Clustering and line detection in laser range measurements

This article presents two algorithms that extract information from laser range data. They are designed to work sequentially. The first method (dcc) separates the data into clusters by means of a convolution operation, using a high-pass filter. The second one (reholt) performs line detection in each of the clusters previously discovered. The reliability of the algorithms devised is tested on the experimental data collected both indoors and outdoors. When compared with other methods found in the literature, the ones proposed here prove to achieve higher performance.