Detection and segmentation of 3D objects in urban environments using indexation

Alfonso Ramirez Pedraza; Jose Joel Gonzalez Barbosa; Juan B. Hurtado Ramos; Angel Ivan Garcia Moreno; Francisco Javier Ornelas Rodriguez; Erick Alejandro Gonzalez Barbosa

doi:10.1109/TLA.2015.7106365

Detection and segmentation of 3D objects in urban environments using indexation

Alfonso Ramirez Pedraza, Jose Joel Gonzalez Barbosa, Juan B. Hurtado Ramos, Angel Ivan Garcia Moreno, Francisco Javier Ornelas Rodriguez, Erick Alejandro Gonzalez Barbosa

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

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.

Original language	English
Article number	7106365
Pages (from-to)	1120-1128
Number of pages	9
Journal	IEEE Latin America Transactions
Volume	13
Issue number	4
DOIs	https://doi.org/10.1109/TLA.2015.7106365
State	Published - 1 Apr 2015
Externally published	Yes

Keywords

3D Segmentation
Indexation
LIDAR

Access to Document

10.1109/TLA.2015.7106365

Cite this

@article{52d3c849d7e842c78b1b67e8f3e5c8cc,

title = "Detection and segmentation of 3D objects in urban environments using indexation",

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 = "3D Segmentation, Indexation, LIDAR",

author = "{Ramirez Pedraza}, Alfonso and {Gonzalez Barbosa}, {Jose Joel} and {Hurtado Ramos}, {Juan B.} and {Garcia Moreno}, {Angel Ivan} and {Ornelas Rodriguez}, {Francisco Javier} and {Gonzalez Barbosa}, {Erick Alejandro}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.",

year = "2015",

month = apr,

day = "1",

doi = "10.1109/TLA.2015.7106365",

language = "Ingl{\'e}s",

volume = "13",

pages = "1120--1128",

journal = "IEEE Latin America Transactions",

issn = "1548-0992",

number = "4",

}

TY - JOUR

T1 - Detection and segmentation of 3D objects in urban environments using indexation

AU - Ramirez Pedraza, Alfonso

AU - Gonzalez Barbosa, Jose Joel

AU - Hurtado Ramos, Juan B.

AU - Garcia Moreno, Angel Ivan

AU - Ornelas Rodriguez, Francisco Javier

AU - Gonzalez Barbosa, Erick Alejandro

PY - 2015/4/1

Y1 - 2015/4/1

N2 - 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.

AB - 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.

KW - 3D Segmentation

KW - Indexation

KW - LIDAR

UR - http://www.scopus.com/inward/record.url?scp=84929352827&partnerID=8YFLogxK

U2 - 10.1109/TLA.2015.7106365

DO - 10.1109/TLA.2015.7106365

M3 - Artículo

SN - 1548-0992

VL - 13

SP - 1120

EP - 1128

JO - IEEE Latin America Transactions

JF - IEEE Latin America Transactions

IS - 4

M1 - 7106365

ER -

Detection and segmentation of 3D objects in urban environments using indexation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this