一种基于位置识别的室内场景点云配准方法

doi:10.13474/j.cnki.11-2246.2023.0120

测绘通报 ›› 2023, Vol. 0 ›› Issue (4): 150-153,158.doi: 10.13474/j.cnki.11-2246.2023.0120

一种基于位置识别的室内场景点云配准方法

牛学超^1,2

1. 广州市城市规划勘测设计研究院, 广东广州 510060;
2. 广东省城市感知与监测预警企业重点实验室, 广东广州 510060

收稿日期:2022-05-05 发布日期:2023-04-25
作者简介:牛学超(1996—),男,硕士,助理工程师,主要研究方向为三维激光点云数据处理。E-mail:987746174@qq.com
基金资助:
广东省城市感知与监测预警企业重点实验室基金(2020B121202019);广州市城市规划勘测设计研究院科技基金(RDI2210201040)

A registration method for indoor scenes point cloud based on place recognition

NIU Xuechao^1,2

1. Guangzhou Urban Planning & Design Survey Research Institute, Guangzhou 510060, China;
2. Guangdong Enterprise Key Laboratory for Urban Sensing, Monitoring and Early Warning, Guangzhou 510060, China

Received:2022-05-05 Published:2023-04-25

摘要/Abstract

摘要： 针对现有方法在低重叠室内场景点云配准稳健性较差的问题,本文提出了一种基于位置识别的点云自配准方法。首先基于室内空间分割结果生成虚拟雷达观测位置,构建虚拟扫描;其次从虚拟扫描中提取全局特征描述符进行位置识别;然后利用位置识别结果确定重叠区域;最后计算重叠区域的转换参数,并根据刚体转换的特性获取最终的整体转换参数。试验结果表明,本文方法能够在低重叠的室内场景精确计算转换参数。

关键词: 点云配准, 位置识别, 全局特征描述符, 虚拟雷达

Abstract: The existing solutions have low robustness for registration between low overlap point clouds in indoor scenes. In this paper, a robust place recognition based registration algorithm is proposed. Virtual scans are generated based on the result of disjoint spaces. Global feature descriptors are extracted from virtual scans subsequently.Then the overlap area can be determined using place recognition. At last, the transformation can be obtained accurately by aligning the point cloud of overlap area. The experiments show that the proposed solution estimate accurately the transformation parameter for low overlap indoor point clouds.

Key words: registration, place recognition, global feature descriptor, virtual LiDAR

中图分类号:

P237

牛学超. 一种基于位置识别的室内场景点云配准方法[J]. 测绘通报, 2023, 0(4): 150-153,158.

NIU Xuechao. A registration method for indoor scenes point cloud based on place recognition[J]. Bulletin of Surveying and Mapping, 2023, 0(4): 150-153,158.

