TSDF map building based on hybrid loopback detection and closed-loop optimization

Song-min JIA; Bo-yang LI; Guo-liang ZHANG

doi:10.3788/OPE.20182606.1497

您当前的位置：

首页 >

文章列表页 >

TSDF map building based on hybrid loopback detection and closed-loop optimization

Information Sciences | 更新时间：2020-07-05

- TSDF map building based on hybrid loopback detection and closed-loop optimization
- Optics and Precision Engineering Vol. 26, Issue 6, Pages: 1497-1506(2018)
- 作者机构：
  
  北京工业大学信息学部, 北京 100124
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20182606.1497
  CLC： TP242.6
- Received：19 October 2017，
  
  Accepted：10 December 2017，
  
  Published：25 June 2018
- 稿件说明：
移动端阅览
Song-min JIA, Bo-yang LI, Guo-liang ZHANG. TSDF map building based on hybrid loopback detection and closed-loop optimization[J]. Optics and precision engineering, 2018, 26(6): 1497-1506.
DOI：

Song-min JIA, Bo-yang LI, Guo-liang ZHANG. TSDF map building based on hybrid loopback detection and closed-loop optimization[J]. Optics and precision engineering, 2018, 26(6): 1497-1506. DOI： 10.3788/OPE.20182606.1497.

摘要

由于原始TSDF（Truncated Signed Distance Function，TSDF）模型仅考虑相邻时间上的关联，误差将不可避免的累积到下一时刻，无法构建全局一致的地图。为了实时精确的建立大场景稠密3D地图，对TSDF模型进行了改进。首先，构筑相机位姿模型和加权融合3D点截断信息的TSDF模型，用于准确表示创建物体的表面。其次，提出一种改进的回环检测方法，并将其与随机蕨类彩色图像编码化相结合，进而优化TSDF模型，即混合优化位姿模型。最后，使用g2o图优化库解算约束函数，建立数据集间的优化边。实验结果表明：混合优化位姿模型能识别曾到达区域，特别在较大场景下使用可以得到更加准确的相机轨迹和地图。采用TUM数据集中的fr1/xyz、fr1/room、fr1/desk对所提算法进行检验，结果表明该方法能够使相机轨迹的均方根误差分别下降0.59 cm，3.14 cm，0.94 cm。在室内环境和公开数据集上的实验结果证明了所提算法的有效性和准确性。

Abstract

Because the original Truncated Signed Distance Function (TSDF) model only considers the correlation of adjacent time

the error will inevitably accumulate to the next time

and it is impossible to build a globally consistent map In order to establish the dense 3D map of large scenes in real time and accurately

the TSDF model was improved in this paper. First

a camera pose model and weighted fusion 3D point truncation information model were established to represent the surface of the created object. Secondly

an improved loop detection method was proposed

which was combined with the random fern color image coding

and then optimized the TSDF model

that is

the mixed optimization pose model. Finally

the g2o diagram was used to solve the constraint function and established the optimized edges between the datasets. The experimental results showed that the loopback detection method proposed in this paper could obtain more accurate camera trajectory and map in a larger scene. The proposed algorithm was verified by fr1/xyz

fr1/room and fr1/desk in the TUM dataset. The results show that the root mean square error of the camera trajectory decreased by 0.59 cm

3.14 cm

0.94 cm

respectively. The validity and accuracy of the proposed algorithm are verified in the laboratory environment and the open data set.

关键词

Keywords

references

FUENTES-PACHECO J, RUIZ-ASCENCIO J, RENDÓN-MANCHA J M. Visual simultaneous localization and mapping:a survey[J]. Artificial Intelligence Review, 2015, 43(1):55-81.

曹天扬, 蔡浩原, 方东明, 等.结合图像内容匹配的机器人视觉导航定位与全局地图构建系统[J].光学精密工程, 2017, 25(8):2221-2232.

CAO T Y, CAI H Y, FANG D M, et al.. Robot vision system for keyframe global map establishment and robot localization based on graphic content matching[J]. Opt. Precision Eng., 2017, 25(8):2221-2232. (in Chinese)

MUR-ARTAL R, MONTIEL J M M, TARDÓS J D. ORB-SLAM:A Versatile and Accurate Monocular SLAM System[J]. IEEE Transactions on Robotics, 2017, 31(5):1147-1163.

