Estimating the essential matrix: GOODSAC versus RANSAC

GOODSAC is a paradigm for estimation of model parameters given measurementsthat are contaminated by outliers. Thus, it is analternative to the well known RANSAC strategy. GOODSAC’s search fora proper set of inliers does not only maximize the sheer size ofthis set, but also takes other assessments for the utility into account.Assessments can be used on many levels of the process to controlthe search and foster precision and proper utilization of the computationalresources. This contribution discusses and compares the twomethods. In particular, the estimation of essential matrices is usedas example. The comparison is performed on synthetic and real dataand is based on standard statistical methods, where GOODSAC achieveshigher precision than RANSAC.     «

GOODSAC is a paradigm for estimation of model parameters given measurementsthat are contaminated by outliers. Thus, it is analternative to the well known RANSAC strategy. GOODSAC’s search fora proper set of inliers does not only maximize the sheer size ofthis set, but also takes other assessments for the utility into account.Assessments can be used on many levels of the process to controlthe search and foster precision and proper utilization of the computationalresources. This contribution discu...     »