Clustering algorithms used in 3D scene segmentation

In this paper, we implement and compare three different clustering algorithms for the purpose of 3D image segmentation. Specifically, the K-means, Mean Shift, and Hierarchical methods are studied, and their performance is compared using cluster validity methods. Performance was analyzed in two ways, first by comparing independent results from each, and second, by comparing results where Hierarchical clustering is used as a cluster reduction method, following K-means and Mean Shift. Experiments show that each method is robust and can produce a clustering of the 3D data that, when compared to a ground truth using cluster validation, can consistently produce a Rand statistic greater than 0.7.