GAO X, ZHANG T. Unsupervised learning to detect loops using deep neural networks for visual SLAM system[J]. Autonomous Robots, 2017, 41(1):1-18.

KERL C, STURM J, CREMERS D. Robust odometry estimation for RGB-D cameras[C]// IEEE International Conference on Robotics and Automation. IEEE , 2013: 3748-3754.

ENDRES F, HESS J, ENGELHARD N, et al . . An evaluation of the RGB-D SLAM system[C]// IEEE International Conference on Robotics and Automation. IEEE , 2012: 1691-1696.

ENDRES F, HESS J, STURM J, et al.. 3-D Mapping With an RGB-D Camera[J]. IEEE Transactions on Robotics, 2017, 30(1):177-187.

KÜMMERLE R, GRISETTI G, STRASDAT H, et al . . G2o: A general framework for graph optimization[C]// IEEE International Conference on Robotics and Automation. IEEE , 2011: 3607-3613. http://ais.informatik.uni-freiburg.de/publications/papers/kuemmerle11icra.pdf

杜航原, 郝燕玲, 赵玉新, 等.用概率假设密度滤波实现同步定位与地图创建[J].光学精密工程, 2011, 19(12):3064-3073.

DU H Y, HAO Y L, ZHAO Y X, et al.. Implementation of SLAM by probability hypothesis density filter[J]. Opt. Precision Eng., 2011, 19(12):3064-3073. (in Chinese)

NEWCOMBE R A, IZADI S, HILLIGES O, et al . . KinectFusion: Real-time dense surface mapping and tracking[C]// IEEE International Symposium on Mixed and Augmented Reality. IEEE , 2012: 127-136. https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/ismar2011.pdf

ANDUJAR D, DORADO J, RIBEIRO A. An Approach to the Use of Depth Cameras for Weed Volume Estimation[J]. Sensors, 2016, 16(7).

TATENO K, TOMBARI F, LAINA I, et al . . CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction[C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition ( CVPR ), Hawaii , USA , June , 2017.

YAN Z, YE M, REN L. Dense Visual SLAM with Probabilistic Surfel Map.[J]. IEEE Transactions on Visualization & Computer Graphics, 2017, PP(99):1-1.

刘宗明, 张宇, 卢山, 等.非合作旋转目标闭环检测与位姿优化[J].光学精密工程, 2017, 25(4):1036-1043.

LIU Z M, ZHANG Y, LU SH, et al.. Closed-loop detection and pose optimization of non-cooperation rotating targets[J]. Opt. Precision Eng., 2017, 25(4):1036-1043. (in Chinese)

GLOCKER B, SHOTTON J, CRIMINISI A, et al.. Real-Time RGB-D Camera Relocalization via Randomized Ferns for Keyframe Encoding[J]. IEEE Trans Vis Comput Graph, 2015, 21(5):571-583.

张百强, 储海荣, 孙婷婷, 等.应用RB无迹卡尔曼滤波组合导航提高GPS重获信号后的导航精度[J].光学精密工程, 2016, 24(4):835-843.

ZHANG B Q, CHU H R, SUN T T, et al.. Precision improvement methodology for INS/GPS after GPS outage using RB-UKF[J]. Opt. Precision Eng., 2016, 24(4):835-843. (in Chinese)

祝继华, 郑南宁, 袁泽剑, 等.基于ICP算法和粒子滤波的未知环境地图创建[J].自动化学报, 2009, 35(8):1107-1113.

ZHU J H, ZHENG N N, YUAN Z J, et al.. A SLAM Approach by Combining ICP Algorithm and Particle Filter[J]. Acta Automatica Sinica, 2009, 35(8):1107-1113. (in Chinese)

STURM J, ENGELHARD N, ENDRES F, et al . . A benchmark for the evaluation of RGB-D SLAM systems[C]// Ieee/rsj International Conference on Intelligent Robots and Systems. IEEE , 2012: 573-580.

Views

662

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