Vehicle Detection in Urban Environments Scanned by a Lidar

Detection of vehicles on 3D point clouds is performed by using the algorithm presented in this work. Point clouds correspond to urban environments and were acquired with the LIDAR Velodyne HDL-64E. The environment is considered semi-structured so that can be modeled using planes. Vehicle detection...

Full description

Saved in:
Bibliographic Details
Main Authors: Alfonso Ramírez Pedraza, José Joel González Barbosa, Francisco Javier Ornelas Rodríguez, Ángel Iván García Moreno, Adan Salazar Garibay, Erick Alejandro González Barbosa
Format: Article
Language:Spanish
Published: Universitat Politècnica de València 2015-04-01
Series:Revista Iberoamericana de Automática e Informática Industrial RIAI
Subjects:
Online Access:https://polipapers.upv.es/index.php/RIAI/article/view/9392
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846094857744941056
author Alfonso Ramírez Pedraza
José Joel González Barbosa
Francisco Javier Ornelas Rodríguez
Ángel Iván García Moreno
Adan Salazar Garibay
Erick Alejandro González Barbosa
author_facet Alfonso Ramírez Pedraza
José Joel González Barbosa
Francisco Javier Ornelas Rodríguez
Ángel Iván García Moreno
Adan Salazar Garibay
Erick Alejandro González Barbosa
author_sort Alfonso Ramírez Pedraza
collection DOAJ
description Detection of vehicles on 3D point clouds is performed by using the algorithm presented in this work. Point clouds correspond to urban environments and were acquired with the LIDAR Velodyne HDL-64E. The environment is considered semi-structured so that can be modeled using planes. Vehicle detection is carried out on to stages, segmentation and indexation. First stage is at the same time composed of three sub-stages. In the first one the principal plane (in this case the floor) is extracted, in the second sub-stage secondary planes are extracted using a tailored version of Hough's method, secondary planes are those perpendicular to the main plane. Finally in the third sub-stage and using MeanShift method, the remaining objects are segmented. Indexation on its side is divided into two sub-stages, in the first one, last segmented objects using MeanShift method are modeled using histograms according to the direction of the object's 3D points normal; in the second stage histograms are compared to those previously stored on a database of object's histograms. Optimizing of detection thresholds was carried out through ROC analysis. Two databases were used during the experiments, the first DB have 4500 objects and was used for ROC analysis training; the second one contained 3000 objects and was used for verification.
format Article
id doaj-art-71e4f03b369d40d1b006c2d33bb97298
institution Kabale University
issn 1697-7912
1697-7920
language Spanish
publishDate 2015-04-01
publisher Universitat Politècnica de València
record_format Article
series Revista Iberoamericana de Automática e Informática Industrial RIAI
spelling doaj-art-71e4f03b369d40d1b006c2d33bb972982025-01-02T12:11:53ZspaUniversitat Politècnica de ValènciaRevista Iberoamericana de Automática e Informática Industrial RIAI1697-79121697-79202015-04-0112218919810.1016/j.riai.2015.03.0036427Vehicle Detection in Urban Environments Scanned by a LidarAlfonso Ramírez Pedraza0José Joel González Barbosa1Francisco Javier Ornelas Rodríguez2Ángel Iván García Moreno3Adan Salazar Garibay4Erick Alejandro González Barbosa5Instituto Politécnico NacionalInstituto Politécnico NacionalInstituto Politécnico NacionalInstituto Politécnico NacionalQuantificare S.A.Instituto Tecnológico Superior de IrapuatoDetection of vehicles on 3D point clouds is performed by using the algorithm presented in this work. Point clouds correspond to urban environments and were acquired with the LIDAR Velodyne HDL-64E. The environment is considered semi-structured so that can be modeled using planes. Vehicle detection is carried out on to stages, segmentation and indexation. First stage is at the same time composed of three sub-stages. In the first one the principal plane (in this case the floor) is extracted, in the second sub-stage secondary planes are extracted using a tailored version of Hough's method, secondary planes are those perpendicular to the main plane. Finally in the third sub-stage and using MeanShift method, the remaining objects are segmented. Indexation on its side is divided into two sub-stages, in the first one, last segmented objects using MeanShift method are modeled using histograms according to the direction of the object's 3D points normal; in the second stage histograms are compared to those previously stored on a database of object's histograms. Optimizing of detection thresholds was carried out through ROC analysis. Two databases were used during the experiments, the first DB have 4500 objects and was used for ROC analysis training; the second one contained 3000 objects and was used for verification.https://polipapers.upv.es/index.php/RIAI/article/view/9392Nube de Puntos 3DLIDARSegmentación 3D
spellingShingle Alfonso Ramírez Pedraza
José Joel González Barbosa
Francisco Javier Ornelas Rodríguez
Ángel Iván García Moreno
Adan Salazar Garibay
Erick Alejandro González Barbosa
Vehicle Detection in Urban Environments Scanned by a Lidar
Revista Iberoamericana de Automática e Informática Industrial RIAI
Nube de Puntos 3D
LIDAR
Segmentación 3D
title Vehicle Detection in Urban Environments Scanned by a Lidar
title_full Vehicle Detection in Urban Environments Scanned by a Lidar
title_fullStr Vehicle Detection in Urban Environments Scanned by a Lidar
title_full_unstemmed Vehicle Detection in Urban Environments Scanned by a Lidar
title_short Vehicle Detection in Urban Environments Scanned by a Lidar
title_sort vehicle detection in urban environments scanned by a lidar
topic Nube de Puntos 3D
LIDAR
Segmentación 3D
url https://polipapers.upv.es/index.php/RIAI/article/view/9392
work_keys_str_mv AT alfonsoramirezpedraza vehicledetectioninurbanenvironmentsscannedbyalidar
AT josejoelgonzalezbarbosa vehicledetectioninurbanenvironmentsscannedbyalidar
AT franciscojavierornelasrodriguez vehicledetectioninurbanenvironmentsscannedbyalidar
AT angelivangarciamoreno vehicledetectioninurbanenvironmentsscannedbyalidar
AT adansalazargaribay vehicledetectioninurbanenvironmentsscannedbyalidar
AT erickalejandrogonzalezbarbosa vehicledetectioninurbanenvironmentsscannedbyalidar