Cargando…

L-DIG: A GAN-Based Method for LiDAR Point Cloud Processing under Snow Driving Conditions

LiDAR point clouds are significantly impacted by snow in driving scenarios, introducing scattered noise points and phantom objects, thereby compromising the perception capabilities of autonomous driving systems. Current effective methods for removing snow from point clouds largely rely on outlier fi...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Yuxiao, Ding, Ming, Yang, Hanting, Niu, Yingjie, Feng, Yan, Ohtani, Kento, Takeda, Kazuya
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10650494/
https://www.ncbi.nlm.nih.gov/pubmed/37960360
http://dx.doi.org/10.3390/s23218660
_version_ 1785135793136730112
author Zhang, Yuxiao
Ding, Ming
Yang, Hanting
Niu, Yingjie
Feng, Yan
Ohtani, Kento
Takeda, Kazuya
author_facet Zhang, Yuxiao
Ding, Ming
Yang, Hanting
Niu, Yingjie
Feng, Yan
Ohtani, Kento
Takeda, Kazuya
author_sort Zhang, Yuxiao
collection PubMed
description LiDAR point clouds are significantly impacted by snow in driving scenarios, introducing scattered noise points and phantom objects, thereby compromising the perception capabilities of autonomous driving systems. Current effective methods for removing snow from point clouds largely rely on outlier filters, which mechanically eliminate isolated points. This research proposes a novel translation model for LiDAR point clouds, the ‘L-DIG’ (LiDAR depth images GAN), built upon refined generative adversarial networks (GANs). This model not only has the capacity to reduce snow noise from point clouds, but it also can artificially synthesize snow points onto clear data. The model is trained using depth image representations of point clouds derived from unpaired datasets, complemented by customized loss functions for depth images to ensure scale and structure consistencies. To amplify the efficacy of snow capture, particularly in the region surrounding the ego vehicle, we have developed a pixel-attention discriminator that operates without downsampling convolutional layers. Concurrently, the other discriminator equipped with two-step downsampling convolutional layers has been engineered to effectively handle snow clusters. This dual-discriminator approach ensures robust and comprehensive performance in tackling diverse snow conditions. The proposed model displays a superior ability to capture snow and object features within LiDAR point clouds. A 3D clustering algorithm is employed to adaptively evaluate different levels of snow conditions, including scattered snowfall and snow swirls. Experimental findings demonstrate an evident de-snowing effect, and the ability to synthesize snow effects.
format Online
Article
Text
id pubmed-10650494
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106504942023-10-24 L-DIG: A GAN-Based Method for LiDAR Point Cloud Processing under Snow Driving Conditions Zhang, Yuxiao Ding, Ming Yang, Hanting Niu, Yingjie Feng, Yan Ohtani, Kento Takeda, Kazuya Sensors (Basel) Article LiDAR point clouds are significantly impacted by snow in driving scenarios, introducing scattered noise points and phantom objects, thereby compromising the perception capabilities of autonomous driving systems. Current effective methods for removing snow from point clouds largely rely on outlier filters, which mechanically eliminate isolated points. This research proposes a novel translation model for LiDAR point clouds, the ‘L-DIG’ (LiDAR depth images GAN), built upon refined generative adversarial networks (GANs). This model not only has the capacity to reduce snow noise from point clouds, but it also can artificially synthesize snow points onto clear data. The model is trained using depth image representations of point clouds derived from unpaired datasets, complemented by customized loss functions for depth images to ensure scale and structure consistencies. To amplify the efficacy of snow capture, particularly in the region surrounding the ego vehicle, we have developed a pixel-attention discriminator that operates without downsampling convolutional layers. Concurrently, the other discriminator equipped with two-step downsampling convolutional layers has been engineered to effectively handle snow clusters. This dual-discriminator approach ensures robust and comprehensive performance in tackling diverse snow conditions. The proposed model displays a superior ability to capture snow and object features within LiDAR point clouds. A 3D clustering algorithm is employed to adaptively evaluate different levels of snow conditions, including scattered snowfall and snow swirls. Experimental findings demonstrate an evident de-snowing effect, and the ability to synthesize snow effects. MDPI 2023-10-24 /pmc/articles/PMC10650494/ /pubmed/37960360 http://dx.doi.org/10.3390/s23218660 Text en © 2023 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
Zhang, Yuxiao
Ding, Ming
Yang, Hanting
Niu, Yingjie
Feng, Yan
Ohtani, Kento
Takeda, Kazuya
L-DIG: A GAN-Based Method for LiDAR Point Cloud Processing under Snow Driving Conditions
title L-DIG: A GAN-Based Method for LiDAR Point Cloud Processing under Snow Driving Conditions
title_full L-DIG: A GAN-Based Method for LiDAR Point Cloud Processing under Snow Driving Conditions
title_fullStr L-DIG: A GAN-Based Method for LiDAR Point Cloud Processing under Snow Driving Conditions
title_full_unstemmed L-DIG: A GAN-Based Method for LiDAR Point Cloud Processing under Snow Driving Conditions
title_short L-DIG: A GAN-Based Method for LiDAR Point Cloud Processing under Snow Driving Conditions
title_sort l-dig: a gan-based method for lidar point cloud processing under snow driving conditions
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10650494/
https://www.ncbi.nlm.nih.gov/pubmed/37960360
http://dx.doi.org/10.3390/s23218660
work_keys_str_mv AT zhangyuxiao ldigaganbasedmethodforlidarpointcloudprocessingundersnowdrivingconditions
AT dingming ldigaganbasedmethodforlidarpointcloudprocessingundersnowdrivingconditions
AT yanghanting ldigaganbasedmethodforlidarpointcloudprocessingundersnowdrivingconditions
AT niuyingjie ldigaganbasedmethodforlidarpointcloudprocessingundersnowdrivingconditions
AT fengyan ldigaganbasedmethodforlidarpointcloudprocessingundersnowdrivingconditions
AT ohtanikento ldigaganbasedmethodforlidarpointcloudprocessingundersnowdrivingconditions
AT takedakazuya ldigaganbasedmethodforlidarpointcloudprocessingundersnowdrivingconditions