Optimization Algorithm of RGB-D SLAM Visual Odometry based on Triangulation

doi:10.23940/ijpe.20.03.p13.438445

Int J Performability Eng ›› 2020, Vol. 16 ›› Issue (3): 438-445.doi: 10.23940/ijpe.20.03.p13.438445

Previous Articles Next Articles

Optimization Algorithm of RGB-D SLAM Visual Odometry based on Triangulation

Jingwei Dong^*, Yiming Jiang, and Zhiyu Han

School of Measure Control Technology and Communication Engineering, Harbin University of Science and Technology, Harbin, 150080, China

Submitted on ; Revised on ; Accepted on
Contact: Jingwei Dong E-mail:djw@hrbust.edu.cn

Abstract

Abstract: In this paper, an improved RGB-D SLAM scheme is proposed to solve the problems of great tracking error, long time-consuming in front-end, and high pressure of algorithm in back-end. The realization scheme is mainly aimed at improving the visual odometry. First, the ORB extraction algorithm is used to extract the feature points of the current frame and calculate the descriptors. Then, the current frame is matched with the local map by descriptors, and the matched feature points are added to the local map. Finally, the camera pose is calculated by the PnP algorithm. In order to ensure the tracking accuracy, a triangulation algorithm is proposed to optimize the depth value of map points in the local map. A series of fr1 datasets in the tum database are tested. The experimental results show that the real-time performance is guaranteed, and the RMSE (root mean square error) in the tracking process is reduced by 9% on average. Moreover, the image indexes of the point cloud image generated in the tracking process are also significantly improved.

Key words: RGB-D SLAM, ORB extraction algorithm, PnP algorithm, triangulation

Jingwei Dong, Yiming Jiang, and Zhiyu Han. Optimization Algorithm of RGB-D SLAM Visual Odometry based on Triangulation [J]. Int J Performability Eng, 2020, 16(3): 438-445.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

1. P. Henry, M. Krainin, E. Herbst, et al.“RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments”, The 12th International Symposium on Experimental Robotics, No.20, pp.22-25, December 2010.
2. J. Stuckler, S. Behnke.“Integrating Depth and Colour Cues for Dense Multi- Resolution Scene Mapping Using RGB-D Cameras”, Multi-sensor Fusion and Integration for Intelligent Systems, Vol.162, June 2013.
3. R. Murartal, J. D. Tardos.“ORB-SLAM2:An Open-source SLAM System for Monocular, Stereo and RGB-D Cameras”, IEEE Transactions or Robotics, Vol.33, No.5, pp.1255-1262, May 2017.
4. S. Chen, Y. Guo, T. Gao, et al.“RGB-D Visual SLAM Algorithm for Mobile Robots”, Transactions of the Chinese Society for Agricultural Machinery, Vol.49, No.10, pp.38-45, August 2018.
5. Y. Zhang, G. Zhang.“Loop-closing Detection Algorithm of Keyframe-based Visual-inertial SLAM”, Journal of Frontiers of Computer Science and Technology, Vol.12, No.11, pp.1777-1787, April 2018.
6. F. Endress, J. Hess, J. Sturm, et al.“3-D Mapping with an RGB-D Camera”, IEEE Transaction on Robotics, Vol.30, No.1, pp.177-187, January 2014.
7. Y. Lin, X. Zhu,Z. Zheng, “The Individual Identification Method of Wireless Device Based on Dimensionality Reduction and Machine Learning,” Journal of Supercomputing, No.5, pp.1-18, May 2017.
8. Z. Zhang, H. Zheng, X. Zhou, et al.“RGB-D SLAM Algorithm Based on ORB Features and Visual Dictionary”, Computer Engineering and Applications, Vol.54, No.12, pp.170-176, June 2018.
9. Y. Lin, C. Wang, J. X. Wang,Z. Dou, “A Novel Dynamic Spectrum Access Framework Based on Reinforcement Learning for Cognitive Radio Sensor Networks,” in Sensors, Vol.16, No.10, pp.1-22, October 2016.
10. Z. Y. Zhang, X. H. Guo,Y. Lin, “Trust Management Method of D2D Communication Based on RF Fingerprint Identification,” in IEEE Access, No.6, pp.66082-66087, June 2018.
11. Y. Tu, Y. Lin,J. Wang, “Semi-Supervised Learning with Generative Adversarial Networks on Digital Signal Modulation Classification,” CMC-Computers Materials & Continua, Vol.55, No.2, pp.243-254, February 2018.
12. E. Rublee, V. Rabaud, K. Konolige, et al.“ORB: An Efficient Alternative to SIFT or SURF”, International Conference on Computer Vision, pp.2564-2571, June 2011.
13. Y. Lin, Y. Li,X. Yin, “Multisensor Fault Diagnosis Modeling Based on the Evidence Theory,” IEEE Transactions on Reliability, Vol.67, No.2, pp.513-521, February 2018.
14. C. Forster, M. Pizzoli, D. Scaramuzza.“SVO: Fast Semi-Direct Monocular Visual Odometry”, In Robotics and Automation (ICRA), 2014 IEEE International Conference on (rs, ed.), pp.15-22, June 2014.

Optimization Algorithm of RGB-D SLAM Visual Odometry based on Triangulation

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 0

Recommended 0