Machine learning point cloud enhancement for self-driving systems

Autores
Salomón, Nicolás; Delrieux, Claudio Augusto; Morero, Damián Alfonso; Borgnino, Leandro
Año de publicación
2025
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Autonomous driving, decades ago relegated to the realm of science fiction, emerged as a tangible reality that is rapidly transforming the automotive industry, redefining our relationship with vehicles, and placing them in the spotlight of both the industry and the general public. Through the study and analysis of modern and efficient interpolation techniques, we aim to reduce the current costs and processing requirements associated with the LiDAR sensor, which is one of the main information sources. Our approach explores the fusion of lower-cost LiDAR sensors with advanced interpolation techniques, with a particular focus on achieving performance parity with pricier 64-channel LiDAR setups.This work is based on 3 main axes: firstly, the analysis of available LiDAR data and its representation; secondly, the development and implementation of an interpolation technique based on 1D convolutional layers integrated with fully connected layers, in order to analyse data coming from a sliding window; and finally, the comparative evaluation of the results between different state-of-the-art interpolation techniques, using object detection networks in point clouds. Furthermore, a basic analysis regarding power consumption and a potential hardware implementation is presented.By interpolating the point clouds with the proposed technique, improvements between 1.92% and 30.98% in detection and classification tasks were achieved, depending on the object and the type of detection (3D or bird´s eye view). Furthermore, computational efficiency was not left aside by reducing the inference times necessary for interpolation, compared to other techniques used as contrast. This highlights the viability and scalability of our approach in realizing cost-effective yet high-performance autonomous driving systems.
Fil: Salomón, Nicolás. Fundación Fulgor; Argentina
Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina
Fil: Morero, Damián Alfonso. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas Físicas y Naturales. Departamento de Electrónica. Laboratorio de Comunicaciones Digitales; Argentina
Fil: Borgnino, Leandro. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas Físicas y Naturales. Departamento de Electrónica. Laboratorio de Comunicaciones Digitales; Argentina
Materia
LiDAR,
Artificial Intelligence
, point clouds,
range images
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/289412
Acceder
id CONICETDig_97b27289074bef6ee0da4375353c963e
oai_identifier_str oai:ri.conicet.gov.ar:11336/289412
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Machine learning point cloud enhancement for self-driving systemsSalomón, NicolásDelrieux, Claudio AugustoMorero, Damián AlfonsoBorgnino, LeandroLiDAR,Artificial Intelligence, point clouds,range imageshttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Autonomous driving, decades ago relegated to the realm of science fiction, emerged as a tangible reality that is rapidly transforming the automotive industry, redefining our relationship with vehicles, and placing them in the spotlight of both the industry and the general public. Through the study and analysis of modern and efficient interpolation techniques, we aim to reduce the current costs and processing requirements associated with the LiDAR sensor, which is one of the main information sources. Our approach explores the fusion of lower-cost LiDAR sensors with advanced interpolation techniques, with a particular focus on achieving performance parity with pricier 64-channel LiDAR setups.This work is based on 3 main axes: firstly, the analysis of available LiDAR data and its representation; secondly, the development and implementation of an interpolation technique based on 1D convolutional layers integrated with fully connected layers, in order to analyse data coming from a sliding window; and finally, the comparative evaluation of the results between different state-of-the-art interpolation techniques, using object detection networks in point clouds. Furthermore, a basic analysis regarding power consumption and a potential hardware implementation is presented.By interpolating the point clouds with the proposed technique, improvements between 1.92% and 30.98% in detection and classification tasks were achieved, depending on the object and the type of detection (3D or bird´s eye view). Furthermore, computational efficiency was not left aside by reducing the inference times necessary for interpolation, compared to other techniques used as contrast. This highlights the viability and scalability of our approach in realizing cost-effective yet high-performance autonomous driving systems.Fil: Salomón, Nicolás. Fundación Fulgor; ArgentinaFil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; ArgentinaFil: Morero, Damián Alfonso. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas Físicas y Naturales. Departamento de Electrónica. Laboratorio de Comunicaciones Digitales; ArgentinaFil: Borgnino, Leandro. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas Físicas y Naturales. Departamento de Electrónica. Laboratorio de Comunicaciones Digitales; ArgentinaCentro Latinoamericano de Estudios en Informática2025-05-16info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/289412Salomón, Nicolás; Delrieux, Claudio Augusto; Morero, Damián Alfonso; Borgnino, Leandro; Machine learning point cloud enhancement for self-driving systems; Centro Latinoamericano de Estudios en Informática; CLEI Electronic Journal; 28; 3; 16-5-2025; 1-180717-5000CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://clei.org/cleiej/index.php/cleiej/article/view/811info:eu-repo/semantics/altIdentifier/doi/10.19153/cleiej.28.3.3info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-08-25T15:26:44Zoai:ri.conicet.gov.ar:11336/289412instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982026-08-25 15:26:45.244CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Machine learning point cloud enhancement for self-driving systems
title Machine learning point cloud enhancement for self-driving systems
spellingShingle Machine learning point cloud enhancement for self-driving systems
Salomón, Nicolás
