Object Class Recognition using Global Shape Descriptors in 3D

Abstract

We formulate Global Shape Descriptors for object classifi cation in range data. The goal of object class recognition is to identify and localize objects of interest in a 3D point cloud.This work focuses on the automatic classifi cation of objects that lie within the vicinity of streets in 3D point clouds of urban environments. The system first successfully segments objects of interest from the scene through a combination of ground segmentation and road extraction using a Kalman filtering approach, and cluster extraction using a region growing technique. Those clusters that fall close to the road are then passed to a classification phase, where they are compared against a labelled database of such clusters. The comparison of clusters is based upon Variable-Dimensional Global Shape Descriptors, which encode the geometry of the objects into multi-dimensional histograms, the similarities of which are measured against the database clusters using a variety of metrics including Earth Movers Distance and Bhattacharya similarity. The technique was tested on a dense data set acquired from central New York City, containing 110 objects partitioned into 5 classes. The method had an average successful recognition rate of 94.5% for a rich set of vehicles, pedestrians, and street furniture such as re hydrants, street signs, and poles.