Combining semantic and geometric features for object class segmentation of indoor scenes

Scene understanding is a necessary prerequisite for robots acting autonomously in complex environments. Low-cost RGB-D cameras such as Microsoft Kinect enabled new methods for analyzing indoor scenes and are now ubiquitously used in indoor robotics. We investigate strategies for efficient pixelwise...

ver descrição completa

Detalhes bibliográficos
Autores: Husain, Farzad, Schulz, Hannes, Dellen, Babette, Torras, Carme, Behnke, Sven
Formato: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2016
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/132983
Acesso em linha:http://hdl.handle.net/10261/132983
Access Level:acceso abierto
Palavra-chave:Semantic scene understanding
Categorization
Segmentation
id ES_c59d8c6964dfabc52193294167033708
oai_identifier_str oai:digital.csic.es:10261/132983
network_acronym_str ES
network_name_str España
repository_id_str
spelling Combining semantic and geometric features for object class segmentation of indoor scenesHusain, FarzadSchulz, HannesDellen, BabetteTorras, CarmeBehnke, SvenSemantic scene understandingCategorizationSegmentationScene understanding is a necessary prerequisite for robots acting autonomously in complex environments. Low-cost RGB-D cameras such as Microsoft Kinect enabled new methods for analyzing indoor scenes and are now ubiquitously used in indoor robotics. We investigate strategies for efficient pixelwise object class labeling of indoor scenes that combine both pretrained semantic features transferred from a large color image dataset and geometric features, computed relative to the room structures, including a novel distance-from-wall feature, which encodes the proximity of scene points to a detected major wall of the room. We evaluate our approach on the popular NYU v2 dataset. Several deep learning models are tested, which are designed to exploit different characteristics of the data. This includes feature learning with two different pooling sizes. Our results indicate that combining semantic and geometric features yields significantly improved results for the task of object class segmentation.This research is partially funded by the CSIC project MANIPlus (201350E102), and the project RobInstruct (TIN2014-58178-R).Peer reviewedInstitute of Electrical and Electronics EngineersConsejo Superior de Investigaciones Científicas (España)Ministerio de Economía y Competitividad (España)Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]201620162016info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Postprintinfo:eu-repo/semantics/acceptedVersionhttp://hdl.handle.net/10261/132983reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Inglés#PLACEHOLDER_PARENT_METADATA_VALUE#info:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2014-58178-Rhttp://dx.doi.org/10.1109/LRA.2016.2532927Síinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/1329832026-05-22T06:33:51Z
dc.title.none.fl_str_mv Combining semantic and geometric features for object class segmentation of indoor scenes
title Combining semantic and geometric features for object class segmentation of indoor scenes
spellingShingle Combining semantic and geometric features for object class segmentation of indoor scenes
Husain, Farzad
Semantic scene understanding
Categorization
Segmentation
title_short Combining semantic and geometric features for object class segmentation of indoor scenes
title_full Combining semantic and geometric features for object class segmentation of indoor scenes
title_fullStr Combining semantic and geometric features for object class segmentation of indoor scenes
title_full_unstemmed Combining semantic and geometric features for object class segmentation of indoor scenes
title_sort Combining semantic and geometric features for object class segmentation of indoor scenes
dc.creator.none.fl_str_mv Husain, Farzad
Schulz, Hannes
Dellen, Babette
Torras, Carme
Behnke, Sven
author Husain, Farzad
author_facet Husain, Farzad
Schulz, Hannes
Dellen, Babette
Torras, Carme
Behnke, Sven
author_role author
author2 Schulz, Hannes
Dellen, Babette
Torras, Carme
Behnke, Sven
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Consejo Superior de Investigaciones Científicas (España)
Ministerio de Economía y Competitividad (España)
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Semantic scene understanding
Categorization
Segmentation
topic Semantic scene understanding
Categorization
Segmentation
description Scene understanding is a necessary prerequisite for robots acting autonomously in complex environments. Low-cost RGB-D cameras such as Microsoft Kinect enabled new methods for analyzing indoor scenes and are now ubiquitously used in indoor robotics. We investigate strategies for efficient pixelwise object class labeling of indoor scenes that combine both pretrained semantic features transferred from a large color image dataset and geometric features, computed relative to the room structures, including a novel distance-from-wall feature, which encodes the proximity of scene points to a detected major wall of the room. We evaluate our approach on the popular NYU v2 dataset. Several deep learning models are tested, which are designed to exploit different characteristics of the data. This includes feature learning with two different pooling sizes. Our results indicate that combining semantic and geometric features yields significantly improved results for the task of object class segmentation.
publishDate 2016
dc.date.none.fl_str_mv 2016
2016
2016
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Postprint
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/132983
url http://hdl.handle.net/10261/132983
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv #PLACEHOLDER_PARENT_METADATA_VALUE#
info:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2014-58178-R
http://dx.doi.org/10.1109/LRA.2016.2532927
Sí
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869419003565309952
score 15.812455

Registos relacionados