Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/168297
COMPARTIR / EXPORTAR:
SHARE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Título: | Low resolution lidar-based multi object tracking for driving applications |
Autor: | Pino, Iván del; Vaquero, Victor CSIC ORCID; Masini, Beatrice; Solà, Joan CSIC ; Moreno-Noguer, Francesc CSIC ORCID ; Sanfeliu, Alberto CSIC ORCID ; Andrade-Cetto, Juan CSIC ORCID | Palabras clave: | HDL-64 DATMO Multi-object tracking Vehicle detection Point cloud Deconvolutional networks VLP-16 MHEKF |
Fecha de publicación: | 2017 | Editor: | Springer Nature | Citación: | ROBOT 2017: Third Iberian Robotics Conference: 287-298 (2017) | Serie: | Advances in Intelligent Systems and Computing 693 | Resumen: | Vehicle detection and tracking in real scenarios are key com- ponents to develop assisted and autonomous driving systems. Lidar sen- sors are specially suitable for this task, as they bring robustness to harsh weather conditions while providing accurate spatial information. How- ever, the resolution provided by point cloud data is very scarce in com- parison to camera images. In this work we explore the possibilities of Deep Learning (DL) methodologies applied to low resolution 3D lidar sensors such as the Velodyne VLP-16 (PUCK), in the context of vehicle detection and tracking. For this purpose we developed a lidar-based sys- tem that uses a Convolutional Neural Network (CNN), to perform point- wise vehicle detection using PUCK data, and Multi-Hypothesis Extended Kalman Filters (MH-EKF), to estimate the actual position and veloci- ties of the detected vehicles. Comparative studies between the proposed lower resolution (VLP-16) tracking system and a high-end system, using Velodyne HDL-64, were carried out on the Kitti Tracking Benchmark dataset. Moreover, to analyze the influence of the CNN-based vehicle detection approach, comparisons were also performed with respect to the geometric-only detector. The results demonstrate that the proposed low resolution Deep Learning architecture is able to successfully accom- plish the vehicle detection task, outperforming the geometric baseline approach. Moreover, it has been observed that our system achieves a similar tracking performance to the high-end HDL-64 sensor at close range. On the other hand, at long range, detection is limited to half the distance of the higher-end sensor. | Descripción: | Trabajo presentado a la Third Iberian Robotics Conference, celebrada en Sevilla del 22 al 24 de noviembre de 2017. | Versión del editor: | https://doi.org/10.1007/978-3-319-70833-1_24 | URI: | http://hdl.handle.net/10261/168297 | DOI: | 10.1007/978-3-319-70833-1_24 | Identificadores: | doi: 10.1007/978-3-319-70833-1_24 isbn: 978-3-319-70832-4 |
Aparece en las colecciones: | (IRII) Libros y partes de libros |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
lowappli.pdf | 4,05 MB | Unknown | Visualizar/Abrir |
CORE Recommender
Page view(s)
454
checked on 01-may-2024
Download(s)
540
checked on 01-may-2024
Google ScholarTM
Check
Altmetric
Altmetric
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.