Segmentation is the process of partitioning a dataset into different blocks of data satisfying certain criteria. The segmentation process can be done in many different ways and with varied criteria; sometimes, it may involve extracting structured information from a point cloud based on a statistical property, and in other cases, it can simply require extracting points in a specific color range.

In many cases, our data might fit a specific mathematical model, such as a plane, line, or sphere, amongst others. When this is the case, it is possible to use a model estimation algorithm to calculate the parameters for the model that fits our data. With those parameters, it is then possible to extract the points belonging to that model and evaluate how well they fit it.

In this example, we are going to show how to perform model-based segmentation of a point cloud. We are going to constrain ourselves to a planar model, which is one of the most common mathematical models you can usually...