参考文献

[1] 蔡振锋,彭斌,季霞,等. 地市级实景三维城市建设及应用——以实景三维临沂建设为例[J]. 测绘通报,2021(11):115-119.
[2] 朱庆,张利国,丁雨淋,等. 从实景三维建模到数字孪生建模[J]. 测绘学报,2022,51(6):1040-1049.
[3] 张帆,黄先锋,高云龙,等. 实景三维中国建设技术大纲(2021版)解读与思考[J]. 测绘地理信息,2021,46(6):171-174.
[4] 郑琦,邹进贵,翟若明. 基于视觉SLAM移动扫描系统的BIM建模技术[J]. 测绘通报,2021(S2):5-8.
[5] 胡小玲,布树辉. 针对大尺度场景的高效SLAM方法[J]. 测绘地理信息,2021,46(6):95-100.
[6] DONG Z,LIANG F,YANG B,et al. Registration of large-scale terrestrial laser scanner point clouds:a review and benchmark[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2020,163:327-342.
[7] GUO Yulan,SOHEL F,BENNAMOUN M,et al. An accurate and robust range image registration algorithm for 3D object modeling[J]. IEEE Transactions on Multimedia,2014,16(5):1377-1390.
[8] ZHEN D,YANG B,YUAN L,et al. A novel binary shape context for 3D local surface description[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2017,130:431-452.
[9] TAO Wuyong,HUA Xianghong,WANG Ruisheng,et al. Quintuple local coordinate images for local shape description[J]. Photogrammetric Engineering & Remote Sensing,2020,86(2):121-132.
[10] PROKOP M,SHAIKH S A,KIM K S. Low overlapping point cloud registration using line features detection[J]. Remote Sensing,2019,12(1):61.
[11] XU Y S,BOERNER R,YAO W,et al. Pairwise coarse registration of point clouds in urban scenes using voxel-based 4-planes congruent sets[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2019,151:106-123.
[12] SEGAL A,HAEHNEL D,THRUN S. Generalized-ICP[C]//Proceedings of 2009 Robotics:Science and Systems. Seattle:University of Washington,2009.
[13] ARMENI I,SENER O,ZAMIR A R,et al. 3D semantic parsing of large-scale indoor spaces[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas,NV:IEEE,2016:1534-1543.
[14] XU D,LIU J. A heterogeneous 3D map-based place recognition solution using virtual LiDAR and a polar grid height coding image descriptor[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2022,183:1-18.
[15] ZHONG Yu. Intrinsic shape signatures:a shape descriptor for 3D object recognition[C]//Proceedings of 2009 IEEE International Conference on Computer Vision Workshops. Kyoto:IEEE,2010:689-696.
[16] RUSU R B,BLODOW N,BEETZ M. Fast point feature histograms (FPFH) for 3D registration[C]//Proceedings of 2009 IEEE International Conference on Robotics and Automation. Kobe:IEEE,2009:3212-3217.

一种基于位置识别的室内场景点云配准方法

A registration method for indoor scenes point cloud based on place recognition

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	谢洪, 陈立波, 聂倩, 吴玮, 张沛. 利用点云配准的空地影像融合技术[J]. 测绘通报, 2022, 0(6): 82-87.
[2]	谢元, 董梦, 马新建. 多源数据在复杂场景建筑物三维重建的应用[J]. 测绘通报, 2022, 0(6): 143-147.
[3]	阮明浩, 卢永华, 刘玉贤, 汤圣君, 王伟玺, 张宇琦, 李游. 激光与倾斜点云精确配准与无缝融合[J]. 测绘通报, 2022, 0(4): 6-10.
[4]	于尧, 孙新柱, 郭俊阳, 陈孟元. 一种基于改进CoHOG的视觉SLAM算法[J]. 测绘通报, 2022, 0(12): 42-50.
[5]	赵彦刚, 付守健, 陈宏强, 吴波. Heron移动背包三维激光扫描系统在1∶500大比例尺测图中的精度评价及效率分析[J]. 测绘通报, 2021, 0(10): 114-116.
[6]	李宇翔, 郭际明, 潘尚毅, 吕丽丽, 卢主兴, 章迪. 一种基于ISS-SHOT特征的点云配准算法[J]. 测绘通报, 2020, 0(4): 21-26.
[7]	杨海舰, 徐二帅, 陈文佳, 许志华. 四元组标靶辅助下的RGB-D室内点云配准[J]. 测绘通报, 2020, 0(12): 32-36.
[8]	袁志聪, 鲁铁定, 刘瑞. 一种基于BFGS修正的正态分布变换点云配准方法[J]. 测绘通报, 2020, 0(10): 38-42.
[9]	李明峰, 陆海芳, 赵湘玉. 对偶四元数法在稳健点云配准中的应用[J]. 测绘通报, 2019, 0(9): 22-26.
[10]	郭雨, 夏永华, 杨明龙. 融合多源测量数据的钟乳石三维建模方法[J]. 测绘通报, 2019, 0(2): 49-53.
[11]	杨铭. 背包式移动三维激光扫描系统的应用[J]. 测绘通报, 2018, 0(9): 91-95.
[12]	杨敏, 甘淑, 袁希平, 高莎, 朱赞, 于辉. 复杂带状地形条件下的地面三维激光扫描点云数据采集与配准处理试验[J]. 测绘通报, 2018, 0(5): 35-40.
[13]	赵夫群, 周明全. 基于二维图像特征的点云配准方法[J]. 测绘通报, 2017, 0(10): 39-42,73.