基于RGB-D的室内场景实时三维重建算法
摘要：针对基于视觉的室内场景三维重建过程中存在三维点云匹配不准确、过程耗时和深度信息部分缺失的问题,提出一种带有深度约束和局部近邻约束的基于RGB-D的室内场景实时三维重建算法.该算法首先利用RGB-D相机采集到的RGB图像做哈里斯角点检测,再用SURF特征点描述方法对检测到的特征点生成64维特征描述子.接着利用特征点集合的深度信息和局部近邻特征点信息作为约束,初步筛选出相邻帧间正确的匹配点对,再结合随机抽样一致性（RANSAC）算法去除外点,以此得到相机的姿态估计.最后利用RGB-D的深度图像,在图优化方法（g2o）的基础上生成三维点云,实现室内场景的三维重建.实验中,RGB-D摄像头装载在...
Saved in:
| Published in | 东北大学学报（自然科学版） Vol. 38; no. 12; pp. 1764 - 1768 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
吉林大学 机械科学与工程学院,吉林 长春 130022
2017
长春汽车工业高等专科学校,吉林 长春 130013%吉林大学 机械科学与工程学院,吉林 长春,130022%长春师范大学,吉林 长春,130032 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1005-3026 |
| DOI | 10.12068/j.issn.1005-3026.2017.12.020 |
Cover
| Abstract | 摘要：针对基于视觉的室内场景三维重建过程中存在三维点云匹配不准确、过程耗时和深度信息部分缺失的问题,提出一种带有深度约束和局部近邻约束的基于RGB-D的室内场景实时三维重建算法.该算法首先利用RGB-D相机采集到的RGB图像做哈里斯角点检测,再用SURF特征点描述方法对检测到的特征点生成64维特征描述子.接着利用特征点集合的深度信息和局部近邻特征点信息作为约束,初步筛选出相邻帧间正确的匹配点对,再结合随机抽样一致性（RANSAC）算法去除外点,以此得到相机的姿态估计.最后利用RGB-D的深度图像,在图优化方法（g2o）的基础上生成三维点云,实现室内场景的三维重建.实验中,RGB-D摄像头装载在自主移动导航的小车上,实时重构的三维场景验证了所提算法的可行性和准确性. |
|---|---|
| AbstractList | TP391.4; 针对基于视觉的室内场景三维重建过程中存在三维点云匹配不准确、过程耗时和深度信息部分缺失的问题,提出一种带有深度约束和局部近邻约束的基于RGB-D的室内场景实时三维重建算法.该算法首先利用RGB-D相机采集到的RGB图像做哈里斯角点检测,再用SURF特征点描述方法对检测到的特征点生成64维特征描述子.接着利用特征点集合的深度信息和局部近邻特征点信息作为约束,初步筛选出相邻帧间正确的匹配点对,再结合随机抽样一致性(RANSAC)算法去除外点,以此得到相机的姿态估计.最后利用RGB-D的深度图像,在图优化方法(g2o)的基础上生成三维点云,实现室内场景的三维重建.实验中,RGB-D摄像头装载在自主移动导航的小车上,实时重构的三维场景验证了所提算法的可行性和准确性. 摘要：针对基于视觉的室内场景三维重建过程中存在三维点云匹配不准确、过程耗时和深度信息部分缺失的问题,提出一种带有深度约束和局部近邻约束的基于RGB-D的室内场景实时三维重建算法.该算法首先利用RGB-D相机采集到的RGB图像做哈里斯角点检测,再用SURF特征点描述方法对检测到的特征点生成64维特征描述子.接着利用特征点集合的深度信息和局部近邻特征点信息作为约束,初步筛选出相邻帧间正确的匹配点对,再结合随机抽样一致性（RANSAC）算法去除外点,以此得到相机的姿态估计.最后利用RGB-D的深度图像,在图优化方法（g2o）的基础上生成三维点云,实现室内场景的三维重建.实验中,RGB-D摄像头装载在自主移动导航的小车上,实时重构的三维场景验证了所提算法的可行性和准确性. |
| Abstract_FL | A novel RGB-D based feature point depth constraint and locality constraint integrated real-time indoor scene 3D reconstruction algorithm is proposed, which focusing to solve problems such as the inaccuracy of 3D point cloud matching, excessive time consuming and the loss of point depth. Firstly, the feature points are detected using Harris point detector, and then labeled with 64 dimensional vector using SURF descriptor. Secondly, the initial correct feature point pairs are selected between the successive frames with the depth information constraint and feature point locality constraint in addition to vector similarity constraint. Thirdly, the outliers are removed and the camera pose is estimated based on the random sample consensus ( RANSAC ) method. Eventually, 3D point clouds are determined using the general graph optimization ( g2o ) facilitating the indoor scene reconstruction. In the experiments, the RGB-D camera is fixed on the automatic guided vehicle to capture the indoor surrounding scenes. Experimental results validate that the proposed approach is feasible and effective. |
