ABSTRACT
Aiming at the accuracy loss caused by integer corner coordinates and repeated detection of the same line features in the point-line visual Simultaneous Localization and Mapping (SLAM) system, this letter proposed an approach that introduced an optimized bilinear interpolation algorithm in point detector, and then used the iterative method to find sub-pixel points. This letter also optimized the line features during processing. Firstly, we used the restricted short-line rejection strategy to remove some short-lines and added line features in multiple directions. Secondly, this letter proposed a method of three strategies to identify and merge repeated lines on pose-graph estimation. We tested the approach on the EuRoC Micro Aerial Vehicle (MAV) datasets and used the Absolute Trajectory Error (ATE) for evaluation. We also tested it in the real world and compared with the other two algorithms to verify its robustness and accuracy. The contribution of this paper is to verify the feasibility of sub-pixel corners in the point line slam system to improve the accuracy of the system, and combined with the optimization of line features to achieve a higher accuracy system.
- G. Bresson, Z. Alsayed, L. Yu, and S. Glaser, "Simultaneous localization and mapping: a survey of current trends in autonomous driving," IEEE Trans. Intell., vol. 2, no. 3, pp. 194-220, Sept. 2017.Google ScholarCross Ref
- R. Kazami and H. Amano, "A rapid optimization method for visual indirect SLAM using a subset of feature points," Proc. 7th Int. Symp. on Computing and Networking Workshops, Nagasaki, Japan, 2019, pp. 275-279.Google Scholar
- H. Zhou, D. Zou, L. Pei, R. Ying, P. Liu, and W. Yu, "StructSLAM: visual SLAM with building structure lines," IEEE Trans. Veh. Technol., vol. 64, no. 4, pp. 1364-1375, April 2015.Google ScholarCross Ref
- R. Mur-Artal and J. D. Tardós, "Orb-slam2: an open-source slam system for monocular stereo and rgb-d cameras," IEEE Trans. Robot., vol. 33, no. 5, pp. 1255-1262, Oct. 2017.Google ScholarDigital Library
- K. Jeong and H. Moon, "Object detection using FAST corner detector based on smartphone platforms," Proc. 1st ACIS/JNU Int. Conf. on Computers, Networks, Systems and Industrial Engineering, Jeju, Korea (South), 2011, pp. 111-115.Google Scholar
- Houssem Eddine Benseddik, Oualid Djekoune, and Mahmoud Belhocine, "SIFT and SURF Performance Evaluation for Mobile Robot-Monocular Visual Odometry," Journal of Image and Graphics, Vol. 2, No. 1, pp. 70-76, June 2014. doi: 10.12720/joig.2.1.70-76.Google Scholar
- Z. Yu and H. Min, "Visual SLAM algorithm based on ORB features and line features," Proc. Chinese Automation Congress, Hangzhou, China, 2019, pp. 3003-3008.Google Scholar
- A. Pumarola, A. Vakhitov, A. Agudo, A. Sanfeliu, and F. Moreno-Noguer, "PL-SLAM: real-time monocular visual SLAM with points and lines," Proc. IEEE Int. Conf. on Robotics and Automation, Singapore, 2017, pp. 4503-4508.Google ScholarDigital Library
- R. Grompone von Gioi, J. Jakubowicz, J. Morel, and G. Randall, "LSD: a fast line segment detector with a false detection control," IEEE Trans. Pattern Anal., vol. 32, no. 4, pp. 722-732, April 2010.Google ScholarDigital Library
- Y. Duan, J. Lu, J. Feng, and J. Zhou, "Learning rotation-invariant local binary descriptor," IEEE Trans. Image Process., vol. 26, no. 8, pp. 3636-3651, Aug. 2017.Google ScholarDigital Library
- O. S. Karthik, D. Varun, and H. Ramasangu, "Localized harris-FAST interest point detector," Proc. IEEE Annu. India Conf., Bangalore, India, 2016, pp. 1-6.Google Scholar
- Y. Qiao, Y. Tang, and J. Li, "Improved harris sub-pixel corner detection algorithm for chessboard image," Proc. of 2013 2nd Int. Conf. on Measurement, Information and Control, Harbin, China, 2013, pp. 1408-1411.Google Scholar
- S. A. Alasal, M. Alsmirat, Q. B. Baker, and Y. Jararweh, "Improving passive 3D model reconstruction using image enhancement," Proc. 6th Int. Conf. on Multimedia Computing and Systems, Rabat, Morocco, 2018, pp. 1-7.Google Scholar
- M. H. Hueckel, "A local visual operator which recognizes edges and lines," J. ACM, vol. 20, no. 4, pp. 634-647, Oct. 1973.Google ScholarDigital Library
- Q. Sun, Y. Hou, and Q. Tan, "A subpixel edge detection method based on an arctangent edge model," Optik, vol. 127, no. 14, pp. 5702-5710, Jul. 2016.Google ScholarCross Ref
