Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/1822/78006 |
Resumo: | Autonomous vehicles are becoming central for the future of mobility, supported by advances in deep learning techniques. The performance of aself-driving system is highly dependent on the quality of the perception task. Developments in sensor technologies have led to an increased availability of 3D scanners such as LiDAR, allowing for a more accurate representation of the vehicle's surroundings, leading to safer systems. The rapid development and consequent rise of research studies around self-driving systems since early 2010, resulted in a tremendous increase in the number and novelty of object detection methods. After the first wave of works that essentially tried to expand known techniques from object detection in images, more recently there has been a notable development in newer and more adapted to LiDAR data works. This paper addresses the existing literature on object detection using LiDAR data within the scope of self-driving and brings a systematic way for analysing it. Unlike general object detection surveys, we will focus on point-cloud data, which presents specific challenges, notably its high-dimensional and sparse nature. This work introduces a common object detection pipeline and taxonomy to facilitate a thorough comparison between different techniques and, departing from it, this work will critically examine the representation of data (critical for complexity reduction), feature extraction and finally the object detection models. A comparison between performance results of the different models is included, alongside with some future research challenges. |
id |
RCAP_0950b4c8f3dba5081a45b9abc82e9766 |
---|---|
oai_identifier_str |
oai:repositorium.sdum.uminho.pt:1822/78006 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomyAutonomous vehiclesComputer visionDeep learningPerceptionLiDAR3D object detection modelsScience & TechnologyAutonomous vehicles are becoming central for the future of mobility, supported by advances in deep learning techniques. The performance of aself-driving system is highly dependent on the quality of the perception task. Developments in sensor technologies have led to an increased availability of 3D scanners such as LiDAR, allowing for a more accurate representation of the vehicle's surroundings, leading to safer systems. The rapid development and consequent rise of research studies around self-driving systems since early 2010, resulted in a tremendous increase in the number and novelty of object detection methods. After the first wave of works that essentially tried to expand known techniques from object detection in images, more recently there has been a notable development in newer and more adapted to LiDAR data works. This paper addresses the existing literature on object detection using LiDAR data within the scope of self-driving and brings a systematic way for analysing it. Unlike general object detection surveys, we will focus on point-cloud data, which presents specific challenges, notably its high-dimensional and sparse nature. This work introduces a common object detection pipeline and taxonomy to facilitate a thorough comparison between different techniques and, departing from it, this work will critically examine the representation of data (critical for complexity reduction), feature extraction and finally the object detection models. A comparison between performance results of the different models is included, alongside with some future research challenges.This work is supported by European Structural and Investment Funds in the FEDER component, through the Operational Competitiveness and Internationalization Programme (COMPETE 2020) [Project n. 037902; Funding Reference: POCI-01-0247-FEDER-037902].ElsevierUniversidade do MinhoFernandes, DuarteSilva, AntonioNevoa, RafaelSimoes, ClaudiaGonzalez, DibetGuevara, MiguelNovais, PauloMonteiro, João L.Melo-Pinto, Pedro2021-042021-04-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/1822/78006engFernandes, D., Silva, A., Névoa, R., Simões, C., Gonzalez, D., Guevara, M., . . . Melo-Pinto, P. (2021). Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy. Information Fusion, 68, 161-191. doi: https://doi.org/10.1016/j.inffus.2020.11.0021566-253510.1016/j.inffus.2020.11.002https://www.sciencedirect.com/science/article/pii/S1566253520304097info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-21T11:58:04Zoai:repositorium.sdum.uminho.pt:1822/78006Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T18:47:45.619455Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy |
title |
Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy |
spellingShingle |
Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy Fernandes, Duarte Autonomous vehicles Computer vision Deep learning Perception LiDAR 3D object detection models Science & Technology |
title_short |
Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy |
title_full |
Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy |
title_fullStr |
Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy |
title_full_unstemmed |
Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy |
title_sort |
Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy |
author |
Fernandes, Duarte |
author_facet |
Fernandes, Duarte Silva, Antonio Nevoa, Rafael Simoes, Claudia Gonzalez, Dibet Guevara, Miguel Novais, Paulo Monteiro, João L. Melo-Pinto, Pedro |
author_role |
author |
author2 |
Silva, Antonio Nevoa, Rafael Simoes, Claudia Gonzalez, Dibet Guevara, Miguel Novais, Paulo Monteiro, João L. Melo-Pinto, Pedro |
author2_role |
author author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade do Minho |
dc.contributor.author.fl_str_mv |
Fernandes, Duarte Silva, Antonio Nevoa, Rafael Simoes, Claudia Gonzalez, Dibet Guevara, Miguel Novais, Paulo Monteiro, João L. Melo-Pinto, Pedro |
dc.subject.por.fl_str_mv |
Autonomous vehicles Computer vision Deep learning Perception LiDAR 3D object detection models Science & Technology |
topic |
Autonomous vehicles Computer vision Deep learning Perception LiDAR 3D object detection models Science & Technology |
description |
Autonomous vehicles are becoming central for the future of mobility, supported by advances in deep learning techniques. The performance of aself-driving system is highly dependent on the quality of the perception task. Developments in sensor technologies have led to an increased availability of 3D scanners such as LiDAR, allowing for a more accurate representation of the vehicle's surroundings, leading to safer systems. The rapid development and consequent rise of research studies around self-driving systems since early 2010, resulted in a tremendous increase in the number and novelty of object detection methods. After the first wave of works that essentially tried to expand known techniques from object detection in images, more recently there has been a notable development in newer and more adapted to LiDAR data works. This paper addresses the existing literature on object detection using LiDAR data within the scope of self-driving and brings a systematic way for analysing it. Unlike general object detection surveys, we will focus on point-cloud data, which presents specific challenges, notably its high-dimensional and sparse nature. This work introduces a common object detection pipeline and taxonomy to facilitate a thorough comparison between different techniques and, departing from it, this work will critically examine the representation of data (critical for complexity reduction), feature extraction and finally the object detection models. A comparison between performance results of the different models is included, alongside with some future research challenges. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-04 2021-04-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://hdl.handle.net/1822/78006 |
url |
https://hdl.handle.net/1822/78006 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Fernandes, D., Silva, A., Névoa, R., Simões, C., Gonzalez, D., Guevara, M., . . . Melo-Pinto, P. (2021). Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomy. Information Fusion, 68, 161-191. doi: https://doi.org/10.1016/j.inffus.2020.11.002 1566-2535 10.1016/j.inffus.2020.11.002 https://www.sciencedirect.com/science/article/pii/S1566253520304097 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799132237476659200 |