PASS: Panoramic Annular Semantic Segmentation

Pixel-wise semantic segmentation is capable of unifying most of driving scene perception tasks, and has enabled striking progress in the context of navigation assistance, where an entire surrounding sensing is vital. However, current mainstream semantic segmenters are predominantly benchmarked again...

Descripción completa

Detalles Bibliográficos
Autores: Yang, Kailun, Hu, Xinxin, Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077, Romera Carmena, Eduardo|||0000-0001-6250-6160, Kaiwei, Wang
Tipo de recurso: artículo
Fecha de publicación:2019
País:España
Institución:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/42859
Acceso en línea:http://hdl.handle.net/10017/42859
https://dx.doi.org/10.1109/TITS.2019.2938965
Access Level:acceso abierto
Palabra clave:Semantics
Cameras
Image segmentation
Sensors
Navigation
Task analysis
Benchmark testing
Intelligent vehicles
Scene parsing
Semantic segmentation
Scene understanding
Panoramic annular images
Electrónica
Electronics
id ES_9b3122fcdd1c8fa0237d0bfecd16ca69
oai_identifier_str oai:ebuah.uah.es:10017/42859
network_acronym_str ES
network_name_str España
repository_id_str
spelling PASS: Panoramic Annular Semantic SegmentationYang, KailunHu, XinxinBergasa Pascual, Luis Miguel|||0000-0002-0087-3077Romera Carmena, Eduardo|||0000-0001-6250-6160Kaiwei, WangSemanticsCamerasImage segmentationSensorsNavigationTask analysisBenchmark testingIntelligent vehiclesScene parsingSemantic segmentationScene understandingPanoramic annular imagesElectrónicaElectronicsPixel-wise semantic segmentation is capable of unifying most of driving scene perception tasks, and has enabled striking progress in the context of navigation assistance, where an entire surrounding sensing is vital. However, current mainstream semantic segmenters are predominantly benchmarked against datasets featuring narrow Field of View (FoV), and a large part of vision-based intelligent vehicles use only a forward-facing camera. In this paper, we propose a Panoramic Annular Semantic Segmentation (PASS) framework to perceive the whole surrounding based on a compact panoramic annular lens system and an online panorama unfolding process. To facilitate the training of PASS models, we leverage conventional FoV imaging datasets, bypassing the efforts entailed to create fully dense panoramic annotations. To consistently exploit the rich contextual cues in the unfolded panorama, we adapt our real-time ERF-PSPNet to predict semantically meaningful feature maps in different segments, and fuse them to fulfill panoramic scene parsing. The innovation lies in the network adaptation to enable smooth and seamless segmentation, combined with an extended set of heterogeneous data augmentations to attain robustness in panoramic imagery. A comprehensive variety of experiments demonstrates the effectiveness for real-world surrounding perception in a single PASS, while the adaptation proposal is exceptionally positive for state-of-the-art efficient networks.Ministerio de Economía y CompetitividadComunidad de MadridIEEE20192019-09-1220192019-09-1220202020-09-12journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10017/42859https://dx.doi.org/10.1109/TITS.2019.2938965reponame:e_Buah Biblioteca Digital Universidad de Alcaláinstname:Universidad de Alcalá (UAH)InglésengMinisterio de Economía y Competitividad http://dx.doi.org/10.13039/501100003329 Not available TRA2015-70501-C2-1-R VEHICULO INTELIGENTE PARA PERSONAS MAYORESComunidad de Madrid http://dx.doi.org/10.13039/100012818 Not available P2018%2FNMT-4331 Madrid Robotics Digital Innovation Hubopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:ebuah.uah.es:10017/428592026-06-18T11:13:07Z
dc.title.none.fl_str_mv PASS: Panoramic Annular Semantic Segmentation
title PASS: Panoramic Annular Semantic Segmentation
spellingShingle PASS: Panoramic Annular Semantic Segmentation
Yang, Kailun
Semantics
Cameras
Image segmentation