| Author | 胡正乙;谭庆昌;孙秋成 |
| AuthorAffiliation | 吉林大学机械科学与工程学院,吉林长春130022;长春汽车工业高等专科学校,吉林长春130013;长春师范大学,吉林长春130032 |
| AuthorAffiliation_xml | – name: 吉林大学 机械科学与工程学院,吉林 长春 130022;长春汽车工业高等专科学校,吉林 长春 130013%吉林大学 机械科学与工程学院,吉林 长春,130022%长春师范大学,吉林 长春,130032 |
| Author_FL | TAN Qing-chang SUN Qiu-cheng HU Zheng-yi |
| Author_FL_xml | – sequence: 1 fullname: HU Zheng-yi – sequence: 2 fullname: TAN Qing-chang – sequence: 3 fullname: SUN Qiu-cheng |
| Author_xml | – sequence: 1 fullname: 胡正乙;谭庆昌;孙秋成 |
| BookMark | eNo9j0FLw0AUhPdQwVr7JwTxlPh2N7ubHLVqFQqC9B52N0lN0a0miPWuFQ96k6KIXjzHgyKS_p0mxX9hpOJpYOab95glVDMDEyK0isHGBLi73rfjNDU2BmAWBcJtAlhUmQ0Eaqj-7y-iZprGCgA8RzDi1REpXvJpfnfQ3rS2Zo-XRfZajK6Kp7x8eCuy53L8Of26mU0-vq9vi0k-y8bl-_0yWojkURo2_7SBujvb3dau1dlv77U2OpZmHlhEBlyJkHHhRYywiEVKYi24EzjaY4ILxojSJGDUFVpBSFwdiKqAdRRKrQRtoLX52XNpIml6fn9wlpjqoR-oYDhUvxOr9QQqcmVO6sOB6Z3GFXuSxMcyufC5oB5lQDH9ASOhZkk |
| ClassificationCodes | TP391.4 |
| 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 ~WA 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.12068/j.issn.1005-3026.2017.12.020 |
| 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- 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 | RGB-D Based Indoor Scene Real-Time 3D Reconstruction Algorithm |
| DocumentTitle_FL | RGB-D Based Indoor Scene Real-Time 3 D Reconstruction Algorithm |
| EndPage | 1768 |
| ExternalDocumentID | dbdxxb201712020 673935031 |
| GrantInformation_xml | – fundername: 国家自然科学基金资助项目 funderid: (51405184) |
| GroupedDBID | -03 2B. 2C. 2RA 5XA 5XD 92E 92I 92L ABDBF ACGFS ALMA_UNASSIGNED_HOLDINGS CCEZO CEKLB CQIGP CW9 EAD EAP EAS EOJEC ESX OBODZ TCJ TGP U1G U5M ~WA 4A8 93N ABJNI ACUHS PSX |
| ID | FETCH-LOGICAL-c590-2ad6b7e5679f525f5fba1c764d4c95767552bc2d5387cb0e28cd7b7e1cfeacb73 |
| ISSN | 1005-3026 |
| IngestDate | Thu May 29 03:59:15 EDT 2025 Wed Feb 14 10:02:06 EST 2024 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 12 |
| Keywords | RGB-D 特征点深度约束 特征点局部近邻约束 feature point depth constraint 3 D reconstruction feature point locality constraint 实时性 instantaneity 三维重建 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c590-2ad6b7e5679f525f5fba1c764d4c95767552bc2d5387cb0e28cd7b7e1cfeacb73 |
