基于边缘强化的无监督单目深度估计
TP391; 为解决无监督单目深度估计边缘深度估计不准确的问题,提出了一种基于边缘强化的无监督单目深度估计网络模型.该模型由单视图深度网络和姿态网络两部分构成,均采用编解码结构,其中单视图深度网络编码器使用高分辨率网络(high-resolution net,HRNet)作为骨干网络,在整个过程中保持高分辨率表示,有利于提取精确空间特征;单视图深度网络解码器引入条状卷积,细化深度边缘附近的深度变化,同时利用经典的高斯拉普拉斯算子增强边缘细节,最终充分利用深度边缘信息提高深度估计质量.在KITTI数据集中进行的实验结果表明:所提模型具有较好的深度估计性能,能够使深度图中的 目标边缘更加清晰,细节...
Saved in:
| Published in | 系统工程与电子技术 Vol. 46; no. 1; pp. 71 - 79 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | Chinese |
| Published |
江南大学轻工过程先进控制教育部重点实验室,江苏无锡 214122
2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1001-506X |
| DOI | 10.12305/j.issn.1001-506X.2024.01.08 |
Cover
| Abstract | TP391; 为解决无监督单目深度估计边缘深度估计不准确的问题,提出了一种基于边缘强化的无监督单目深度估计网络模型.该模型由单视图深度网络和姿态网络两部分构成,均采用编解码结构,其中单视图深度网络编码器使用高分辨率网络(high-resolution net,HRNet)作为骨干网络,在整个过程中保持高分辨率表示,有利于提取精确空间特征;单视图深度网络解码器引入条状卷积,细化深度边缘附近的深度变化,同时利用经典的高斯拉普拉斯算子增强边缘细节,最终充分利用深度边缘信息提高深度估计质量.在KITTI数据集中进行的实验结果表明:所提模型具有较好的深度估计性能,能够使深度图中的 目标边缘更加清晰,细节更加丰富. |
|---|---|
| AbstractList | TP391; 为解决无监督单目深度估计边缘深度估计不准确的问题,提出了一种基于边缘强化的无监督单目深度估计网络模型.该模型由单视图深度网络和姿态网络两部分构成,均采用编解码结构,其中单视图深度网络编码器使用高分辨率网络(high-resolution net,HRNet)作为骨干网络,在整个过程中保持高分辨率表示,有利于提取精确空间特征;单视图深度网络解码器引入条状卷积,细化深度边缘附近的深度变化,同时利用经典的高斯拉普拉斯算子增强边缘细节,最终充分利用深度边缘信息提高深度估计质量.在KITTI数据集中进行的实验结果表明:所提模型具有较好的深度估计性能,能够使深度图中的 目标边缘更加清晰,细节更加丰富. |
| Abstract_FL | To solve the problem of poor edge depth estimation accuracy in unsupervised monocular depth estimation,an unsupervised monocular depth estimation model based on edge enhancement is proposed.The model is composed of a single-view depth network and a camera pose estimation network,both of which adopt encoder-decoder structures.The single-view depth network encoder uses high-resolution net(HRNet)as the backbone which maintains high resolution representations throughout the whole process,and is conducive to extract accurate spatial features;The single-view depth network decoder introduces strip convolutions to refine the depth variations near the edges,while enhancing the edge details using the classical Laplace of Gaussian operator.The method fully utilizes the depth edge information to improve the quality of the depth estimation.The experimental results on the KITTI dataset show that the proposed model has good depth estimation performance,making the edges of the depth map clearer with more details. |
| Author | 曲熠 陈莹 |
| AuthorAffiliation | 江南大学轻工过程先进控制教育部重点实验室,江苏无锡 214122 |
| AuthorAffiliation_xml | – name: 江南大学轻工过程先进控制教育部重点实验室,江苏无锡 214122 |
| Author_FL | QU Yi CHEN Ying |
| Author_FL_xml | – sequence: 1 fullname: QU Yi – sequence: 2 fullname: CHEN Ying |
| Author_xml | – sequence: 1 fullname: 曲熠 – sequence: 2 fullname: 陈莹 |
| BookMark | eNo9j7tKA0EUhqeIYIx5Cythx3NmMrtnSgneIGCjYBd29hKyyAQcxUttqYKFUQyiIlgGrcQl-DTZbB7DiGL1wV98P98Cq9ieTRhbQuAoJKiVjHedsxwB0FPg73EBosEBOVCFVf_neVZ3rmtAoQwUBI0qg-IxH-dX06_PcnRXjPLiol_en09un8rBdfnwUlzelIPh5OO9yF_Ho7fp8HmRzaXhvkvqf6yx3fW1neam19re2GqutjyHoMgjjBPwUUsthUBpjPEl-ipKEOJQpyR0YkQoowgoNRTHFPgglKKAFJLWRtbY8q_3OLRpaDvtrHd0YGeP7ZPDTnQan2XupxFmbSS_AfHlXG8 |
| ClassificationCodes | TP391 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.12305/j.issn.1001-506X.2024.01.08 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| DocumentTitle_FL | Unsupervised monocular depth estimation based on edge enhancement |
| EndPage | 79 |
| ExternalDocumentID | xtgcydzjs202401008 |
| GrantInformation_xml | – fundername: 国家自然科学基金 funderid: (62173160) |
