A RANSAC-Based Approach to Model Fitting and Its Application to Finding Cylinders in Range Data

General principles for fitting models to data containing "gross" errors in addition to "measurement" errors are presented A fitting technique is described and illustrated by its application to the problem of locating cylinders in range data, two key steps in this process arc fitting ellipses to partial data and fitting lines to sets of three-dimensional points The technique is specifically designed to filter out gross errors before applying a smoothing procedure to compute a precise model Such a technique is particularly applicable to computer vision tasks because the data in these tasks arc often produced by local computations that are inherently unreliable