Motion Estimation Using a Compounded Self Organizing Map-multi Layer Perceptron Network

@inproceedings{MichaelisMotionEU,
  title={Motion Estimation Using a Compounded Self Organizing Map-multi Layer Perceptron Network},
  author={Bernd Michaelis and Olaf Schnelting and Udo Seiffert and R{\"u}diger Mecke}
}
In this paper the utilization of Artificial Neural Networks (ANN) for motion estimation is considered. With simple neural structures it is possible to improve the reliability and accuracy of block matching algorithms (BMA) by a postprocessing of the similarity criterion. The ANN dimensions the appropriate structures. An associative memory realizes an adaptive choise of these filtering structures depending on the image contents. The fundamental idea and some first results will be described. The… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-9 of 9 references

Artifical Neural Networks for Motion Estimation

  • O. Schnelting, B. Michaelis, R. Mecke
  • Proc. ICANNGA 95, Ales, France,
  • 1995
1 Excerpt

Motion Estimation by Using Artifical Neural Networks

  • O. Schnelting, B. Michaelis, R. Mecke
  • IEEE NIPS 95, Neos Marmas Halkidiki, Greece,
  • 1995
1 Excerpt

Neural Network for Motion Estimation and Interpretation

  • G. Convertino
  • Proc. ICANN' 94, Sorrento, Italy,
  • 1994
1 Excerpt

Hopfield : Neural Network for Motion Estimation and Interpretation

  • G. Convertino

Similar Papers

Loading similar papers…