By Topic

Neural network based motion vector computation and application to MPEG coding

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
S. S. Skrzypkowiak ; Dept. of Electr. Eng., Univ. of South Florida, Tampa, FL, USA ; V. K. Jain

A neural network based motion-estimation technique is developed, that is applicable to sub-pixel as well as large movements. Experiments on typical test frame sequences indicate marked improvement in accuracy of motion vector estimates over the MPEG logarithmic block matching algorithm. The method utilizes a modified Hopfield neural network. Due to the neural network's fault-tolerant nature and parallel computation capability, fast, accurate, and reliable results are obtained. Application to MPEG based video compression is also discussed

Published in:

Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference  (Volume:2 )

Date of Conference:

13-16 Nov 1994