Scale Adaptive Clustering of Multiple Structures

TL;DR

The paper introduces MISRE, a robust, parameter-free clustering method that adaptively segments noisy data into multiple structures by estimating their scales and sorting by density, demonstrated on synthetic and real data.

Contribution

MISRE is a novel adaptive clustering algorithm that automatically estimates structure scales without manual tuning, improving robustness and efficiency.

Findings

Effective on synthetic and real datasets

Automatically estimates structure scales

Robust to noise and outliers

Abstract

We propose the segmentation of noisy datasets into Multiple Inlier Structures with a new Robust Estimator (MISRE). The scale of each individual structure is estimated adaptively from the input data and refined by mean shift, without tuning any parameter in the process, or manually specifying thresholds for different estimation problems. Once all the data points were classified into separate structures, these structures are sorted by their densities with the strongest inlier structures coming out first. Several 2D and 3D synthetic and real examples are presented to illustrate the efficiency, robustness and the limitations of the MISRE algorithm.