[1]刘 阔,张宗华.基于多视图融合的闭环检测技术研究[J].河北工业大学学报,2018,(05):1-7.[doi:10.14081/j.cnki.hgdxb.2018.05.001]
 LIU Kuo,ZHANG Zonghua.Loop closure detection based on multi view fusion data[J].Journal of Hebei University of Technology,2018,(05):1-7.[doi:10.14081/j.cnki.hgdxb.2018.05.001]
点击复制

基于多视图融合的闭环检测技术研究()
分享到:

《河北工业大学学报》[ISSN:1007-2373/CN:13-1208/T]

卷:
期数:
2018年05期
页码:
1-7
栏目:
机械工程
出版日期:
2018-10-25

文章信息/Info

Title:
Loop closure detection based on multi view fusion data
文章编号:
1007-2373(2018)05-0001-07
作者:
刘 阔张宗华
(河北工业大学 机械工程学院,天津 300130)
Author(s):
LIU KuoZHANG Zonghua
(School of Mechanical Engineering, Hebei University of Technology, Tianjin 300130, China)
关键词:
词袋模型闭环检测自动全局配准三维点云多视图
Keywords:
bag-of-words loop closure detection automated global registration 3D point cloud multi view
分类号:
TP249
DOI:
10.14081/j.cnki.hgdxb.2018.05.001
文献标志码:
A
摘要:
针对多视图融合点云片段的闭环检测问题,提出一种基于视觉词典的闭环检测方法,该方法避免了O(N 2 )的匹配复杂度的问题. 首先对融合后的点云进行去除边缘响应等预处理.然后对每个点云片段提取尺度不变特征变换Scale Invariant Feature Transform(SIFT)关键点,计算快速点特征直方图Fast Point Feature Histo?gram(FPFH)描述子,将描述子空间离散化处理构建三维特征的视觉词典树,利用树状结构的词典加快了验证几何片段的对应关系.为了保证检测闭环候选系统的可靠性,采用了点云重叠区域作为几何验证的标准.最后,利用公开的数据集进行测试,得到了较高的召回率与准确率.实验结果证明了该方法可以实现自动的全局配准.
Abstract:
Aiming at solving loop closure detection of multi view fusion of point cloud fragments, a novel detection algo?rithm based on visual dictionary is proposed, which avoids a matching of complexity O(N 2 ). Firstly, the fusion point cloudis used to remove the edge response and other preprocessing. Then the SFIT (Scale Invariant Feature Transform) keypoints and FPFH (Fast Point Feature Histogram) descriptors are extracted for each point cloud fragment. A 3D (three-di?mensional) visual vocabulary tree that discretizes a descriptor space is build. And use the tree to speed up correspon?dences for geometrical fragment verification. To ensure the reliability of detecting closed-loop candidates, the overlap ar?ea between the point clouds is used as the standard for geometric verification. Finally, experimental results on public 3Dpoint cloud datasets demonstrate that the loop closure detection system has high recall rates and precision. The experi?mental results show that the proposed method can realize automatic global registration.

参考文献/References:

[1] 邢关生,张慧,刘卫朋,等. 基于Kinect的特定人员鲁棒识别与定位[J]. 河北工业大学学报,2014,43(5):1-7.[2] 张明路,戈新良,唐智强,等. 多传感器信息融合技术研究现状和发展趋势[J]. 河北工业大学学报,2003,32(2):30-35.[3] Gao X,Zhang T. Robust RGB-D simultaneous localization and mapping using planar point features[J]. Robotics & Autonomous Systems,2015,72:1-14.[4] Zhou Q Y,Koltun V. Color map optimization for 3D reconstruction with consumer depth cameras[J]. Acm Transactions on Graphics,2014,33(4):1-10.[5] Galvez-López D,Tardos J D. Bags of binary words for fast place recognition in image sequences[J]. IEEE Transactions on Robotics,2012,28(5):1188-1197.[6] Gálvez-López D,Tardós J D. Real-time loop detection with bags of binary words[C]//IEEE International Conference on Intelligent Robots and Sys?tems,2011:51-58.[7] 李维鹏,张国良,姚二亮,等. 基于空间位置不确定性约束的改进闭环检测算法[J]. 机器人,2016,38(3):301-310..[8] 梁志伟,陈燕燕,朱松豪,等. 基于视觉词典的单目视觉闭环检测算法[J]. 模式识别与人工智能,2013,26(6):561-570.[9] Dai A,Izadi S,Theobalt C. BundleFusion:Real-time globally consistent 3D reconstruction using on-the-fly surface re-integration[J]. Acm Transac?tions on Graphics,2017,36(4):76a.[10] Besl P J,Mckay N D. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(2):239-256.[11] Curless B,Levoy M. A volumetric method for building complex models from range images[C]//Conference on Computer Graphics and InteractiveTechniques,1996:303-312.[12] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision,2004,60(2):91-110.[13] Rusu R B,Blodow N,Beetz M. Fast point feature histograms(FPFH)for 3D registration[C]//IEEE International Conference on Robotics and Automa?tion,2009:3212-3217.[14] Rusu R B,Blodow N,Marton Z C,et al. Aligning point cloud views using persistent feature histograms[C]//IEEE International Conference on Intelli?gent Robots and Systems,2013:3384-3391.[15] 高翔,张涛,刘毅,等. 视觉SLAM十四讲:从理论到实践[M]. 北京:电子工业出版社,2017:297-317.[16] Robertson S. Understanding inverse document frequency:on theoretical arguments for IDF[J]. Journal of Documentation,2013,60(5):503-520.[17] Zeng A,Song S,Niessner M,et al. 3DMatch:learning the matching of local 3D geometry in range scans[J]. arXiv preprint arXiv:1603.08182,2016.[18] Fischler M A,Bolles R C. Random sample consensus:A paradigm for model fitting with applications to image analysis and automated cartography[J]. Readings in Computer Vision,1987,24(6):726-740.[19] Zeng A,Song S,Niessner M,et al. 3DMatch:learning local geometric descriptors from RGB-D reconstructions[J]. arXiv. 1603,2016.[20] Hinterstoisser S,Lepetit V,Ilic S,et al. Model based training,detection and pose estimation of texture-less 3D objects in heavily cluttered scenes[C]//Asian Conference on Computer Vision,2012:548-562.

备注/Memo

备注/Memo:
收稿日期:2018 - 01 - 07基金项目:国家重点研发计划(2017YFF0106404);国家自然科学基金(51675160);河北省应用基础研究计划重点基础研究资助项目(15961701D);河北省高层次人才资助项目(GCC2014049);河北省人才工程培养经费资助项目(A201500503);江苏省双创人才资助项目;European Horizon 2020 through Marie Sklodowska-Curie Individual Fellowship Scheme (707466-3DRM)作者简介:刘阔(1991—),男,硕士研究生. 通讯作者:张宗华(1974—),男,教授.
更新日期/Last Update: 2018-11-20