Authors:
Yacine Yaddaden
1
;
2
;
Sylvie Daniel
3
;
2
and
Denis Laurendeau
1
;
2
Affiliations:
1
Département de Génie Électrique et de Génie Informatique, Université de Laval, ville de Québec, Québec, Canada
;
2
Laboratoire de Vision et Systèmes Numériques (LVSN), Université de Laval, ville de Québec, Québec, Canada
;
3
Département des Sciences Géomatiques, Université de Laval, ville de Québec, Québec, Canada
Keyword(s):
Online Machine Learning, Point Cloud Data, Unique Shape Context, Signature of Histograms of Orientation, Principal Component Analysis, Multi-class Support Vector Machine.
Abstract:
In the context of vehicle localization based on point cloud data collected using LiDAR sensors, several 3D descriptors might be employed to highlight the relevant information about the vehicle’s environment. However, it is still a challenging task to assess which one is the more suitable with respect to the constraint of real-time processing. In this paper, we propose a system based on classical machine learning techniques and performing recognition from point cloud data after applying several preprocessing steps. We compare the performance of two distinct state-of-the-art local 3D descriptors namely Unique Shape Context and Signature of Histograms of Orientation when combined with online learning algorithms. The proposed system also includes two distinct modes namely normal and cluster to deal with the point cloud data size and for which performances are evaluated. In order to measure the performance of the proposed system, we used a benchmark RGB-D object dataset from which we rand
omly selected three stratified subsets. The obtained results are promising and suggesting further experimentation involving real data collected from LiDAR sensors on vehicles.
(More)