Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Martinez, Julieta, Doubov, Sasha, Fan, Jack, Bârsan, Ioan Andrei, Wang, Shenlong, Máttyus, Gellért, Urtasun, Raquel
Formato: Preprint
Publicado: 2020
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913337049088000
author Martinez, Julieta
Doubov, Sasha
Fan, Jack
Bârsan, Ioan Andrei
Wang, Shenlong
Máttyus, Gellért
Urtasun, Raquel
author_facet Martinez, Julieta
Doubov, Sasha
Fan, Jack
Bârsan, Ioan Andrei
Wang, Shenlong
Máttyus, Gellért
Urtasun, Raquel
contents We are interested in understanding whether retrieval-based localization approaches are good enough in the context of self-driving vehicles. Towards this goal, we introduce Pit30M, a new image and LiDAR dataset with over 30 million frames, which is 10 to 100 times larger than those used in previous work. Pit30M is captured under diverse conditions (i.e., season, weather, time of the day, traffic), and provides accurate localization ground truth. We also automatically annotate our dataset with historical weather and astronomical data, as well as with image and LiDAR semantic segmentation as a proxy measure for occlusion. We benchmark multiple existing methods for image and LiDAR retrieval and, in the process, introduce a simple, yet effective convolutional network-based LiDAR retrieval method that is competitive with the state of the art. Our work provides, for the first time, a benchmark for sub-metre retrieval-based localization at city scale. The dataset, its Python SDK, as well as more information about the sensors, calibration, and metadata, are available on the project website: https://pit30m.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2012_12437
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars
Martinez, Julieta
Doubov, Sasha
Fan, Jack
Bârsan, Ioan Andrei
Wang, Shenlong
Máttyus, Gellért
Urtasun, Raquel
Computer Vision and Pattern Recognition
Robotics
We are interested in understanding whether retrieval-based localization approaches are good enough in the context of self-driving vehicles. Towards this goal, we introduce Pit30M, a new image and LiDAR dataset with over 30 million frames, which is 10 to 100 times larger than those used in previous work. Pit30M is captured under diverse conditions (i.e., season, weather, time of the day, traffic), and provides accurate localization ground truth. We also automatically annotate our dataset with historical weather and astronomical data, as well as with image and LiDAR semantic segmentation as a proxy measure for occlusion. We benchmark multiple existing methods for image and LiDAR retrieval and, in the process, introduce a simple, yet effective convolutional network-based LiDAR retrieval method that is competitive with the state of the art. Our work provides, for the first time, a benchmark for sub-metre retrieval-based localization at city scale. The dataset, its Python SDK, as well as more information about the sensors, calibration, and metadata, are available on the project website: https://pit30m.github.io/
title Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2012.12437