Moving object segmentation algorithm based on cellular neural networks in the H.264 compressed domain

Feng Jie; Yaowu Chen; Xiang Tian

doi:10.1117/1.3158987

1 July 2009 Moving object segmentation algorithm based on cellular neural networks in the H.264 compressed domain

Feng Jie, Yaowu Chen, Xiang Tian

Author Affiliations +

Optical Engineering, Vol. 48, Issue 7, 077001 (July 2009). https://doi.org/10.1117/1.3158987

Abstract

A cellular neural network (CNN)-based moving object segmentation algorithm in the H.264 compressed domain is proposed. This algorithm mainly utilizes motion vectors directly extracted from H.264 bitstreams. To improve the robustness of the motion vector information, the intramodes in I-frames are used for smooth and nonsmooth region classification, and the residual coefficient energy of P-frames is used to update the classification results first. Then, an adaptive motion vector filter is used according to interpartition modes. Finally, many CNN models are applied to implement moving object segmentation based on motion vector fields. Experiment results are presented to verify the efficiency and the robustness of this algorithm.

©(2009) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Feng Jie, Yaowu Chen, and Xiang Tian "Moving object segmentation algorithm based on cellular neural networks in the H.264 compressed domain," Optical Engineering 48(7), 077001 (1 July 2009). https://doi.org/10.1117/1.3158987

Published: 1 July 2009

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE