TimePillars: Temporally-Recurrent 3D LiDAR Object Detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Calvo, Ernesto Lozano, Taveira, Bernardo, Kahl, Fredrik, Gustafsson, Niklas, Larsson, Jonathan, Tonderski, Adam
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916076128829440
author Calvo, Ernesto Lozano
Taveira, Bernardo
Kahl, Fredrik
Gustafsson, Niklas
Larsson, Jonathan
Tonderski, Adam
author_facet Calvo, Ernesto Lozano
Taveira, Bernardo
Kahl, Fredrik
Gustafsson, Niklas
Larsson, Jonathan
Tonderski, Adam
contents Object detection applied to LiDAR point clouds is a relevant task in robotics, and particularly in autonomous driving. Single frame methods, predominant in the field, exploit information from individual sensor scans. Recent approaches achieve good performance, at relatively low inference time. Nevertheless, given the inherent high sparsity of LiDAR data, these methods struggle in long-range detection (e.g. 200m) which we deem to be critical in achieving safe automation. Aggregating multiple scans not only leads to a denser point cloud representation, but it also brings time-awareness to the system, and provides information about how the environment is changing. Solutions of this kind, however, are often highly problem-specific, demand careful data processing, and tend not to fulfil runtime requirements. In this context we propose TimePillars, a temporally-recurrent object detection pipeline which leverages the pillar representation of LiDAR data across time, respecting hardware integration efficiency constraints, and exploiting the diversity and long-range information of the novel Zenseact Open Dataset (ZOD). Through experimentation, we prove the benefits of having recurrency, and show how basic building blocks are enough to achieve robust and efficient results.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17260
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TimePillars: Temporally-Recurrent 3D LiDAR Object Detection
Calvo, Ernesto Lozano
Taveira, Bernardo
Kahl, Fredrik
Gustafsson, Niklas
Larsson, Jonathan
Tonderski, Adam
Computer Vision and Pattern Recognition
Machine Learning
Robotics
Object detection applied to LiDAR point clouds is a relevant task in robotics, and particularly in autonomous driving. Single frame methods, predominant in the field, exploit information from individual sensor scans. Recent approaches achieve good performance, at relatively low inference time. Nevertheless, given the inherent high sparsity of LiDAR data, these methods struggle in long-range detection (e.g. 200m) which we deem to be critical in achieving safe automation. Aggregating multiple scans not only leads to a denser point cloud representation, but it also brings time-awareness to the system, and provides information about how the environment is changing. Solutions of this kind, however, are often highly problem-specific, demand careful data processing, and tend not to fulfil runtime requirements. In this context we propose TimePillars, a temporally-recurrent object detection pipeline which leverages the pillar representation of LiDAR data across time, respecting hardware integration efficiency constraints, and exploiting the diversity and long-range information of the novel Zenseact Open Dataset (ZOD). Through experimentation, we prove the benefits of having recurrency, and show how basic building blocks are enough to achieve robust and efficient results.
title TimePillars: Temporally-Recurrent 3D LiDAR Object Detection
topic Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2312.17260