File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: An Unequal Learning Approach for 3D Point Cloud Segmentation

TitleAn Unequal Learning Approach for 3D Point Cloud Segmentation
Authors
Keywordsobject segmentation
point inequivalence
point cloud
gene expression programming
Issue Date2020
PublisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=9424
Citation
IEEE Transactions on Industrial Informatics, 2020, Epub 2020-12-11 How to Cite?
AbstractObject segmentation for three-dimensional point clouds plays a critical role in autonomous driving, robotic navigation, and other computer version applications. In object segmentation, all points are considered to be equal of importance in the literature. However, unequal cases exist and a segmentation boundary is mainly determined by neighbor points. To investigate point inequivalence, an unequal learning approach is proposed to integrate gene expression programming (GEP) and a deep neural network (DNN). GEP is designed to discover the inequivalent function, which measures the importance of different points according to the distances to the segmentation boundary. A cost sensitive learning method is improved to guide the DNN to obtain the loss of different points unequally with the discovered inequivalent function during model training. The experimental results reveal that point inequivalence with respect to boundary distance exists and is helpful to improve the accuracy of object segmentation.
Persistent Identifierhttp://hdl.handle.net/10722/295263
ISSN
2023 Impact Factor: 11.7
2023 SCImago Journal Rankings: 4.420
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWang, J-
dc.contributor.authorXu, C-
dc.contributor.authorDai, L-
dc.contributor.authorZhang, J-
dc.contributor.authorZhong, RY-
dc.date.accessioned2021-01-11T13:57:38Z-
dc.date.available2021-01-11T13:57:38Z-
dc.date.issued2020-
dc.identifier.citationIEEE Transactions on Industrial Informatics, 2020, Epub 2020-12-11-
dc.identifier.issn1551-3203-
dc.identifier.urihttp://hdl.handle.net/10722/295263-
dc.description.abstractObject segmentation for three-dimensional point clouds plays a critical role in autonomous driving, robotic navigation, and other computer version applications. In object segmentation, all points are considered to be equal of importance in the literature. However, unequal cases exist and a segmentation boundary is mainly determined by neighbor points. To investigate point inequivalence, an unequal learning approach is proposed to integrate gene expression programming (GEP) and a deep neural network (DNN). GEP is designed to discover the inequivalent function, which measures the importance of different points according to the distances to the segmentation boundary. A cost sensitive learning method is improved to guide the DNN to obtain the loss of different points unequally with the discovered inequivalent function during model training. The experimental results reveal that point inequivalence with respect to boundary distance exists and is helpful to improve the accuracy of object segmentation.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=9424-
dc.relation.ispartofIEEE Transactions on Industrial Informatics-
dc.rightsIEEE Transactions on Industrial Informatics. Copyright © Institute of Electrical and Electronics Engineers.-
dc.rights©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectobject segmentation-
dc.subjectpoint inequivalence-
dc.subjectpoint cloud-
dc.subjectgene expression programming-
dc.titleAn Unequal Learning Approach for 3D Point Cloud Segmentation-
dc.typeArticle-
dc.identifier.emailZhong, RY: zhongzry@hku.hk-
dc.identifier.authorityZhong, RY=rp02116-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TII.2020.3044106-
dc.identifier.scopuseid_2-s2.0-85097925974-
dc.identifier.hkuros320764-
dc.identifier.volumeEpub 2020-12-11-
dc.identifier.isiWOS:000690940600006-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats