Cellular Neural Network-based object-oriented video compression: Performance evaluation

被引：0

作者：

Grassi, Giuseppe ^{[1
]}

Vecchio, Pietro ^{[1
]}

机构：

[1] Univ Salento, Dipartimento Ingn Innovaz, I-73100 Lecce, Italy

来源：

DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS | 2007年 / 14卷 / 05期

关键词：

Cellular Neural Networks; object-oriented methods; image processing; video compression; neural dynamics;

D O I：

暂无

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

In the context of video delivering techniques some efforts have been recently devoted to the development of Cellular Neural Network-based (CNN-based) architecture for real-time object-oriented video coding applications. However, until now attention has been mainly focused on the basic functionality of the architecture, rather than on the system performances. This paper bridges the gap by analyzing the compression capabilities related to some benchmark video sequences. In particular, by considering the bit-per-pixel and the Peak Signal to Noise Ratio related to Foreman and Car-phone video sequences, the paper shows that the CNN-based coding approach outperforms the MPEG-4 codec without any CNN capability. Comparisons with different MPEG-4 codecs confirm the potentiality of the proposed CNN-based coding paradigm.

引用

页码：705 / 716

页数：12

共 13 条

[1] CNN: A vision of complexity
Chua, LO
[J]. INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 1997, 7 (10): : 2219 - 2425
[2] CHUA LO, 1988, IEEE T CIRCUITS SYST, V35, P1272
[3] MPEG-4 natural video coding - An overview
Ebrahimi, T
Horne, C
[J]. SIGNAL PROCESSING-IMAGE COMMUNICATION, 2000, 15 (4-5) : 365 - 385
[4] A new approach to design cellular neural networks for associative memories
Grassi, G
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1997, 44 (09): : 835 - 838
[5] New object-oriented segmentation algorithm based on the CNN paradigm
Grassi, G
Di Sciascio, E
Grieco, LA
Vecchio, P
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2006, 53 (04): : 259 - 263
[6] CNN-based architecture for real-time object-oriented video coding applications
Grassi, G
Grieco, LA
[J]. INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS, 2005, 33 (01) : 53 - 64
[7] Object-oriented image analysis using the CNN universal machine: New analogic CNN algorithms for motion compensation, image synthesis, and consistency observation
Grassi, G
Grieco, LA
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2003, 50 (04) : 488 - 499
[8] MPEG-4 - Multimedia for our time
Koenen, R
[J]. IEEE SPECTRUM, 1999, 36 (02) : 26 - 33
[9] Pourmohammadi-Fallah Y, 2004, IEEE POTENTIALS, V23, P34, DOI 10.1109/MP.2004.1266939
[10] THE CNN UNIVERSAL MACHINE - AN ANALOGIC ARRAY COMPUTER
ROSKA, T
CHUA, LO
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING, 1993, 40 (03): : 163 - 173

← 1 2 →