Sensors
Navigation
Task analysis
Benchmark testing
Intelligent vehicles
Scene parsing
Semantic segmentation
Scene understanding
Panoramic annular images
Electrónica
Electronics
title_short PASS: Panoramic Annular Semantic Segmentation
title_full PASS: Panoramic Annular Semantic Segmentation
title_fullStr PASS: Panoramic Annular Semantic Segmentation
title_full_unstemmed PASS: Panoramic Annular Semantic Segmentation
title_sort PASS: Panoramic Annular Semantic Segmentation
dc.creator.none.fl_str_mv Yang, Kailun
Hu, Xinxin
Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077
Romera Carmena, Eduardo|||0000-0001-6250-6160
Kaiwei, Wang
author Yang, Kailun
author_facet Yang, Kailun
Hu, Xinxin
Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077
Romera Carmena, Eduardo|||0000-0001-6250-6160
Kaiwei, Wang
author_role author
author2 Hu, Xinxin
Bergasa Pascual, Luis Miguel|||0000-0002-0087-3077
Romera Carmena, Eduardo|||0000-0001-6250-6160
Kaiwei, Wang
author2_role author
author
author
author
dc.subject.none.fl_str_mv Semantics
Cameras
Image segmentation
Sensors
Navigation
Task analysis
Benchmark testing
Intelligent vehicles
Scene parsing
Semantic segmentation
Scene understanding
Panoramic annular images
Electrónica
Electronics
topic Semantics
Cameras
Image segmentation
Sensors
Navigation
Task analysis
Benchmark testing
Intelligent vehicles
Scene parsing
Semantic segmentation
Scene understanding
Panoramic annular images
Electrónica
Electronics
description Pixel-wise semantic segmentation is capable of unifying most of driving scene perception tasks, and has enabled striking progress in the context of navigation assistance, where an entire surrounding sensing is vital. However, current mainstream semantic segmenters are predominantly benchmarked against datasets featuring narrow Field of View (FoV), and a large part of vision-based intelligent vehicles use only a forward-facing camera. In this paper, we propose a Panoramic Annular Semantic Segmentation (PASS) framework to perceive the whole surrounding based on a compact panoramic annular lens system and an online panorama unfolding process. To facilitate the training of PASS models, we leverage conventional FoV imaging datasets, bypassing the efforts entailed to create fully dense panoramic annotations. To consistently exploit the rich contextual cues in the unfolded panorama, we adapt our real-time ERF-PSPNet to predict semantically meaningful feature maps in different segments, and fuse them to fulfill panoramic scene parsing. The innovation lies in the network adaptation to enable smooth and seamless segmentation, combined with an extended set of heterogeneous data augmentations to attain robustness in panoramic imagery. A comprehensive variety of experiments demonstrates the effectiveness for real-world surrounding perception in a single PASS, while the adaptation proposal is exceptionally positive for state-of-the-art efficient networks.
publishDate 2019
dc.date.none.fl_str_mv 2019
2019-09-12
2019
2019-09-12
2020
2020-09-12
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10017/42859
https://dx.doi.org/10.1109/TITS.2019.2938965
url http://hdl.handle.net/10017/42859
https://dx.doi.org/10.1109/TITS.2019.2938965
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Ministerio de Economía y Competitividad http://dx.doi.org/10.13039/501100003329 Not available TRA2015-70501-C2-1-R VEHICULO INTELIGENTE PARA PERSONAS MAYORES
Comunidad de Madrid http://dx.doi.org/10.13039/100012818 Not available P2018%2FNMT-4331 Madrid Robotics Digital Innovation Hub
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:e_Buah Biblioteca Digital Universidad de Alcalá
instname:Universidad de Alcalá (UAH)
instname_str Universidad de Alcalá (UAH)
reponame_str e_Buah Biblioteca Digital Universidad de Alcalá
collection e_Buah Biblioteca Digital Universidad de Alcalá
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869414483839942656
score 15,300719

Similares en LA Referencia