image sequences using adaptive regions of interest

Author

Doulamis, Nikolaos ; Doulamis, Anastasios ; Kalogeras, Dimitrios ; Kollias, Stefanos

Author_Institution

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

Volume

8

Issue

8

fYear

1998

fDate

12/1/1998 12:00:00 AM

Firstpage

928

Lastpage

934

Abstract

An adaptive algorithm for extracting foreground objects from background in videophone or videoconference applications is presented. The algorithm uses a neural network architecture that classifies the video frames in regions of interest (ROI) and non-ROI areas, also being able to automatically adapt its performance to scene changes. The algorithm is incorporated in motion-compensated discrete cosine transform (MC-DCT)-based coding schemes, allocating more bits to ROI than to non-ROI areas. Simulation results are presented, using the Claire and Trevor sequences, which show reconstructed images of better quality, as well as signal-to-noise ratio improvements of about 1.4 dB, compared to those achieved by standard MC-DCT encoders

Keywords

adaptive signal processing; discrete cosine transforms; image classification; image reconstruction; image segmentation; image sequences; motion compensation; neural net architecture; teleconferencing; transform coding; video coding; videotelephony; MC-DCT based coding; MC-DCT encoders; adaptive algorithm; adaptive regions of interest; background; foreground objects extraction; image sequences; low bit-rate coding; motion-compensated discrete cosine transform; neural network architecture; nonROI areas; performance; reconstructed image quality; scene changes; signal-to-noise ratio; simulation results; video frames classification; videoconference application; videophone; Bit rate; Head; Image coding; Image reconstruction; Image sequences; Layout; Neural networks; Transform coding; Video compression; Videoconference;

fLanguage

English

Journal_Title

Circuits and Systems for Video Technology, IEEE Transactions on

Publisher

ieee

ISSN

1051-8215

Type

jour

DOI

10.1109/76.736718

Filename

736718