Abstract
The research considers the implementation of simultaneous localization and mapping algorithm based on the FastSLAM technique and specific problems that are typical for the RGB-D sensor-based solutions. An improvement of the classical FastSLAM algorithm has been obtained by replacing the method of landmarks’ observations filtering with unscented Kalman filters. Instead of linearizing, the nonlinear models through the first order Taylor series expansion at the mean of the landmark state were applied. The proposed algorithm computes a more accurate mean and uncertainty of the landmarks, which are moving nonlinearly. Various data preprocessing issues are discussed, such as the method of calibration of Kinect-like cameras, depth map restoration using a modified interpolation technique, and filtering the noise in the RGB images for more accurate detection of key features. Additionally, the chapter presents an improved resampling algorithm for the particle filtering through the adaptive thresholding based on the data of the effective particle number evolution. The proposed algorithm runs in real time and shows good accuracy and robustness in comparison with other modern SLAM systems using all the advantages and disadvantages of the RGB-D sensors.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Dutta, T.: Evaluation of the Kinect sensor for 3-D kinematic measurement in the workplace. Appl. Ergon. 43(4), 645–649 (2012)
Karlsson, N., di Bernardo E., Ostrowski, J., Goncalves, L., Pirjanian, P., Munich, M.: The vSLAM algorithm for robust localization and mapping. In: International Conference on Robotics and Automation (ICRA’2005), pp. 18–22 (2005)
Aulinas, J.: The SLAM problem: a survey. In: 2008 Conference on Artificial Intelligence Research & Development, pp. 363–371 (2015)
Zakaria, A.M., Said, A.M.: 3D reconstruction of a scene from multiple uncalibrated images using close range photogrammetry. In: International Symposium on Information Technology (ITSim’2010), pp. 1–5 (2010)
Tomasi, C., Kanade, T.: Detection and tracking of point features. Tech Report CMU-CS-91-132, Carnegie-Melon University (1992)
Technical description of Kinect calibration. Available from: http://wiki.ros.org/kinect_calibration/technical. Accessed 3 July 2017
Smisek, J., Jancosek, M., Pajdla, T.: 3D with kinect. In: Fossati, A., Gall, J., Grabner, H., Ren, X., Konolige, K. (eds.) Consumer Depth Cameras for Computer Vision, Advances in Computer Vision and Pattern Recognition, pp. 3–25. Springer, London (2013)
Herrera, C., Kannala, J., Heikkila, J.: Joint depth and color camera calibration with distortion correction. IEEE Trans. Pattern Anal. Mach. Intell. 34(10), 2058–2064 (2012)
Wagner, D., Mulloni, A., Langlotz, T., Schmalstieg, D.: Real-time panoramic mapping and tracking on mobile phones. In: IEEE Virtual Reality Conference (VR’2010), pp. 211–218 (2010)
Einicke, G.A., White, L.B.: Robust extended Kalman filtering. IEEE Trans. Sig. Process. 47(9), 2596–2599 (1999)
Koller, D., Montemerlo, M., Thrun, S., Wegbreit, B.: FastSLAM: A factored solution to the simultaneous localization and mapping problem. In: 18th National Conference on Artificial intelligence (AAAI’2002), pp. 593–598 (2002)
Murphy, K.: Bayesian map learning in dynamic environments. In: 12th Int Conf Neural Information Processing Systems (NIPS’1999), pp. 1015–1021 (1999)
Doucet, A., Freitas, N., Murphy, K., Russell, S.: Rao-Blackwellised particle filtering for dynamic Bayesian networks. In: 16th Conference on Uncertainty in Artificial Intelligence (UAI’2000), pp. 176–183 (2000)
Murphy, K., Russell, S.: Rao-blackwellized particle filtering for dynamic Bayesian networks. In: Doucet, A., de Freitas, N., Gordon, N. (eds.) Sequential MonteCarlo Methods in Practice, pp. 499–515. Springer Science+Business Media, New York (2001)
