On the efficiency of population-based optimization in finding best parameters for RGB-D visual odometry

• Autorzy: Kostusiak Aleksander , Skrzypczyński Piotr

Identyfikatory

DOI

10.14313/JAMRIS/2-2019/13

• Języki publikacji: EN

Abstrakty

EN

Visual odometry estimates the transformations between consecutive frames of a video stream in order to recover the camera’s trajectory. As this approach does not require to build a map of the observed environment, it is fast and simple to implement. In the last decade RGBD cameras proliferated in roboTIcs, being also the sensors of choice for many practical visual odometry systems. Although RGB-D cameras provide readily available depth images, that greatly simplify the frame-to-frame transformations computaTIon, the number of numerical parameters that have to be set properly in a visual odometry system to obtain an accurate trajectory estimate remains high. Whereas seƫng them by hand is certainly possible, it is a tedious try-and-error task. Therefore, in this article we make an assessment of two population-based approaches to parameter opTImizaTIon, that are for long time applied in various areas of robotics, as means to find best parameters of a simple RGB-D visual odometry system. The optimization algorithms investigated here are particle swarm optimization and an evolutionary algorithm variant. We focus on the optimization methods themselves, rather than on the visual odometry algorithm, seeking an efficient procedure to find parameters that minimize the estimated trajectory errors. From the experimental results we draw conclusions as to both the efficiency of the optimization methods, and the role of particular parameters in the visual odometry system.

Słowa kluczowe

EN

particle swarm optimization (PSO); evolutionary algorithm; visual odometry; RGB-D

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2019
• Tom: Vol. 13, No. 2
• Strony: 5--14
• Opis fizyczny: Bibliogr. 27 poz., rys.

