Visual-aid inertial SLAM method based on graph optimization in indoor

被引：0
作者：
Xu X.-S. [1 ,2 ]
Dai W. [1 ,2 ]
Yang B. [1 ,2 ]
Li Y. [1 ,2 ]
Dong Y. [1 ,2 ]
机构：
[1] Key Laboratory of Micro-inertial Instrument and Advanced Navigation Technology, Ministry of Education, Nanjing
[2] School of Instrument Science and Engineering, Southeast University, Nanjing
来源：
| 2017年 / Editorial Department of Journal of Chinese Inertial Technology卷 / 25期
关键词：
Cluster sampling; Graph optimization; Integrated location; Loop detection; Simultaneous localization and mapping (SLAM);
D O I：
10.13695/j.cnki.12-1222/o3.2017.03.007
中图分类号：
学科分类号：
摘要：
To realize the accurate autonomous navigation of mobile robot in unfamiliar environment, a graph-based SLAM method based on the visual odometry is proposed, which adds loop detection into the motion estimation of visual odometry and thus optimizes the nonlinear constraints to improve the positioning accuracy. In the motion estimation of visual odometry, a cluster sampling matching track method based on ORB feature is be proposed to deal with the high mismatch rate. In the pose graph optimization, an improved loop detection method is proposed to reduce the mismatch possibility. Finally, the inertial navigation system is combined with the visual SLAM to further improve the steady and accuracy of the system. The simulations using open indoor SLAM test datasets show that the locating RMSE of the proposed method is in centimeter level, and the generated point cloud map is clearly visible. © 2017, Editorial Department of Journal of Chinese Inertial Technology. All right reserved.
引用
收藏
页码：313 / 319
页数：6
相关论文
共 13 条
  • [1] Smith R.C., Cheeseman P., On the representation and estimation of spatial uncertainty, International Journal of Robotics Research, 5, 4, pp. 56-68, (1986)
  • [2] Thrun S., Montemerlo M., The graph SLAM algorithm with applications to large-scale mapping of urban structures, International Journal of Robotics Research, 25, 5-6, pp. 403-429, (2006)
  • [3] Liang M.-J., Min H.-Q., Luo R.-H., Graph-based SLAM: A survey, Robot, 35, 4, pp. 500-512, (2013)
  • [4] Luo W.-C., Liu G.-D., Yang H.-Y., Application of SIFT and advanced RANSAC algorithm on image registration, Computer Engineering and Applications, 49, 15, (2013)
  • [5] Qu T.-W., An B., Chen G.-L., Application of improved RANSAC algorithm to image registration, Computer Application, 7, (2010)
  • [6] Liu C.-Y., Indoor localization method based on pedestrian dead reckoning aided by multi-source fusion, Journal of Chinese Inertial Technology, 24, 2, pp. 208-214, (2016)
  • [7] Henry P., Krainin M., Herbst E., Et al., RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments, International Journal of Robotics Research, 31, 5, pp. 647-663, (2012)
  • [8] Rublee E., Rabaud V., Konolige K., Et al., ORB: An efficient alternative to SIFT or SURF, International Conference of Computer Vision, pp. 2564-2571, (2011)
  • [9] Sattler T., Leibe B., Kobbelt L., SCRAMSAC: Improving RANSAC's efficiency with a spatial consistency filter, 12th IEEE International Conference on Computer Vision, pp. 2090-2097, (2015)
  • [10] Raguram R., Chum O., Pollefeys M., Et al., USAC: A universal framework for random sample consensus, IEEE Transactions on Pattern Analysis & Machine Intelligence, 35, 8, pp. 2022-2038, (2013)
12