Abstract
Abstract. Introducing an organization to the unstructured point cloud before extracting information from airborne lidar data is common in many applications. Aggregating the points with similar features into segments in 3-D which comply with the nature of actual objects is affected by the neighborhood, scale, features and noise among other aspects. In this study, we present a min-cut based method for segmenting the point cloud. We first assess the neighborhood of each point in 3-D by investigating the local geometric and statistical properties of the candidates. Neighborhood selection is essential since point features are calculated within their local neighborhood. Following neighborhood determination, we calculate point features and determine the clusters in the feature space. We adapt a graph representation from image processing which is especially used in pixel labeling problems and establish it for the unstructured 3-D point clouds. The edges of the graph that are connecting the points with each other and nodes representing feature clusters hold the smoothness costs in the spatial domain and data costs in the feature domain. Smoothness costs ensure spatial coherence, while data costs control the consistency with the representative feature clusters. This graph representation formalizes the segmentation task as an energy minimization problem. It allows the implementation of an approximate solution by min-cuts for a global minimum of this NP hard minimization problem in low order polynomial time. We test our method with airborne lidar point cloud acquired with maximum planned post spacing of 1.4 m and a vertical accuracy 10.5 cm as RMSE. We present the effects of neighborhood and feature determination in the segmentation results and assess the accuracy and efficiency of the implemented min-cut algorithm as well as its sensitivity to the parameters of the smoothness and data cost functions. We find that smoothness cost that only considers simple distance parameter does not strongly conform to the natural structure of the points. Including shape information within the energy function by assigning costs based on the local properties may help to achieve a better representation for segmentation.
Highlights
We focus our efforts for the segmentation of point clouds following the track of algorithms which deal with 3-D point coordinates instead of 2.5-D range images
Numerous algorithms have been developed over the years for the segmentation of lidar point clouds; employing both range images and unstructured point clouds
Once we construct the graph with all data and smoothness costs, we use the software library implementation provided by Veksler and Delong based on the algorithms in Boykov et al (2001), Kolmogorov and Zabih (2004), and Boykov and Kolmogorov (2004) to perform the graph cut optimization
Summary
Lidar (light detection and ranging) is considered as one of the most important data acquisition technologies introduced for geospatial data acquisition lately (Petrie and Toth, 2009) and is progressively utilized for remote sensing of the Earth. This rapidly advancing technology quickly attracted interest for a variety of applications due to the dense point coverage (Filin and Pfeifer 2005). We perform a segmentation of the point cloud with a min-cut algorithm using this feature vector and model the surface and scattered points. We form a second feature vector and carry out a segmentation of the points labeled as surface
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have