Detección y Segmentación de Objetos 3D in Áreas Urbanas Utilizando Indexación (Detection and Segmentation of 3D Objects in Urban Environments Using Indexation)

Alfonso Ramírez Pedraza (ponchorp.1985@gmail.com)1, José Joel González Barbosa (jgonzalezba@ipn.mx)1, Juan B. Hurtado Ramos (jbautistah@ipn.mx)1, Ángel Iván García Moreno (angelivan.garciam@gmail.com)1, Francisco Javier Ornelas Rodriguez (fornelasr@ipn.mx)1, Erick Alejandro González Barbosa (ergonzalez@itesi.edu.mx)2


1CICATA-Qro. IPN
2ITESI-Irapuato

This paper appears in: Revista IEEE América Latina

Publication Date: April 2015
Volume: 13,   Issue: 4 
ISSN: 1548-0992


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.

Index Terms:
Indexation, LIDAR, 3D Segmentation.   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (770)]