一种改进ORB特征匹配的半稠密三维重建ORB-SLAM算法

doi:10.16180/j.cnki.issn1007-7820.2021.12.011

电子科技 ›› 2021, Vol. 34 ›› Issue (12): 62-67.doi: 10.16180/j.cnki.issn1007-7820.2021.12.011

一种改进ORB特征匹配的半稠密三维重建ORB-SLAM算法

陈文佑,章伟,史晓帆,宋芳

上海工程技术大学机械与汽车工程学院,上海 201620

收稿日期:2020-08-11 出版日期:2021-12-15 发布日期:2021-12-06
作者简介:陈文佑(1995-),男,硕士研究生。研究方向:机器人定位与导航。|章伟(1977-),男,博士,教授。研究方向:非线性控制与观测、多智能体协调控制。|史晓帆(1985-),男,博士,讲师。研究方向:数字化制造、机电一体化装备。
基金资助:
国家自然科学基金(51505273)

A Semi-Dense 3D Reconstruction ORB-SLAM Algorithm with Improved ORB Feature Matching

CHEN Wenyou,ZHANG Wei,SHI Xiaofan,SONG Fang

School of Mechanical and Automotive Engineering,Shanghai University of Engineering Science, Shanghai 201620,China

Received:2020-08-11 Online:2021-12-15 Published:2021-12-06
Supported by:
National Natural Science Foundation of China(51505273)

摘要/Abstract

摘要：

视觉SLAM技术的目标是建立完善的地图及估计更精确的相机位姿。为了构建更加详细完整的三维地图,文中提出一种改进ORB特征匹配的半稠密三维重建ORB-SLAM算法来实现环境稀疏三维点云地图的构建。所提方法在ORB-SLAM算法的基础上,增加半稠密建图线程,建立半稠密三维点云地图,利用SURF特征匹配算法尺度不变性的特点改进了ORB特征匹配。在TUM RGBD数据集中进行的仿真实验结果表明,与ORB-SLAM算法相比,采用改进ORB-SLAM算法建立的三维地图能更加直观地显示出环境中物体的轮廓,特征匹配精度也有所增加。最后,应用两组数据集验证了算法的一致性。

关键词: 视觉SLAM, 半稠密, 三维重建, ORB特征匹配, SURF算法, 单目视觉, 计算机视觉, 图像处理

Abstract:

The goal of visual SLAM technology is to build a more complete map and estimate a more accurate camera pose. To construct a more detailed and complete 3D map, a semi-dense 3D reconstruction ORB-SLAM algorithm with improved ORB feature matching is proposed to realize the construction of a sparse 3D point cloud map of the environment. On the basis of the ORB-SLAM algorithm, a semi-dense mapping thread is added to establish a semi-dense 3D point cloud map. Then, the scale invariance of SURF feature matching algorithm is used to improve ORB feature matching. Simulation experiments in the TUM RGBD datasets reveal that the 3D map established by the improved ORB-SLAM algorithm can more intuitively exhibit the contours of objects in the environment when compared with the ORB-SLAM algorithm, and the feature matching accuracy is increased. Finally, the consistency of the algorithm is verified by experiments in two datasets.

Key words: visual SLAM, semi-dense, three-dimensional reconstruction, ORB feature matching, SURF algorithm, monocular vision, computer vision, image processing

中图分类号:

TP242.6

陈文佑,章伟,史晓帆,宋芳. 一种改进ORB特征匹配的半稠密三维重建ORB-SLAM算法[J]. 电子科技, 2021, 34(12): 62-67.

CHEN Wenyou,ZHANG Wei,SHI Xiaofan,SONG Fang. A Semi-Dense 3D Reconstruction ORB-SLAM Algorithm with Improved ORB Feature Matching[J]. Electronic Science and Technology, 2021, 34(12): 62-67.

