On augmenting the visual slam with direct orientation measurement using the 5-point algorithm

• Autorzy: Schmidt A. , Kraft A. , Fularz M. , Domagała Z.
• Języki publikacji: EN

Abstrakty

EN

This paper presents the attempt to merge two paradigms of the visual robot navigation: Visual Simultaneous Localization and Mapping (VSLAM) and Visual Odometry (VO). The VSLAM was augmented with the direct, visual measurement of the robot orientation change using the 5-point algorithm. The extended movement model of the robot was proposed and additional measurements were introduced to the SLAM system. The efficiency of the 5-point and 8-point algorithms was compared. The augmented system was compared with the state of the art VSLAM solution and the proposed modification allowed to reduce the tracking error by over 30%.

Słowa kluczowe

EN

visual SLAM; visual odometry

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2013
• Tom: Vol. 7, No. 1
• Strony: 5--10
• Opis fizyczny: Bibliogr. 14 poz., rys.

Twórcy

autor

Schmidt A.

• Poznań University of Technology, Institute of Control and Information Engineering, ul. Piotrowo 3A, 60-965 Poznań, Poland

autor

Kraft A.

• Poznań University of Technology, Institute of Control and Information Engineering, ul. Piotrowo 3A, 60-965 Poznań, Poland

autor

Fularz M.

• Poznań University of Technology, Institute of Control and Information Engineering, ul. Piotrowo 3A, 60-965 Poznań, Poland

autor

Domagała Z.

• Poznań University of Technology, Institute of Control and Information Engineering, ul. Piotrowo 3A, 60-965 Poznań, Poland

Bibliografia

• [1] A.J. Davison, D.W. Murray, “Simultaneous Localization and Map-Building Using Active Vision”, IEEE Trans. PAMI, vol. 24(7), 2002, pp. 865–880.
• [2] R. Sim, P. Elinas, M. Griffin, “Vision-Based SLAM Using the Rao-Blackwellised Particle Filter”. In: Proc. IJCAI Workshop Reasoning with Uncertainty in Robotics, 2005.
• [3] J. Sturm, A. Visser, “An appearance-based visual compass for mobile robots”, Robotics and Autonomous Systems, vol. 57(5), 2009, pp. 536–545.
• [4] A.J. Davison, I. Reid, N. Molton and O. Stasse, “MonoSLAM: Real-Time Single Camera SLAM”, IEEE Trans. PAMI, vol. 29(6), 2007, pp. 1052–1067.
• [5] A. Schmidt, A. Kasinski, “The Visual SLAM System for a Hexapod Robot”, Lecture Notes in Computer Science, vol. 6375, 2010, pp. 260–267.
• [6] D. Scaramuzza, F. Fraundorfer, “Visual Odometry: Part I - The First 30 Years and Fundamentals”, IEEE Robotics and Automation Magazine, vol. 18(4), 2011, pp. 80–92.
• [7] F. Fraundorfer, D. Scaramuzza, “Visual Odometry: Part II - Matching, Robustness and Applications”, IEEE Robotics and Automation Magazine, vol. 19(2), 2012, pp. 78–90.
• [8] M. Fularz, M. Kraft, A. Schmidt, A. Kasinski, “FPGA Implementation of the Robust Essential Matrix Estimation with RANSAC and the 8-Point and the 5-Point Method”, Lecture Notes in Computer Science, vol. 7174, 2012, pp. 60-71.
• [9] H. Li, R. Hartley, “Five-Point Motion Estimation Made Easy”, in Proc. of the 18th International Conference on Pattern Recognition, vol. 1, 2006, pp. 630–633.
• [10] S. Ceriani, G. Fontana, A. Giusti, D. Marzorati, M. Matteucci, D. Migliore, D. Rizzi, D.G. Sorrenti, P. Taddei, “RAWSEEDS ground truth collection systems for indoor self-localization and mapping”, Autonomous Robots Journal, vol. 27(4), 2009, pp. 353–371.
• [11] J. Civera, A.J. Davison, J.M.M. Montiel, “Inverse Depth Parametrization for Monocular SLAM”, IEEE Transactions on Robotics, vol. 24(5), 2008, pp. 932–945.
• [12] R.I. Hartley, A. Zisserman, “Multiple View Geometry in Computer Vision”, 2nd edition, 2004, Cambridge University Press.
• [13] H. Stewénius, C. Engels, D. Nistér, “Recent developments on direct relative orientation”, ISPRS J. of Photogrammetry and Remote Sensing, vol. 60(4), 2006, pp. 284–294.
• [14] M. Fischler and R. Bolles, “Random Sample Consensus: a Paradigm for Model Fitting with Applications to Image Analysis andAutomated Cartography”, Comm. of the ACM, vol. 24(6), 1981, pp. 381–395.