LiDAR,
Artificial Intelligence
, point clouds,
range images
title_short Machine learning point cloud enhancement for self-driving systems
title_full Machine learning point cloud enhancement for self-driving systems
title_fullStr Machine learning point cloud enhancement for self-driving systems
title_full_unstemmed Machine learning point cloud enhancement for self-driving systems
title_sort Machine learning point cloud enhancement for self-driving systems
dc.creator.none.fl_str_mv Salomón, Nicolás
Delrieux, Claudio Augusto
Morero, Damián Alfonso
Borgnino, Leandro
author Salomón, Nicolás
author_facet Salomón, Nicolás
Delrieux, Claudio Augusto
Morero, Damián Alfonso
Borgnino, Leandro
author_role author
author2 Delrieux, Claudio Augusto
Morero, Damián Alfonso
Borgnino, Leandro
author2_role author
author
author
dc.subject.none.fl_str_mv LiDAR,
Artificial Intelligence
, point clouds,
range images
topic LiDAR,
Artificial Intelligence
, point clouds,
range images
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Autonomous driving, decades ago relegated to the realm of science fiction, emerged as a tangible reality that is rapidly transforming the automotive industry, redefining our relationship with vehicles, and placing them in the spotlight of both the industry and the general public. Through the study and analysis of modern and efficient interpolation techniques, we aim to reduce the current costs and processing requirements associated with the LiDAR sensor, which is one of the main information sources. Our approach explores the fusion of lower-cost LiDAR sensors with advanced interpolation techniques, with a particular focus on achieving performance parity with pricier 64-channel LiDAR setups.This work is based on 3 main axes: firstly, the analysis of available LiDAR data and its representation; secondly, the development and implementation of an interpolation technique based on 1D convolutional layers integrated with fully connected layers, in order to analyse data coming from a sliding window; and finally, the comparative evaluation of the results between different state-of-the-art interpolation techniques, using object detection networks in point clouds. Furthermore, a basic analysis regarding power consumption and a potential hardware implementation is presented.By interpolating the point clouds with the proposed technique, improvements between 1.92% and 30.98% in detection and classification tasks were achieved, depending on the object and the type of detection (3D or bird´s eye view). Furthermore, computational efficiency was not left aside by reducing the inference times necessary for interpolation, compared to other techniques used as contrast. This highlights the viability and scalability of our approach in realizing cost-effective yet high-performance autonomous driving systems.
Fil: Salomón, Nicolás. Fundación Fulgor; Argentina
Fil: Delrieux, Claudio Augusto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería Eléctrica y de Computadoras; Argentina
Fil: Morero, Damián Alfonso. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas Físicas y Naturales. Departamento de Electrónica. Laboratorio de Comunicaciones Digitales; Argentina
Fil: Borgnino, Leandro. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas Físicas y Naturales. Departamento de Electrónica. Laboratorio de Comunicaciones Digitales; Argentina
description Autonomous driving, decades ago relegated to the realm of science fiction, emerged as a tangible reality that is rapidly transforming the automotive industry, redefining our relationship with vehicles, and placing them in the spotlight of both the industry and the general public. Through the study and analysis of modern and efficient interpolation techniques, we aim to reduce the current costs and processing requirements associated with the LiDAR sensor, which is one of the main information sources. Our approach explores the fusion of lower-cost LiDAR sensors with advanced interpolation techniques, with a particular focus on achieving performance parity with pricier 64-channel LiDAR setups.This work is based on 3 main axes: firstly, the analysis of available LiDAR data and its representation; secondly, the development and implementation of an interpolation technique based on 1D convolutional layers integrated with fully connected layers, in order to analyse data coming from a sliding window; and finally, the comparative evaluation of the results between different state-of-the-art interpolation techniques, using object detection networks in point clouds. Furthermore, a basic analysis regarding power consumption and a potential hardware implementation is presented.By interpolating the point clouds with the proposed technique, improvements between 1.92% and 30.98% in detection and classification tasks were achieved, depending on the object and the type of detection (3D or bird´s eye view). Furthermore, computational efficiency was not left aside by reducing the inference times necessary for interpolation, compared to other techniques used as contrast. This highlights the viability and scalability of our approach in realizing cost-effective yet high-performance autonomous driving systems.
publishDate 2025
dc.date.none.fl_str_mv 2025-05-16
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/289412
Salomón, Nicolás; Delrieux, Claudio Augusto; Morero, Damián Alfonso; Borgnino, Leandro; Machine learning point cloud enhancement for self-driving systems; Centro Latinoamericano de Estudios en Informática; CLEI Electronic Journal; 28; 3; 16-5-2025; 1-18
0717-5000
CONICET Digital
CONICET
url http://hdl.handle.net/11336/289412
identifier_str_mv Salomón, Nicolás; Delrieux, Claudio Augusto; Morero, Damián Alfonso; Borgnino, Leandro; Machine learning point cloud enhancement for self-driving systems; Centro Latinoamericano de Estudios en Informática; CLEI Electronic Journal; 28; 3; 16-5-2025; 1-18
0717-5000
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://clei.org/cleiej/index.php/cleiej/article/view/811
info:eu-repo/semantics/altIdentifier/doi/10.19153/cleiej.28.3.3
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Centro Latinoamericano de Estudios en Informática
publisher.none.fl_str_mv Centro Latinoamericano de Estudios en Informática
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1874775324829417472
score 13.265058

Publicaciones similares