快速鲁棒的城市场景分段平面重建
对于基于图像的城市场景重建,由于光照变化、透视畸变、弱纹理区域等因素的影响,传统像素级与区域级的重建算法通常难以获得可靠的重建结果.为了解决此问题,本文提出一种快速、鲁棒的分段平面重建算法.根据城市场景结构特征与分段平面假设,本文算法首先利用基于连通域检测的空间平面拟合方法从初始空间点中抽取充分且可靠的候选空间平面,然后在MRF（Markov random field）能量最小化框架下将场景的完整结构推断问题转化为平面标记问题进行求解.由于候选平面集与融合灰度一致性度量、空间几何与可见性约束的能量模型的高可靠性,场景的完整结构因此可被有效地重建.实验结果表明,本文算法能较好地克服传统算法可靠性...
Saved in:
| Published in | 自动化学报 Vol. 43; no. 4; pp. 674 - 684 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
中国科学院大学 北京100049
2017
周口师范学院网络工程学院 周口466000%中国科学院自动化研究所模式识别国家重点实验室 北京100190 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0254-4156 1874-1029 |
| DOI | 10.16383/j.aas.2017.c160261 |
Cover
| Abstract | 对于基于图像的城市场景重建,由于光照变化、透视畸变、弱纹理区域等因素的影响,传统像素级与区域级的重建算法通常难以获得可靠的重建结果.为了解决此问题,本文提出一种快速、鲁棒的分段平面重建算法.根据城市场景结构特征与分段平面假设,本文算法首先利用基于连通域检测的空间平面拟合方法从初始空间点中抽取充分且可靠的候选空间平面,然后在MRF（Markov random field）能量最小化框架下将场景的完整结构推断问题转化为平面标记问题进行求解.由于候选平面集与融合灰度一致性度量、空间几何与可见性约束的能量模型的高可靠性,场景的完整结构因此可被有效地重建.实验结果表明,本文算法能较好地克服传统算法可靠性差、重建场景不完整等缺点,同时具有较高的计算效率. |
|---|---|
| AbstractList | 对于基于图像的城市场景重建,由于光照变化、透视畸变、弱纹理区域等因素的影响,传统像素级与区域级的重建算法通常难以获得可靠的重建结果.为了解决此问题,本文提出一种快速、鲁棒的分段平面重建算法.根据城市场景结构特征与分段平面假设,本文算法首先利用基于连通域检测的空间平面拟合方法从初始空间点中抽取充分且可靠的候选空间平面,然后在MRF（Markov random field）能量最小化框架下将场景的完整结构推断问题转化为平面标记问题进行求解.由于候选平面集与融合灰度一致性度量、空间几何与可见性约束的能量模型的高可靠性,场景的完整结构因此可被有效地重建.实验结果表明,本文算法能较好地克服传统算法可靠性差、重建场景不完整等缺点,同时具有较高的计算效率. 对于基于图像的城市场景重建,由于光照变化、透视畸变、弱纹理区域等因素的影响,传统像素级与区域级的重建算法通常难以获得可靠的重建结果.为了解决此问题,本文提出一种快速、鲁棒的分段平面重建算法.根据城市场景结构特征与分段平面假设,本文算法首先利用基于连通域检测的空间平面拟合方法从初始空间点中抽取充分且可靠的候选空间平面,然后在MRF (Markov random field)能量最小化框架下将场景的完整结构推断问题转化为平面标记问题进行求解.由于候选平面集与融合灰度一致性度量、空间几何与可见性约束的能量模型的高可靠性,场景的完整结构因此可被有效地重建.实验结果表明,本文算法能较好地克服传统算法可靠性差、重建场景不完整等缺点,同时具有较高的计算效率. |
| Abstract_FL | For image-based urban scene reconstruction,traditional pixeMevel or region-level methods often fail to achieve satisfactory results because of various negative factors such as illumination variations,perspective distortion,poorly textured regions,etc.To address this problem,a rapid and robust piecewise planar stereo method is proposed in this paper.Under the scene piecewise planar assumption and by taking into account the structural characteristics of urban scenes,the proposed method at first extracts sufficient and reliable candidate planes from initial spatial points based on the connected-region detection;then the problem of scene reconstruction is converted into a plane labeling problem under the Markov random field (MRF) framework.By virtue of the high reliability of our extracted candidate planes and the energy model properly designed by incorporating geometric constraints,spatial visibility and photo-consistency measures,a complete scene structure is effectively reconstructed.Experiment results show that the proposed method can satisfactorily handle the low-reliability and incomplete-reconstruction problems in traditional methods with computational efficiency. |
| Author | 王伟 高伟 朱海 胡占义 |
| AuthorAffiliation | 周口师范学院网络工程学院,周口466000 中国科学院自动化研究所模式识别国家重点实验室,北京100190 中国科学院大学,北京100049 |
| AuthorAffiliation_xml | – name: 周口师范学院网络工程学院 周口466000%中国科学院自动化研究所模式识别国家重点实验室 北京100190;中国科学院大学 北京100049 |
| Author_FL | WANG Wei ZHU Hai GAO Wei HU Zhan-Yi |
| Author_FL_xml | – sequence: 1 fullname: WANG Wei – sequence: 2 fullname: GAO Wei – sequence: 3 fullname: ZHU Hai – sequence: 4 fullname: HU Zhan-Yi |
| Author_xml | – sequence: 1 fullname: 王伟 高伟 朱海 胡占义 |
