Motion vector prediction using frequency sensitive competitive learning

Authors:
HyungJun Kim
Affiliations:
Division of Information Technology, Hansei University, Korea
Venue:
ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
Year:
2006

Citing 4
Cited 0

Vector quantization and signal compression

Vector quantization and signal compression
Block-matching algorithm based on an adaptive reduction of the search area for motion estimation

Real-Time Imaging - Special issue on real-time digital video over multimedia networks
A fast block-matching algorithm using smooth motion vector field adaptive search technique

Journal of Computer Science and Technology
Motion vector quantization for video coding

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a search region prediction method using a Frequency Sensitive Competitive Learning(FSCL) algorithm for the adaptive vector quantization of the motion vector. We train the motion vector codebook using the first two successive images of a sequence of images and utilize it for search region prediction. The proposed method can reduce computation time by using a smaller number of search points compared to other methods, and also decreases the bits required to represent motion vectors. The experimental results show that it provides competitive PSNR values compared to other block matching algorithms.