A Generative Model Based Approach to Motion Segmentation

@inproceedings{Cremers2003AGM,
  title={A Generative Model Based Approach to Motion Segmentation},
  author={Daniel Cremers and Alan L. Yuille},
  booktitle={DAGM-Symposium},
  year={2003}
}
We address the question of how to choose between different likelihood functions for motion estimation. To this end, we formulate motion estimation as a problem of Bayesian inference and compare the likelihood functions generated by various models for image formation. In contrast to alternative approaches which focus on noise in the measurement process, we… CONTINUE READING