| BookMark | eNotkDtLA0EUhQeJYIz5BXYWdrvO-86WEnxBwCb9Mjs7STboRrOIj0pF1EYLO0UJaCkoKILGwl8zK_sv3BCbc5qPc-49s6iS9lOL0DzBPpFMsaWer3XmU0zAN0RiKskUqhIF3COYBhVUxVRwjxMhZ1A9y5KoJDkElOEq8tzPc3E8LN5O8qeb37szN7x2n6fufpTfvrrL8_zlw329Fw-PxcWV-x7Noem23sps_d9rqLW60mqse83NtY3GctMzQoFnJcM2ikUsIgiUiS1VjGLglnCsYwOWmgiA8fGxJqIBgLYcc6EYxxKUZjW0OInd12lbp52w198bpGVheBR3D6Lxp5iXUoILE9B0-2lnNynRnUGyrQeHoYRyAQGEsT9rbmL4 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2RA 92L CQIGP W92 ~WA 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.16383/j.aas.2017.c160261 |
| DatabaseName | 维普_期刊 中文科技期刊数据库-CALIS站点 维普中文期刊数据库 中文科技期刊数据库-工程技术 中文科技期刊数据库- 镜像站点 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 |
| DocumentTitleAlternate | Rapid and Robust Piecewise Planar Reconstruction of Urban Scenes |
| DocumentTitle_FL | Rapid and Robust Piecewise Planar Reconstruction of Urban Scenes |
| EISSN | 1874-1029 |
| EndPage | 684 |
| ExternalDocumentID | zdhxb201704017 671875713 |
| GrantInformation_xml | – fundername: 国家高技术研究发展计划(863计划); 国家自然科学基金; 河南省自然科学基金; 河南省科技攻关项目; 河南省高校重点科研项目; 周口师范学院高层次人才科研启动基金; National High Technology Research and Development Program of China (863 Program); National Natural Science Foundation of China; Natural Science Foundation of of Henan Province; Key Scientific and Technological Project of Henan; College Key Research Project of Henan; Scientific Research Starting Foundation for Advanced Talents of Zhoukou Normal University funderid: (2015AA124102); (61273280,61333015,61472419); (162300410347); (162102310589,162102210396); (17A520018,17A520019,15A520116,16B520034); (zknuc2015103); (2015AA124102); (61273280,61333015,61472419); (162300410347); (162102310589,162102210396); (17A520018,17A520019,15A520116,16B520034); (zknuc2015103) |
| GroupedDBID | --K -0Y .~1 0R~ 1B1 1~. 1~5 2B. 2C0 2RA 4.4 457 4G. 5GY 5VS 5XA 5XJ 7-5 71M 8P~ 92H 92I 92L AAIKJ AALRI AAQFI AAXUO ACGFS ADEZE ADTZH AECPX AEKER AFTJW AGHFR AGYEJ AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS BLXMC CCEZO CQIGP CS3 CUBFJ CW9 EBS EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FNPLU GBLVA HVGLF HZ~ IHE J1W JJJVA M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SES TCJ TGT U1G U5S W92 ~WA 4A8 93N ABJNI ABWVN ACRPL ADNMO PSX |
| ID | FETCH-LOGICAL-c587-e630ebd5d5b798cde2832074e140adc7e2cb7734c160cb2977ae40458340678a3 |
| ISSN | 0254-4156 |
| IngestDate | Thu May 29 04:10:30 EDT 2025 Wed Feb 14 10:03:30 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | 深度图 3D reconstruction 能量最小化 depth map plane fitting 平面拟合 Energy minimization 三维重建 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c587-e630ebd5d5b798cde2832074e140adc7e2cb7734c160cb2977ae40458340678a3 |
| Notes | Energy minimization; plane fitting; 3D reconstruction; depth map WANG Wei1, GAO Wei2,3, ZHU Hai1 ,HU Zhan-Yi2,3 （1. School of Network Engineering, Zhoukou Normal University, Zhoukou 466000 2. National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190 3. University of Chinese Academy of Sciences, Beijing 100049） For image-based urban scene reconstruction, traditional pixel-level or region-level methods often fail to achieve satisfactory results because of various negative factors such as illumination variations, perspective distortion, poorly textured regions, etc. To address this problem, a rapid and robust piecewise planar stereo method is proposed in this paper. Under the scene piecewise planar assumption and by taking into account the structural characteristics of urban scenes, the proposed method at first extracts sufficient and reliable candidate planes from initial spatial points based on the connected-region detection; then the problem of scene recons |