| Notes | A novel RGB-D based feature point depth constraint and locality constraint integrated real-time indoor scene 3D reconstruction algorithm is proposed, which focusing to solve problems such as the inaccuracy of 3D point cloud matching, excessive time consuming and the loss o f point depth. Firstly, the feature points are detected using Harris point detector, and then labeled with 64 dimensional vector using SURF descriptor. Secondly,the initial correct feature point pairs are selected between the successive frames with the depth information constraint and feature point locality constraint in addition to vector similarity constraint. T h ird ly, the outliers are removed and the camera pose is estimated based on the random sample consensus （ R ANSAC） method. Eventually, 3D point clouds are determined using the general graph optimization （ g2o ） facilitating the indoor scene reconstruction. In the experiments, the RGB-D camera is fixed on the automatic guided vehicle to capture the indoor surrounding scenes. Exper |
| PageCount | 5 |
| ParticipantIDs | wanfang_journals_dbdxxb201712020 chongqing_primary_673935031 |
| PublicationCentury | 2000 |
| PublicationDate | 2017 |
| PublicationDateYYYYMMDD | 2017-01-01 |
| PublicationDate_xml | – year: 2017 text: 2017 |
| PublicationDecade | 2010 |
| PublicationTitle | 东北大学学报（自然科学版） |
| PublicationTitleAlternate | Journal of Northeastern University（Natural Science） |
| PublicationTitle_FL | Journal of Northeastern University(Natural Science) |
| PublicationYear | 2017 |
| Publisher | 吉林大学 机械科学与工程学院,吉林 长春 130022 长春汽车工业高等专科学校,吉林 长春 130013%吉林大学 机械科学与工程学院,吉林 长春,130022%长春师范大学,吉林 长春,130032 |
| Publisher_xml | – name: 长春汽车工业高等专科学校,吉林 长春 130013%吉林大学 机械科学与工程学院,吉林 长春,130022%长春师范大学,吉林 长春,130032 – name: 吉林大学 机械科学与工程学院,吉林 长春 130022 |
| SSID | ssib000947529 ssib051368049 ssib023167010 ssj0040330 ssib002039846 ssib004675270 ssib006703041 ssib002263414 ssib008679651 ssib001128993 |
| Score | 2.1294165 |
| Snippet | 摘要：针对基于视觉的室内场景三维重建过程中存在三维点云匹配不准确、过程耗时和深度信息部分缺失的问题,提出一种带有深度约束和局部近邻约束的基于RGB-D的室内场景实时三... TP391.4; 针对基于视觉的室内场景三维重建过程中存在三维点云匹配不准确、过程耗时和深度信息部分缺失的问题,提出一种带有深度约束和局部近邻约束的基于RGB-D的室内场景实... |
| SourceID | wanfang chongqing |
| SourceType | Aggregation Database Publisher |
| StartPage | 1764 |
| SubjectTerms | RGB-D 三维重建 实时性 特征点局部近邻约束 特征点深度约束 |
| Title | 基于RGB-D的室内场景实时三维重建算法 |
| URI | http://lib.cqvip.com/qk/90188A/201712/673935031.html https://d.wanfangdata.com.cn/periodical/dbdxxb201712020 |