图/表 7

图1

图2

图3

图4

图5

表1

表2

参考文献 16

[1]	Liu H M, Zhang G F, Bao H J. A survey of monocular simultaneous localization and mapping[J]. Journal of Computer-Aided Design & Compute Graphics, 2016, 28(6):855-868.
[2]	Davison A J, Reid I D, Molton N D, et al. Monoslam:real-time single camera SLAM[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6):1052-1067. pmid: 17431302
[3]	Engel J, Schops T, Cremers D. LSD-SLAM:large-scale direct monocular SLAM [C].Zurich:The Thirteenth European Conference on Computer Vision, 2014.
[4]	Endres F, Hess J, Sturm J, et al. 3-D mapping with an RGB-D camera[J]. IEEE Transactions on Robotics, 2014, 30(1):177-187. doi: 10.1109/TRO.2013.2279412
[5]	Gomez-Ojeda R, Moreno F A, Zuiga-Noñl D, et al. PL-SLAM: a stereo SLAM system through the combination of points and line segments[J]. IEEE Transactions on Robotics, 2019, 35(3):734-746. doi: 10.1109/TRO.8860
[6]	Mur-Artal R, Montiel J M M, Tardos J D. ORB-SLAM:a versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics, 2015, 31(5):1147-1163. doi: 10.1109/TRO.2015.2463671
[7]	Rublee E, Rabaud V, Konolige K, et al. ORB:an efficient alternative to sift or surf [C].Barcelona:IEEE International Conference on Computer Vision, 2011.
[8]	Calonder M, Lepetit V, Strecha C, et al. Brief: Binary robust independent elementary features [C].Crete:The Eleventh European Conference on Computer Vision, 2010.
[9]	Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110. doi: 10.1023/B:VISI.0000029664.99615.94
[10]	Bay H, Tuytelaars T, Van Gool L. Surf:speeded up robust features [C].Graz:The Ninth European Conference on Computer Vision, 2006.
[11]	胥斌. 图像多尺度不变特性研究及其应用[D]. 重庆:重庆大学, 2013.
	Xu Bin. Study on multi-scale invariant features of images and its applications[D]. Chongqing:Chongqing University, 2013.
[12]	Mur-Artal R, Tardós J D. Probabilistic semi-dense mapping from highly accurate feature-based monocular SLAM [C].Rome:Robotics: Science and System, 2015.
[13]	Engel J, Sturm J, Cremers D. Semi-dense visual odometry for a monocular camera [C].Sydney:IEEE International Conference on Computer Vision, 2013.
[14]	许宏科, 秦严严, 陈会茹. 基于改进ORB的图像特征点匹配[J]. 科学技术与工程, 2014, 14(18):105-109.
	Xu Hongke, Qin Yanyan, Chen Huiru. Feature points matching in image based on improved ORB[J]. Science Technology and Engineering, 2014, 14(18):105-109.
[15]	Sturm J, Engelhard N, Endres F, et al. A benchmark for the evaluation of RGB-D SLAM systems [C].Algarve:The Twenty-fifth IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012.
[16]	Yang S H, Huang Y L, Scherer S. Semantic 3D occupancy mapping through efficient high order CRFs [C].Vancouver: IEEE/RSJ International Conference on Intelligent Robots and Systems, 2017.

序列名称	freiburg1_xyz	freiburg2_xyz
序列时长	30.09	122.74
ORB-SLAM	34.96	180.16
半稠密算法	36.55	191.48
改进ORB-SLAM算法	37.23	194.90

序列名称	freiburg1_xyz	freiburg2_xyz
ORB-SLAM	83.8	86.3
半稠密算法	83.8	86.3
改进ORB-SLAM算法	88.9	91.4

一种改进ORB特征匹配的半稠密三维重建ORB-SLAM算法

A Semi-Dense 3D Reconstruction ORB-SLAM Algorithm with Improved ORB Feature Matching

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 16

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	宗圣康,程建鹏,张西良. 基于光斑位置的起重机轨道高度差自动检测方法[J]. 电子科技, 2022, 35(1): 21-28.
[2]	宋章明,贺慧勇,黄跃俊. 扁平漆包线表面缺陷在线检测研究[J]. 电子科技, 2021, 34(5): 72-78.
[3]	闫超,孙占全,田恩刚,赵杨洋,范小燕. 基于深度学习的医学图像分割技术研究进展[J]. 电子科技, 2021, 34(2): 7-11.
[4]	黎阳,沈烨,刘敏,戴仁月,姜晓燕. 融合运动信息与表观信息的多目标跟踪算法[J]. 电子科技, 2020, 33(9): 21-25.
[5]	黄雨泽,陈广东,王媛,万思钰. 一种共照射源超空间分辨率三维重建方法[J]. 电子科技, 2020, 33(7): 57-62.
[6]	章天昊,李郝林. 一种基于高斯拟合法的激光光束中心提取方法[J]. 电子科技, 2020, 33(5): 72-76.
[7]	史伟忠,曹卫卫,范彦铭,董佳筠,陈纾,肖昊. 基于FPGA的深空图像实时边缘检测算法与实现[J]. 电子科技, 2020, 33(5): 45-49.
[8]	秦兴,高晓琪,陈滨. 基于压缩卷积神经网络的图像超分辨率算法[J]. 电子科技, 2020, 33(5): 1-8.
[9]	谢智烜,姚红兵,范宁,陈枫. 面向多目标透镜的连通域标记检测算法[J]. 电子科技, 2020, 33(4): 50-54.
[10]	詹雁,张娟. 一种结构感知损失的域适应深度估计方法[J]. 电子科技, 2020, 33(12): 12-16.
[11]	杨云辉. 基于单目视觉的工件定位技术研究[J]. 电子科技, 2019, 32(12): 72-75.
[12]	康秀娟, 施展. 基于图形处理的人体内异物定位测量系统设计[J]. , 2018, 31(1): 71-.
[13]	章佳佳，杨振超，周律. 基于Matlab图像处理的果核分拣系统[J]. , 2017, 30(9): 50-.
[14]	李志森，陈晓荣. 基于Halcon的银行卡卡号识别[J]. , 2017, 30(9): 56-.
[15]	杨振超，章佳佳，周律，吴飞. 基于LabVIEW的马铃薯分拣技术[J]. , 2017, 30(9): 72-.