| GroupedDBID | -0Y 2B. 4A8 5XA 5XJ 92E 92I 93N ABJNI ACGFS ALMA_UNASSIGNED_HOLDINGS CCEZO CUBFJ CW9 PSX TCJ TGP U1G U5S |
| ID | FETCH-LOGICAL-s1058-81de06193932213bbb63165ce10da9f829eb2a3cc08fb8dd876025587851899b3 |
| ISSN | 1001-506X |
| IngestDate | Thu May 29 04:00:31 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 1 |
| Keywords | 单目深度估计 strip convolutions 无监督学习 edge enhancement 边缘增强 条状卷积 monocular depth estimation unsupervised learning |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1058-81de06193932213bbb63165ce10da9f829eb2a3cc08fb8dd876025587851899b3 |
| PageCount | 9 |
| ParticipantIDs | wanfang_journals_xtgcydzjs202401008 |
| PublicationCentury | 2000 |
| PublicationDate | 2024 |
| PublicationDateYYYYMMDD | 2024-01-01 |
| PublicationDate_xml | – year: 2024 text: 2024 |
| PublicationDecade | 2020 |
| PublicationTitle | 系统工程与电子技术 |
| PublicationTitle_FL | Systems Engineering and Electronics |
| PublicationYear | 2024 |
| Publisher | 江南大学轻工过程先进控制教育部重点实验室,江苏无锡 214122 |
| Publisher_xml | – name: 江南大学轻工过程先进控制教育部重点实验室,江苏无锡 214122 |
| SSID | ssib051375074 ssib002263377 ssib001102898 ssib057620160 ssib023168126 ssib023646287 ssj0042237 |
| Score | 2.3929818 |
| Snippet | TP391; 为解决无监督单目深度估计边缘深度估计不准确的问题,提出了一种基于边缘强化的无监督单目深度估计网络模型.该模型由单视图深度网络和姿态网络两部分构成,均采用编解码结构,其中单视图深度网络编码器使用高分辨率网络(high-resolution... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 71 |
| Title | 基于边缘强化的无监督单目深度估计 |
| URI | https://d.wanfangdata.com.cn/periodical/xtgcydzjs202401008 |
| Volume | 46 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LaxRBEG7iBkQP4hPfBLRPMnG6e3qm-9izO0sQ48UEcgvzTPCwgtmA7tljFDz4wCAqgsegJ3EJ_ppsNj_Dqt7OzkBEoiw0TXVN1VddO9NVTT8IuQ1DCPxR8srTyi-8QJSBl1aF7-lcFVJX8Mtxv_Pig3BhObi3IldmTmw1Vi1t9rP5fPDHfSX_41WggV9xl-w_eHYqFAhQB_9CCR6G8lg-pomkuktjQ5MAS5XQRNE4obGmSUTjNtUKeaCCPJIqoITYpIE5oElIdUSNbykx1cxWOtQIy9yhWromkyBzDDKZFWioCa1SkOyjUmAwrBnpWgCCxrGtxIgTHwR1VqZRVMVWgrKwQQvUJfIY0OujOmVwHQaCbFMzXYFsCTGNOT6kQoBft2iqNVUKASnsheacBq9nM60tzEFCMyOrN6AmcgDQOujJjsU_hQ2ULlVRAz88Lp1CaAJYCDtxcoAehxauRFwIilvcgFGgBKxECAAt4dZrEntSJ9hkDPprQgFsvN2AbbWrbsODGjvQsDucBYw35nLx9CtP-vYix-lg5OZjmy_dZGSZXFTjYpTJ_TtHRj9IJ6Ud_lD-_FT-PHaxPZxW1aP-dC3m0_5a_qwYPNpALp_ZnfOzPIqYbJFZ01m8_7AOrzEabaTnELoLUe9j5ngJGqvDebybIOR1-C-ZgPi0Tjcg1eV4wOFh5BRAqGovQzoEfhK-Jc6su38xyu6361Vpb60RGi6dJWdcTjdnJi_oOTIzWD9PTjdO-rxA_NHH4d7w5cGvn-Pdd6Pd4Wjrzfj98_23n8bbr8YfvoxevB5v7-z_-D4aft3b_Xaw8_kiWe4mS-0Fz11W4m1AiqI8yPtKiI21gISIM5FlWQjdIfOS-UWqK8V1mfFU5LmvqkwVBUQhmM6rCFIepXUmLpFW73GvvEzmdCGELMNSFDoLopSrSvMqrTJR8bRSRXaF3HL2rrqP0cbqUS9ePRbXNXIK65NJxeuk1X-yWd6AMLuf3XTe_w1iz5i2 |
| linkProvider | EBSCOhost |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E8%BE%B9%E7%BC%98%E5%BC%BA%E5%8C%96%E7%9A%84%E6%97%A0%E7%9B%91%E7%9D%A3%E5%8D%95%E7%9B%AE%E6%B7%B1%E5%BA%A6%E4%BC%B0%E8%AE%A1&rft.jtitle=%E7%B3%BB%E7%BB%9F%E5%B7%A5%E7%A8%8B%E4%B8%8E%E7%94%B5%E5%AD%90%E6%8A%80%E6%9C%AF&rft.au=%E6%9B%B2%E7%86%A0&rft.au=%E9%99%88%E8%8E%B9&rft.date=2024&rft.pub=%E6%B1%9F%E5%8D%97%E5%A4%A7%E5%AD%A6%E8%BD%BB%E5%B7%A5%E8%BF%87%E7%A8%8B%E5%85%88%E8%BF%9B%E6%8E%A7%E5%88%B6%E6%95%99%E8%82%B2%E9%83%A8%E9%87%8D%E7%82%B9%E5%AE%9E%E9%AA%8C%E5%AE%A4%2C%E6%B1%9F%E8%8B%8F%E6%97%A0%E9%94%A1+214122&rft.issn=1001-506X&rft.volume=46&rft.issue=1&rft.spage=71&rft.epage=79&rft_id=info:doi/10.12305%2Fj.issn.1001-506X.2024.01.08&rft.externalDocID=xtgcydzjs202401008 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fxtgcydzjs%2Fxtgcydzjs.jpg |