| Volume | 38 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVEBS databaseName: EBSCOhost Academic Search Ultimate - TFS issn: 1005-3026 databaseCode: ABDBF dateStart: 20150901 customDbUrl: https://search.ebscohost.com/login.aspx?authtype=ip,shib&custid=s3936755&profile=ehost&defaultdb=asn isFulltext: true dateEnd: 99991231 titleUrlDefault: https://search.ebscohost.com/direct.asp?db=asn omitProxy: true ssIdentifier: ssj0040330 providerName: EBSCOhost |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR3LbtQw0OpDQnBAPEUpoB7wqdqS2HFsH53dLBUSHFCReqsSJymnLY9WqnrmIQ5wQxUIwQWJWzmAENr-TrcVf8GMk901sOJ1sRx7xvOKMxPHnhByVQB3WSnKFjz_Q0yqDVOqLFjLcvDVLKoKa3FB_-atePlOdGNVrE5Nf_B2LW1t5kt2Z-K5kv-xKrSBXfGU7D9YdjQoNEAd7AslWBjKv7IxTQXVXZoYmkZYqvT29aTVoamkGq4i7DcpNa6iYqqEw2g7jJhqTU23gdGpa5E0id1giiqN4yQJTQBdUyWp6iAwthjsQiyJWAmn9S8sh1FuMwIQQrptByaQDVNXOtTEXgUYM9QAbyBKmypFU4XkjKMCUiBLEnF16GFJ5BCBa6zRgobD5tSEODDCcseOpvoHkCTATpTHoGpQeMBrj0EcIa0b0ipxfIJQgb9QUp8IdTe1U23g1BajOicJvej6hvo3DLmYIFqt_9RxJ51moFSOhxGMduZjMEV-JbzougG528hlxCJ-UGTeGm-IyWF5UCcSGDoprvzJyDyXE8o6DXwTvsClmugaWRAr5xuRyNKICO5ulG5FnAXjmGC0U7PIi-3tHGFgABZMk1mGC18zZNYknaTrReqRFF6kDWE8vMl7kWDAtfIz2bEY4if_iDSge64jRk_kReouL-T4AzbDBA7BOHIVIY-V-2BcB2FRwHmdiKQR8xihQyVc-50KMMXK3Y3e-n0IHN05vl6V9da9kHPlFDnZvCsumHrinyZTO3fPkBNeBtGzhA3e9Q_6L9y0P3r9aLD3fvDk8eBN__DVx8He28PdLwdfnx3tf_729Plgv3-0t3v46eU5stJNV9rLreY3KC0rdNBiWRHnshSggEowUYkqz0ILRi8iqwXmYhIst6yAyEXaPCiZsoUEhNBWEFTlkp8nM72NXnmBLAie2SKsKpvzKspkmcnQZlkZVFJmueLlHJkfCb92r852gxs_NRfg--fIQqOOteYZ-HDtp9vj4p9B5slxrNermJfIzOaDrfIyxPWb-ZXmnvoOqLizcQ |
| 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%8ERGB-D%E7%9A%84%E5%AE%A4%E5%86%85%E5%9C%BA%E6%99%AF%E5%AE%9E%E6%97%B6%E4%B8%89%E7%BB%B4%E9%87%8D%E5%BB%BA%E7%AE%97%E6%B3%95&rft.jtitle=%E4%B8%9C%E5%8C%97%E5%A4%A7%E5%AD%A6%E5%AD%A6%E6%8A%A5%EF%BC%88%E8%87%AA%E7%84%B6%E7%A7%91%E5%AD%A6%E7%89%88%EF%BC%89&rft.au=%E8%83%A1%E6%AD%A3%E4%B9%99&rft.au=%E8%B0%AD%E5%BA%86%E6%98%8C&rft.au=%E5%AD%99%E7%A7%8B%E6%88%90&rft.date=2017&rft.pub=%E5%90%89%E6%9E%97%E5%A4%A7%E5%AD%A6+%E6%9C%BA%E6%A2%B0%E7%A7%91%E5%AD%A6%E4%B8%8E%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E5%90%89%E6%9E%97+%E9%95%BF%E6%98%A5+130022&rft.issn=1005-3026&rft.volume=38&rft.issue=12&rft.spage=1764&rft.epage=1768&rft_id=info:doi/10.12068%2Fj.issn.1005-3026.2017.12.020&rft.externalDocID=dbdxxb201712020 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fimage.cqvip.com%2Fvip1000%2Fqk%2F90188A%2F90188A.jpg http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fdbdxxb%2Fdbdxxb.jpg |