Szeliski, R.: Computer Vision: Algorithms and Applications. Springer, London (2010)
Sonka, M., Hlavac, V., Boyle, R.: Image Processing, Analysis and Machine Vision, 2nd edn. Springer Science+Business Media, London
Barnich, O., Droogenbroeck, M.: A universal background subtraction algorithm for video sequences. IEEE Trans. Image Process. 20(6), 1709–1724 (2011)
Isard, M., Blake, A.: Condensation—conditional density propagation for visual tracking. Int. J. Comput. Vis. 29(1), 5–28 (1998)
Prozorov, A., Priorov, A.: Three-dimensional reconstruction of a scene with the use of monocular vision. Meas. Tech. 57(10), 1137–1143 (2015)
RGB-D SLAM dataset and benchmark. Available from: https://vision.in.tum.de/data/datasets/rgbd-dataset. Accessed 3 July 2017
PUT Kinect 1 & Kinect 2 data set. Available from: http://lrm.put.poznan.pl/putkk/. Accessed 3 July 2017
The Malaga Stereo and Laser Urban Data Set. Available from: http://www.mrpt.org/MalagaUrbanDataset. Accessed 3 July 2017
Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D SLAM systems. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’2012), pp. 573–580 (2012)
Kuemmerle, R., Steder, B., Dornhege, C., Ruhnke, M., Grisetti, G., Stachniss, C., Kleiner, A.: On measuring the accuracy of SLAM algorithms. J Auton. Rob. 27(4), 387–407 (2009)
Oxford Robotical Dataset. Available from: http://robotcar-dataset.robots.ox.ac.uk/. Accessed 3 July 2017
Kurt-Yavuz, Z., Yavuz, S.: A comparison of EKF, UKF, FastSLAM2.0, and UKF-based FastSLAM algorithms. In: IEEE 16th International Conference on Intelligent Engineering Systems (INES’2012), pp. 37–43 (2012)
Wan, E.A., Van Der Merwe, R.: The unscented Kalman filter for nonlinear estimation. In: IEEE Adaptive Systems for Signal Processing, Communications, and Control Symposium (AS-SPCC’2000), pp. 153–158 (2000)
Simon, J., Jeffrey, U.: Unscented filtering and nonlinear estimation. Proc. IEEE 92(3), 401–422 (2004)
Wan, E.A., Van der Merwe, R.: The square-root unscented Kalman filter for state and parameter-estimation. In: IEEE International Conference on Acoustics, Speech, and Signal (ICASSP’2001), pp. 3461–3464 (2001)
Camera Calibration Toolbox for Matlab. Available from: http://www.vision.caltech.edu/bouguetj/calib_doc. Accessed 3 July 2017
Wang, H.M., Huang, C.H., Yang, J.F.: Depth maps interpolation from existing pairs of keyframes and depth maps for 3D video generation. In: IEEE International Symposium on Circuits and Systems (ISCAS’2010), pp. 3248–3251 (2010)
Criminisi, A., Perez, P., Toyama, K.: Region filling and object removal by exemplar-based inpainting. IEEE Trans. Image Process. 13(9), 1200–1212 (2004)
Canny, J.A.: Computational approach to edge detection. IEEE Trans Pattern Anal. Mach. Intell. (PAMI) 8(6), 679–698 (1988)
Blanco, J.L.: Contributions to localization, mapping and navigation in mobile robotics. Ph.D. Thesis, Universidad de Malaga
Douc, R., Cappe, O., Moulines, E.: Comparison of resampling schemes for particle filtering. In: 4th International Symposium on Image and Signal Processing and Analysis (ISPA’2005), pp. 64–69 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this chapter
Cite this chapter
Prozorov, A., Priorov, A., Khryashchev, V. (2018). Unscented RGB-D SLAM in Indoor Environment. In: Favorskaya, M., Jain, L. (eds) Computer Vision in Control Systems-4. Intelligent Systems Reference Library, vol 136. Springer, Cham. https://doi.org/10.1007/978-3-319-67994-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-67994-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67993-8
Online ISBN: 978-3-319-67994-5
eBook Packages: EngineeringEngineering (R0)