Twórcy

autor

Kostusiak Aleksander

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

autor

Skrzypczyński Piotr

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

Bibliografia

• [1] P. Alcantarilla, J. Nuevo, and A. Bartoli, “Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces”. In: Procedings of the British Machine Vision Conference 2013, Bristol, 2013, 13.1–13.11, 10.5244/C.27.13.
• [2] M. Annunziato and S. Pizzuti, “Adaptive parameterization of evolutionary algorithms driven by reproduction and competition”. In: Proceedings of the European Symposium on Intelligent Techniques (ESIT 2000), 2000, 246–256.
• [3] J. Arabas, Lectures in evolutionary algorithms (in Polish: Wykłady z algorytmów ewolucyjnych), WNT: Warsaw, 2001.
• [4] A. Bachrach, S. Prentice, R. He, P. Henry, A. S. Huang, M. Krainin, D. Maturana, D. Fox, and N. Roy, “Estimation, planning, and mapping for autonomous ϐlight using an RGB-D camera in GPSdenied environments”, The International Journal of Robotics Research, vol. 31, no. 11, 2012, 1320–1343, 10.1177/0278364912455256.
• [5] D. Belter, M. Nowicki, and P. Skrzypczyński, “On the Performance of Pose-Based RGB-D Visual Navigation Systems”. In: D. Cremers, I. Reid, H. Saito, and M.-H. Yang, eds., Computer Vision –ACCV 2014, 2015, 407–423, 10.1007/978-3-319-16808-1_28.
• [6] D. Belter and P. Skrzypczyński, “Populationbased Methods for Identification and Optimization of a Walking Robot Model”. In: K. R. Kozłowski, ed., Robot Motion and Control 2009, 2009, 185–195, 10.1007/978-1-84882-985-5_18.
• [7] R. Eberhart and J. Kennedy, “A new optimizer using particle swarm theory”. In: MHS’95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science, 1995, 39–43, 10.1109/MHS.1995.494215.
• [8] A. S. Eesa, Z. Orman, and A. M. A. Brifcani, “A novel feature-selection approach based on the cuttlefish optimization algorithm for intrusion detection systems”, Expert Systems with Applications, vol. 42, no. 5, 2015, 2670–2679, 10.1016/j.eswa.2014.11.009.
• [9] F. Endres, J. Hess, N. Engelhard, J. Sturm, D. Cremers, and W. Burgard, “An evaluation of the RGBD SLAM system”. In: 2012 IEEE International Conference on Robotics and Automation, 2012, 1691–1696, 10.1109/ICRA.2012.6225199.
• [10] F. Endres, J. Hess, J. Sturm, D. Cremers, and W. Burgard, “3-D Mapping With an RGB-D Camera”, IEEE Transactions on Robotics, vol. 30, no. 1, 2014, 177–187, 10.1109/TRO.2013.2279412.
• [11] A. Engelbrecht, “Particle swarm optimization: Velocity initialization”. In: 2012 IEEE Congress on Evolutionary Computation, 2012, 1–8, 10.1109/CEC.2012.6256112.
• [12] J. M. Falquez, M. Kasper, and G. Sibley, “Inertial aided dense & semi-dense methods for robust direct visual odometry”. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016, 3601–3607, 10.1109/IROS.2016.7759530.
• [13] M. A. Fischler and R. C. Bolles, “Random sample consensus: A paradigm for model ϐitting with applications to image analysis and automated cartography”, Communications of the ACM, vol. 24, no. 6, 1981, 381–395, 10.1145/358669.358692.
• [14] D. E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, AddisonWesley Longman Publishing Co., Inc.: Boston, MA, USA, 1989.
• [15] W. Kabsch, “A solution for the best rotation to relate two sets of vectors”, Acta Crystallographica Section A: Crystal Physics, Diffraction, Theoretical and General Crystallography, vol. 32, no. 5, 1976, 922–923, 10.1107/S0567739476001873.
• [16] C. Kerl, J. Sturm, and D. Cremers, “Robust odometry estimation for RGB-D cameras”. In: 2013 IEEE International Conference on Robotics and Automation, 2013, 3748–3754, 10.1109/ICRA.2013.6631104.
• [17] A. Kostusiak and P. Skrzypczyński, “Populationbased methods for optimization of parameters in a rgb-d visual odometry system (in Polish: Optymalizacja parametrów systemu odometrii wizyjnej rgb-d metodami populacyjnymi)”, Prace Naukowe Politechniki Warszawskiej. Elektronika, vol.196, 2018, 461–470.
• [18] A. Kostusiak, “The Comparison of Keypoint Detectors and Descriptors for Registration of RGBD Data”. In: R. Szewczyk, C. Zieliński, and M. Kaliczyń ska, eds., Challenges in Automation, Robotics and Measurement Techniques, 2016, 609–622, 10.1007/978-3-319-29357-8_53.
• [19] A. Kostusiak, “Frame-to-Frame Visual Odometry: The Importance of Local Transformations”. In: M. Kurzynski, M. Wozniak, and R. Burduk, eds., Proceedings of the 10th International Conference on Computer Recognition Systems CORES 2017, 2018, 357–366, 10.1007/978-3-319-59162-9_37.
• [20] A. Kostusiak, M. Nowicki, and P. Skrzypczyński, “On the Application of RGB-D SLAM Systems for Practical Localization of the Mobile Robots”, Journal of Automation, Mobile Robotics and Intelligent Systems, vol. 11, no. 2, 2017, 57–66, 10.14313/JAMRIS_2-2017/17.
• [21] M. Kraft, M. Nowicki, A. Schmidt, M. Fularz, and P. Skrzypczyński, “Toward evaluation of visual navigation algorithms on RGB-D data from the first- and second-generation Kinect”, Machine Vision and Applications, vol. 28, no. 1, 2017, 61–74,10.1007/s00138-016-0802-6.
• [22] S.-K. Oh, H.-J. Jang, and W. Pedrycz, “A comparative experimental study of type-1/type-2 fuzzy cascade controller based on genetic algorithms and particle swarm optimization”, Expert Systems with Applications, vol. 38, no. 9, 2011, 11217–11229, 10.1016/j.eswa.2011.02.169.
• [23] D. Scaramuzza and F. Fraundorfer, “Visual Odometry: Part I the First 30 Years and Fundamentals”,IEEE Robotics Automation Magazine, vol. 18, no. 4, 2011, 80–92, 10.1109/MRA.2011.943233.
• [24] P. Skrzypczyński, “Mobile Robot Localization: Where We Are and What Are the Challenges?”. In: R. Szewczyk, C. Zieliński, and M. Kaliczyńska, eds., Automation 2017, 2017, 249–267, 10.1007/978-3-319-54042-9_23.
• [25] J. Sturm, W. Burgard, and D. A. Cremers, “Evaluating Egomotion and Structure-from-Motion Approaches Using the TUM RGB-D Benchmark”. In: Proc. of the Workshop on Color-Depth Camera Fusion in Robotics at the IEEE/RJS International Conference on Intelligent Robot Systems (IROS), 2012.
• [26] J. Wietrzykowski and P. Skrzypczyń ski, “PlaneLoc: Probabilistic global localization in 3-D using local planar features”, Robotics and Autonomous Systems, vol. 113, 2019, 160–173, 10.1016/j.robot.2019.01.008.
• [27] Z. Xinchao, “A perturbed particle swarm algorithm for numerical optimization”, Applied Soft Computing, vol. 10, no. 1, 2010, 119–124, 10.1016/j.asoc.2009.06.010.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).