???ENUM_LANGUAGE_JA???
 
???mainMenu_lnkPrivacyPolicy??? ???mainMenu_lnkPolicy???

???ViewItemPage???

???ViewItemFull_lblItemActions??????List_lblExportOptions???
 
 
???export_btDownload??????export_btEMail???
 ???ViewItemFull_lblSubHeaderLocalTags??????ViewItemFull_btnItemVersions??????ViewItemFull_btnItemView??????ViewItemOverview_lblLinkOverviewPage???
  Unsupervised Estimation of Monocular Depth and VO in Dynamic Environments via Hybrid Masks

Sun, Q., Tang, Y., Zhang, C., Zhao, C., Qian, F., Kurths, J. (2022): Unsupervised Estimation of Monocular Depth and VO in Dynamic Environments via Hybrid Masks. - IEEE Transactions on Neural Networks and Learning Systems, 33, 5, 2023-2033.
https://doi.org/10.1109/TNNLS.2021.3100895

Item is

 

???ViewItemFull_lblShowGroup??? ???ViewItemFull_lblAll??? ???ViewItemFull_lblHideGroup??? ???ViewItemFull_lblAll???

???ViewItemFull_lblBasic???

???ViewItemFull_lblShowGroup??? ???ViewItemFull_lblHideGroup???
???ViewItemFull_lblCiteItemAs???: https://publications.pik-potsdam.de/pubman/item/item_26573 ???ViewItemFull_lblCiteItemVersionAs???: https://publications.pik-potsdam.de/pubman/item/item_26573_2
???ViewItemFull_lblGenre???: ???ENUM_GENRE_ARTICLE???

???ViewItemFull_lblSubHeaderLocators???

???ViewItemFull_lblShowGroup???

???ViewItemFull_lblCreators???

???ViewItemFull_lblShowGroup???
???ViewItemFull_lblHideGroup???
 ???ViewItemFull_lblCreators???:
Sun, Qiyu1, ???ENUM_CREATORROLE_AUTHOR???
Tang, Yang1, ???ENUM_CREATORROLE_AUTHOR???
Zhang, Chongzhen 1, ???ENUM_CREATORROLE_AUTHOR???
Zhao, Chaoqiang 1, ???ENUM_CREATORROLE_AUTHOR???
Qian, Feng1, ???ENUM_CREATORROLE_AUTHOR???
Kurths, Jürgen2, ???ENUM_CREATORROLE_AUTHOR???           
???ViewItemFull_lblAffiliations???:
1External Organizations, ou_persistent22              
2Potsdam Institute for Climate Impact Research, ou_persistent13              

???EditItem_lblContent???

???ViewItemFull_lblShowGroup???
???ViewItemFull_lblHideGroup???
???ViewItemFull_lblSubject???: ???lbl_noEntry???
 ???ViewItemFull_lblAbstract???: Deep learning-based methods have achieved remarkable performance in 3-D sensing since they perceive environments in a biologically inspired manner. Nevertheless, the existing approaches trained by monocular sequences are still prone to fail in dynamic environments. In this work, we mitigate the negative influence of dynamic environments on the joint estimation of depth and visual odometry (VO) through hybrid masks. Since both the VO estimation and view reconstruction process in the joint estimation framework is vulnerable to dynamic environments, we propose the cover mask and the filter mask to alleviate the adverse effects, respectively. As the depth and VO estimation are tightly coupled during training, the improved VO estimation promotes depth estimation as well. Besides, a depth-pose consistency loss is proposed to overcome the scale inconsistency between different training samples of monocular sequences. Experimental results show that both our depth prediction and globally consistent VO estimation are state of the art when evaluated on the KITTI benchmark. We evaluate our depth prediction model on the Make3D dataset to prove the transferability of our method as well.

???ViewItemFull_lblSubHeaderDetails???

???ViewItemFull_lblShowGroup???
???ViewItemFull_lblHideGroup???
???ViewItemFull_lblLanguages???: eng - English
 ???ViewItemFull_lblDates???: 2021-08-042022-05
 ???ViewItemFull_lblPublicationStatus???: ???ViewItem_lblPublicationState_published-in-print???
 ???ViewItemFull_lblPages???: 11
 ???ViewItemFull_lblPublishingInfo???: ???lbl_noEntry???
 ???ViewItemFull_lblTOC???: ???lbl_noEntry???
 ???ViewItemFull_lblRevisionMethod???: ???ENUM_REVIEWMETHOD_PEER???
 ???ViewItemFull_lblIdentifiers???: ???ENUM_IDENTIFIERTYPE_DOI???: 10.1109/TNNLS.2021.3100895
???ENUM_IDENTIFIERTYPE_MDB_ID???: No data to archive
???ENUM_IDENTIFIERTYPE_PIKDOMAIN???: RD4 - Complexity Science
???ENUM_IDENTIFIERTYPE_ORGANISATIONALK???: RD4 - Complexity Science
???ENUM_IDENTIFIERTYPE_RESEARCHTK???: Complex Networks
???ENUM_IDENTIFIERTYPE_RESEARCHTK???: Health
???ENUM_IDENTIFIERTYPE_RESEARCHTK???: Nonlinear Dynamics
???ENUM_IDENTIFIERTYPE_MODELMETHOD???: Machine Learning
 ???ViewItemFull_lblDegreeType???: ???lbl_noEntry???

???ViewItemFull_lblSubHeaderEvent???

???ViewItemFull_lblShowGroup???

???ViewItemFull_lblSubHeaderLegalCase???

???ViewItemFull_lblShowGroup???

???g_project_info???

???ViewItemFull_lblShowGroup???

???ViewItemFull_lblSubHeaderSource??? 1

???ViewItemFull_lblShowGroup???
???ViewItemFull_lblHideGroup???
???ViewItemFull_lblSourceTitle???: IEEE Transactions on Neural Networks and Learning Systems
???ViewItemFull_lblSourceGenre???: ???ENUM_GENRE_JOURNAL???, SCI, Scopus
 ???ViewItemFull_lblSourceCreators???:
???ViewItemFull_lblSourceAffiliations???:
???ViewItemFull_lblSourcePubInfo???: ???lbl_noEntry???
???ViewItemFull_lblPages???: ???lbl_noEntry??? ???ViewItemFull_lblSourceVolumeIssue???: 33 (5) ???ViewItemFull_lblSourceSequenceNo???: ???lbl_noEntry??? ???ViewItemFull_lblSourceStartEndPage???: 2023 - 2033 ???ViewItemFull_lblSourceIdentifier???: ???ENUM_IDENTIFIERTYPE_OTHER???: 2162-237X
???ENUM_IDENTIFIERTYPE_ISSN???: 2162-237X
???ENUM_IDENTIFIERTYPE_CONE???: https://publications.pik-potsdam.de/cone/journals/resource/IEEE-transactions-on-neural-networks-and-learning-systems
???ENUM_IDENTIFIERTYPE_PUBLISHER???: Institute of Electrical and Electronics Engineers (IEEE)