Robust Estimation for Motion Parameters

The performance of least squares method ca'n be improved by changing the error metric so that points which lie far from the bulk of data do not influence the final value—that is to reject the outliers. In this paper, the combination of two robust estimators are used to obtain motion parameters of a camera from matched image features. Results obtained show that the robust estimator has the ability to remove gross errors and mismatch points automatically. Therefore the existence of a small amount of outliers or mismatches will not affect the final results. Different robust estimators can be used for the purpose of parameters estimation. In our case the Huber and Tukey's estimators are used which allows ten per cent mismatches. Median absolute estimator can also be used which can allow as high as fifty per cent outliers in the whole corresponding points. But one of the disadvantage is that it will take much more time.