Segmentation and Pose Estimation of Planar Metallic Objects

Abstract

The problem of estimating the pose of metallic objects with shiny surfaces is studied. A new application has been developed using state-of-the-art 3D object segmentation (euclidean clustering) and pose estimation (ICP) methods. We analyze the planar surfaces of the metallic objects in 3D laser scanner data. First we segment these planar objects using euclidean clustering based on surface normals. Thereafter to estimate the pose of these segmented objects we compute Fast Point Feature Histograms (FPFH) descriptors. Finally we use an ICP algorithm that computes the rigid transformation with Singular Value Decomposition(SVD). Two different round of experiments are conducted:-one for the clustering and the other one for the pose estimation. We present the experimental results and analysis along with the possible application scenario and future work.

A model comparison method in digital inspection of railway track wear

“…For this data set, a Euclidean clustering method is introduced for extracting cluster data that represent planar surfaces. Within a search radius, the angle deviations between the surface normals of the clustered points are analyzed [11]. A Kd-Tree is created to store the points for searching and extracting, and the segmentation is implemented by the Point Cloud Library(PCL).…”