| PageCount | 11 |
| ParticipantIDs | wanfang_journals_zdhxb201704017 chongqing_primary_671875713 |
| PublicationCentury | 2000 |
| PublicationDate | 2017 |
| PublicationDateYYYYMMDD | 2017-01-01 |
| PublicationDate_xml | – year: 2017 text: 2017 |
| PublicationDecade | 2010 |
| PublicationTitle | 自动化学报 |
| PublicationTitleAlternate | Acta Automatica Sinica |
| PublicationTitle_FL | Acta Automatica Sinica |
| PublicationYear | 2017 |
| Publisher | 中国科学院大学 北京100049 周口师范学院网络工程学院 周口466000%中国科学院自动化研究所模式识别国家重点实验室 北京100190 |
| Publisher_xml | – name: 周口师范学院网络工程学院 周口466000%中国科学院自动化研究所模式识别国家重点实验室 北京100190 – name: 中国科学院大学 北京100049 |
| SSID | ssib017479230 ssib001102911 ssib006576350 ssib051375349 ssib007293330 ssj0059721 ssib007290157 ssib023646446 ssib005904210 |
| Score | 2.1914573 |
| Snippet | 对于基于图像的城市场景重建,由于光照变化、透视畸变、弱纹理区域等因素的影响,传统像素级与区域级的重建算法通常难以获得可靠的重建结果.为了解决此问题,本文提出一种快速、... |
| SourceID | wanfang chongqing |
| SourceType | Aggregation Database Publisher |
| StartPage | 674 |
| SubjectTerms | 三维重建 平面拟合 深度图 能量最小化 |
| Title | 快速鲁棒的城市场景分段平面重建 |
| URI | http://lib.cqvip.com/qk/90250X/201704/671875713.html https://d.wanfangdata.com.cn/periodical/zdhxb201704017 |
| Volume | 43 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier) customDbUrl: eissn: 1874-1029 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0059721 issn: 0254-4156 databaseCode: GBLVA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR3LahRBsAmbix7EJ8b4yME-hYk7j34dezazBlFPq-S29Mz0ZvGw8ZGA5KQi6kUP3hQlokdBQRE0HvyaiexfWNXT2R2IiMrC0NNdU109NVuPflQRcl4NwoEsIxMMcpEHiWnbIGdWBVa1y1BwK6yL033lKl-5llxaZaszM28au5Y2N_KlYuu350r-h6tQB3zFU7L_wNkJUqiAMvAXrsBhuP4Vj2nGaNqlOqWZclsWulhIIzAPacapjqmKaCao0lQmCAwAMnNPSSojV9OhqUZgpajuYo2EJu4ez2jKHDDgjBGzWqY6cn0JKpddU0q9p39jjySJrVo7VJpq6QodqjgWNGBwyLGJ7XEbaQS6JIwjoSnAdhexFxiXks0q7sh1YwPKUrHoeoupDl0ngLvtwIFA1ZzOqM9tenkHvmqA_mStmmp5LEUCmsJPiniBXcd18h9m0pC-vE744xU5r3PP7dMRIHFipySMwXjtoVgqQkzEFU5V4mSjIgfVLZjAtMizEc74tMjsxfTydT01OZG6hoxkCsRgw6TiDEP-Te8FLlw3VprhPo6nLhw4iBjRcXKP8f15w2VnYQwOJrrMtbXBMPqSm0f0L89H1sJBXtg_RIwgMlwfrd0Cu8gdUxsNzGitYVH1DpND3hVa0PV3fYTMbA2PkoONAJnHSFD9eD--tz3-dH_33fOfLx9W28-qrw-qVzu7Lz5WTx7tfvhSffs8fv12_Php9X3nOOl1s15nJfAJPoKCgW6zPG7bvGQly4WSRWkxbRaYtBacflMWwkZFLkScIO1FHoGnYmziFvoTtLFMfIK0Rusje5IsxKowRoWRgV-SJwOlDCYOKDAwCeMDM0fmJ-Pu36zjuPQnzJ0j5_yb6Pt_953-Vjm8m-OrAy0XilN_fH6eHEDIembuNGlt3N60Z8BW3cjP-s_lF4q-bvk |
| linkProvider | Elsevier |
| 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%BF%AB%E9%80%9F%E9%B2%81%E6%A3%92%E7%9A%84%E5%9F%8E%E5%B8%82%E5%9C%BA%E6%99%AF%E5%88%86%E6%AE%B5%E5%B9%B3%E9%9D%A2%E9%87%8D%E5%BB%BA&rft.jtitle=%E8%87%AA%E5%8A%A8%E5%8C%96%E5%AD%A6%E6%8A%A5&rft.au=%E7%8E%8B%E4%BC%9F+%E9%AB%98%E4%BC%9F+%E6%9C%B1%E6%B5%B7+%E8%83%A1%E5%8D%A0%E4%B9%89&rft.date=2017&rft.issn=0254-4156&rft.eissn=1874-1029&rft.volume=43&rft.issue=4&rft.spage=674&rft.epage=684&rft_id=info:doi/10.16383%2Fj.aas.2017.c160261&rft.externalDocID=671875713 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fimage.cqvip.com%2Fvip1000%2Fqk%2F90250X%2F90250X.jpg http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fzdhxb%2Fzdhxb.jpg |