Cargando…
Real-Time Detection of Non-Stationary Objects Using Intensity Data in Automotive LiDAR SLAM
This article aims at demonstrating the feasibility of modern deep learning techniques for the real-time detection of non-stationary objects in point clouds obtained from 3-D light detecting and ranging (LiDAR) sensors. The motion segmentation task is considered in the application context of automoti...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8538971/ https://www.ncbi.nlm.nih.gov/pubmed/34695994 http://dx.doi.org/10.3390/s21206781 |
_version_ | 1784588633872793600 |
---|---|
author | Nowak, Tomasz Ćwian, Krzysztof Skrzypczyński, Piotr |
author_facet | Nowak, Tomasz Ćwian, Krzysztof Skrzypczyński, Piotr |
author_sort | Nowak, Tomasz |
collection | PubMed |
description | This article aims at demonstrating the feasibility of modern deep learning techniques for the real-time detection of non-stationary objects in point clouds obtained from 3-D light detecting and ranging (LiDAR) sensors. The motion segmentation task is considered in the application context of automotive Simultaneous Localization and Mapping (SLAM), where we often need to distinguish between the static parts of the environment with respect to which we localize the vehicle, and non-stationary objects that should not be included in the map for localization. Non-stationary objects do not provide repeatable readouts, because they can be in motion, like vehicles and pedestrians, or because they do not have a rigid, stable surface, like trees and lawns. The proposed approach exploits images synthesized from the received intensity data yielded by the modern LiDARs along with the usual range measurements. We demonstrate that non-stationary objects can be detected using neural network models trained with 2-D grayscale images in the supervised or unsupervised training process. This concept makes it possible to alleviate the lack of large datasets of 3-D laser scans with point-wise annotations for non-stationary objects. The point clouds are filtered using the corresponding intensity images with labeled pixels. Finally, we demonstrate that the detection of non-stationary objects using our approach improves the localization results and map consistency in a laser-based SLAM system. |
format | Online Article Text |
id | pubmed-8538971 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-85389712021-10-24 Real-Time Detection of Non-Stationary Objects Using Intensity Data in Automotive LiDAR SLAM Nowak, Tomasz Ćwian, Krzysztof Skrzypczyński, Piotr Sensors (Basel) Article This article aims at demonstrating the feasibility of modern deep learning techniques for the real-time detection of non-stationary objects in point clouds obtained from 3-D light detecting and ranging (LiDAR) sensors. The motion segmentation task is considered in the application context of automotive Simultaneous Localization and Mapping (SLAM), where we often need to distinguish between the static parts of the environment with respect to which we localize the vehicle, and non-stationary objects that should not be included in the map for localization. Non-stationary objects do not provide repeatable readouts, because they can be in motion, like vehicles and pedestrians, or because they do not have a rigid, stable surface, like trees and lawns. The proposed approach exploits images synthesized from the received intensity data yielded by the modern LiDARs along with the usual range measurements. We demonstrate that non-stationary objects can be detected using neural network models trained with 2-D grayscale images in the supervised or unsupervised training process. This concept makes it possible to alleviate the lack of large datasets of 3-D laser scans with point-wise annotations for non-stationary objects. The point clouds are filtered using the corresponding intensity images with labeled pixels. Finally, we demonstrate that the detection of non-stationary objects using our approach improves the localization results and map consistency in a laser-based SLAM system. MDPI 2021-10-13 /pmc/articles/PMC8538971/ /pubmed/34695994 http://dx.doi.org/10.3390/s21206781 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Nowak, Tomasz Ćwian, Krzysztof Skrzypczyński, Piotr Real-Time Detection of Non-Stationary Objects Using Intensity Data in Automotive LiDAR SLAM |
title | Real-Time Detection of Non-Stationary Objects Using Intensity Data in Automotive LiDAR SLAM |
title_full | Real-Time Detection of Non-Stationary Objects Using Intensity Data in Automotive LiDAR SLAM |
title_fullStr | Real-Time Detection of Non-Stationary Objects Using Intensity Data in Automotive LiDAR SLAM |
title_full_unstemmed | Real-Time Detection of Non-Stationary Objects Using Intensity Data in Automotive LiDAR SLAM |
title_short | Real-Time Detection of Non-Stationary Objects Using Intensity Data in Automotive LiDAR SLAM |
title_sort | real-time detection of non-stationary objects using intensity data in automotive lidar slam |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8538971/ https://www.ncbi.nlm.nih.gov/pubmed/34695994 http://dx.doi.org/10.3390/s21206781 |
work_keys_str_mv | AT nowaktomasz realtimedetectionofnonstationaryobjectsusingintensitydatainautomotivelidarslam AT cwiankrzysztof realtimedetectionofnonstationaryobjectsusingintensitydatainautomotivelidarslam AT skrzypczynskipiotr realtimedetectionofnonstationaryobjectsusingintensitydatainautomotivelidarslam |