- K. Jensen and D. Anastassiou, "Subpixel edge localization and the interpolation of still images," IEEE Trans. Image Process., vol. 4, no. 3, pp. 285-295, Mar. 1995.Google ScholarDigital Library
- N. Yang, R. Wang, X. Gao, and D. Cremers, "Challenges in monocular visual odometry: photometric calibration, motion bias, and rolling shutter effect," IEEE Robot. Automat. Lett., vol. 3, no. 4, pp. 2878-2885, Oct. 2018.Google ScholarCross Ref
- G. Yang, Q. Wang, P. Liu and C. Yan, "PLS-VINS: visual inertial state estimator with point-line features fusion and structural constraints," IEEE Sensors Journal, vol. 21, no. 24, pp. 27967-27981, 15 Dec.15, 2021.Google ScholarCross Ref
- Z. Liu, D. Shi, R. Li, W. Qin, Y. Zhang and X. Ren, "PLC-VIO: visual-inertial odometry based on point-line constraints," IEEE Trans. Auto. Sci. Eng., 2021, pp. 1-18.Google Scholar
- H. Wei, F. Tang, Z. Xu, C. Zhang and Y. Wu, "A point-pine VIO system with novel feature hybrids and with novel line predicting-matching," IEEE Robot. Automat. Lett., vol. 6, no. 4, pp. 8681-8688, Oct. 2021.Google ScholarCross Ref
- J. Wen, X. Zhang, H. Gao, J. Yuan, and Y. Fang, "CAE-RLSM: Consistent and efficient redundant line segment merging for online feature map building," IEEE Trans. Instrum. Meas., vol. 69, no. 7, pp. 4222-4237, July 2020.Google ScholarCross Ref
- X. Zheng, C. Xiang, H. Lu, B. M. Chen, and T. H. Lee, "Human vision inspired multi-scale line segments merging and filtering," IEEE 14th Int. Conf. on Control and Automation, 2018, pp. 259-264.Google Scholar
- Y. He, J. Zhao, Y. Guo, W. He, and K. Yuan, "PL-VIO: tightly-coupled monocular visual-inertial odometry using point and line features", Sensors, vol. 18, no. 4, pp. 1159, 2018.Google ScholarCross Ref
- G. Yao, J. Cui, K. Deng, and L. Zhang, "Robust harris corner matching based on the Quasi-Homography transform and self-adaptive window for wide-baseline stereo images," IEEE Trans. Geosci. Remote Sens., vol. 56, no. 1, pp. 559-574, Jan. 2018.Google ScholarCross Ref
- M. Burri, J. Nikolic, P. Gohl, T. Schneider, J. Rehder, S. Omari, , "The EuRoC micro aerial vehicle datasets," Proc. Int. J. Robot. Research, vol. 35, pp. 1157-1163, 2015.Google ScholarDigital Library
- A. M. Sllame, "EVO-EXPLORER: a tool for designing high-performance digital systems," Proc. Innovations in Information Technologies, Dubai, United Arab Emirates, 2007, pp. 352-356.Google Scholar
- H. Alaoui, M. T. Moutacalli, and M. Adda, "AI-Enabled high-level layer for posture recognition using the azure kinect in unity3D," Proc. IEEE 4th Int. Conf. on Image Processing, Applications and Systems, Genova, Italy, 2020, pp. 155-161.Google Scholar
- R. Suzuki, R. Kataoka, Y. Ji, K. Umeda, H. Fujii, and H. Kono, "SLAM using ICP and graph optimization considering physical properties of environment," Proc. 21st Int. Conf. on Research and Education in Mechatronics, Cracow, Poland, 2020, pp. 1-5.Google Scholar
Index Terms
- Robust Visual SLAM systems with Constrained Sub-pixel Corners and High-quality Line Features
Recommendations
An Improved Monocular PL-SlAM Method with Point-Line Feature Fusion under Low-Texture Environment
ICCCV '21: Proceedings of the 4th International Conference on Control and Computer VisionTraditional visual SLAM only relies on the point features in the scene to complete positioning and mapping. When the texture information in the scene is missing, it affects the accuracy of pose estimation and mapping. In the artificial structured ...
Integrated PSO and line based representation approach for SLAM
SAC '11: Proceedings of the 2011 ACM Symposium on Applied ComputingThis paper presents a novel method for integrating swarm intelligence and line-based representation of environment to solve the simultaneous localization and mapping (SLAM) problem of mobile robots. SLAM is a well-studied problem in mobile robotics. ...
Cooperative SLAM using M-Space representation of linear features
This paper presents a multi-robot simultaneous localization and map building (SLAM) algorithm, suitable for environments which can be represented in terms of lines and segments. Linear features are described by adopting the recently introduced M-Space ...
Comments