A Revisited Half-Quadratic Approach for Simultaneous Robust Fitting of Multiple Curves

Abstract

In this paper, we address the problem of robustly recovering several instances of a curve model from a single noisy data set with outliers. Using M-estimators revisited in a Lagrangian formalism, we derive an algorithm that we call Simultaneous Multiple Robust Fitting (SMRF), which extends the classical Iterative Reweighted Least Squares algorithm (IRLS). Compared to the IRLS, it features an extra probability ratio, which is classical in clustering algorithms, in the expression of the weights. Potential numerical issues are tackled by banning zero probabilities in the computation of the weights and by introducing a Gaussian prior on curves coefficients. Applications to camera calibration and lane-markings tracking show the effectiveness of the SMRF algorithm, which outperforms classical Gaussian mixture model algorithms in the presence of outliers.

Reference

@INCOLLECTION{jpt-ln08, author = {Tarel, J.-P. and Charbonnier, P. and Ieng, S.-S.}, title = {A Revisited Half-Quadratic Approach for Simultaneous Robust Fitting of Multiple Curves}, editor = {Braz, J. and Ranchordas, A. and Ara\'ujo, H. and Pereira, J. M.}, booktitle = {Computer vision and Computer Graphics, revised selected papers of visigrapp'07, CCIS 21}, publisher = {Springer-Verlag}, address = {Berlin Heidelberg, Germany}, year = {2009}, pages = {121--133}, url = {http://perso.lcpc.fr/tarel.jean-philippe/publis/ln08.html} }