Detection and Segmentation of 3D Objects in Urban Environments Using Indexation

Author

Pedraza, A.R. ; Barbosa, J.J.G. ; Ramos, J.B.H. ; Moreno, A.I.G. ; Rodriguez, F.J.O. ; Barbosa, E.A.G.

Volume

13

Issue

4

fYear

2015

fDate

Apr-15

Firstpage

1120

Lastpage

1128

Abstract

A procedure for automobile detection on 3D point clouds of urban areas is presented in this work. Point clouds are obtained using an HDL-64E Velodyne LIDAR. The work is divided into two sections: Segmentation, in which the base plane (floor) and its perpendicular planes are extracted using Hough´s technique. Next every other object is segmented using MeanShift method; and Indexation, in which all segmented objects are modeled according to a normal direction so that its histograms can be obtained and compared to a pre-loaded histogram database. The reconstructed environment is considered to be semi-structured, meaning that it can be modeled using planes. In the process ROC analysis is used for thresholds optimization.

Keywords

Hough transforms; image reconstruction; image segmentation; object detection; 3D point clouds; HDL-64E Velodyne LIDAR; Hough technique; Indexation; MeanShift method; ROC analysis; automobile detection; object segmentation; pre-loaded histogram database; thresholds optimization; urban areas; Computational modeling; Image segmentation; Kernel; Laser radar; Media; Robustness; Three-dimensional displays; 3D Segmentation; Indexation; LIDAR;

fLanguage

English

Journal_Title

Latin America Transactions, IEEE (Revista IEEE America Latina)

Publisher

ieee

ISSN

1548-0992

Type

jour

DOI

10.1109/TLA.2015.7106365

Filename

7106365