Vehicle Classification Via 3D Geometries

Abstract

We present a generalized mobile technique which allows for the classification of vehicles by tracking two vehicle based Points of Interest (PoI). Tracking the two PoI allows for the composition of those points into a 3D geometry, which is unique to a given vehicle type. Using high fidelity physics based simulation we demonstrate the capability to classify the 3D geometries in the presence of noise by extracting vector lengths and angles as features. Additionally, we investigate the classification advantages presented by representing the features in multiple linear transform domains and fusing the information from those different domains into a single ensemble classifier.

Publication Date

7-2-2016

Publication Title

Midwest Symposium on Circuits and Systems

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/MWSCAS.2016.7870119

Socpus ID

85015931414 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85015931414

This document is currently not available here.

Share

COinS