Automated tracking and real time following of moving person for robotics applications

• Autorzy: Patoliya Jignesh J. , Mewada Hiren K.

Identyfikatory

DOI

10.14313/JAMRIS/4-2019/35

• Języki publikacji: EN

Abstrakty

EN

Presently the interaction of robots with human plays an important role in various social applications. Reliable tracking is an important aspect for the social robots where robots need to follow the moving person. This paper proposes the implementation of automated tracking and real time following algorithm for robotic automation. Occlusion and identity retention are the major challenges in the tracking process. Hence, a feature set based identity retention algorithm is used and integrated with robot operating system. The tracking algorithm is implemented using robot operating system in Linux and using OpenCV. The tracking algorithm achieved 85% accuracy and 72.30% precision. Further analysis of tracking algorithm corresponds to the integration of ROS and OpenCV is presented. The analysis of tracking algorithm concludes that ROS linking required 0.64% more time in comparison with simple OpenCV code based tracking algorithm.

Słowa kluczowe

EN

visual tracking; robot operating system; identity retention; Gaussian Mixture Model

• 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. 4
• Strony: 31--37
• Opis fizyczny: Bibliogr. 17 poz., rys.

Twórcy

autor

Patoliya Jignesh J.

• Electronics and Communication Engineering Department, Chandubhai S Patel Institute of Technology, Charotar University of Science and Technology, Post Changa, Gujarat, India

autor

Mewada Hiren K.

• Assistant Research Professor, Electrical Engineering Department, Prince Mohammad Bin Fahd University, Kingdom of Saudi Arabia

Bibliografia

• [1] M. Munaro, C. Lewis, D. Chambers, P. Hvass, E. Menegatti, “RGB-D Human Detection and Tracking for Industrial Environments”. In: Intelligent Autonomous Systems 13, 2016, 1655–1668 DOI: 10.1007/978-3-319-08338-4_119.
• [2] D. Reynolds, “Gaussian Mixture Models”. In: Encyclopedia of Biometrics, 2009, 659–663.
• [3] D. Israni, H. Mewada, “Identity Retention of Multiple Objects under Extreme Occlusion Scenarios using Feature Descriptors”, Journal of Communications Software and Systems, vol. 14, no. 4, 2018, 290–301 DOI: 10.24138/jcomss.v14i4.541.
• [4] H. K. Mewada, A. V. Patel, K. K. Mahant, “Concurrent design of active contour for image segmentation using Zynq ZC702”, Computers & Electrical Engineering, vol. 72, 2018, 631–643 DOI: 10.1016/j.compeleceng.2018.01.024.
• [5] W. Niu, J. Long, D. Han, Y.-F. Wang, “Human activity detection and recognition for video surveillance”. In: 2004 IEEE International Conference on Multimedia and Expo (ICME), vol. 1, 2004, 719–722 DOI: 10.1109/ICME.2004.1394293.
• [6] O. Javed, M. Shah, “Tracking and Object Classification for Automated Surveillance”. In: Computer Vision — ECCV 2002, 2002, 343–357 DOI: 10.1007/3-540-47979-1_23.
• [7] R. Diaz, J. Manuel, Model-based object tracking with an infrared stereo camera, Master Thesis, Örebro University, School of Science and Technology, 2015.
• [8] A. Bolotnikova, Articulated Object Tracking from Visual Sensory Data for Robotic Manipulation Master Thesis, University of Tartu, Faculty of Science and Technology, Institute of Computer Science, 2017.
• [9] K. L. Besseghieur, R. Trębiński, W. Kaczmarek, J. Panasiuk, “Trajectory tracking control for a nonholonomic mobile robot under ROS”, Journal of Physics: Conference Series, vol. 1016, 2018 DOI: 10.1088/1742-6596/1016/1/012008.
• [10] Y. Wei, Z. Lin, “Vision-based Tracking by a Quadrotor on ROS”, IFAC-PapersOnLine, vol. 50, no. 1, 2017, 11447–11452 DOI: 10.1016/j.ifacol.2017.08.1814.
• [11] G. Priyandoko, C. K. Wei, M. S. H. Achmad, “Human Following on ROS Framework a Mobile Robot”, SINERGI, vol. 22, no. 2, 2018, 77–82 DOI: 10.22441/sinergi.2018.2.002.
• [12] R. Collins, Y. Liu, M. Leordeanu, “Online selection of discriminative tracking features”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 10, 2005, 1631–1643 DOI: 10.1109/TPAMI.2005.205.
• [13] O. Javed, M. Shah, “Tracking and Object Classification for Automated Surveillance”. In: European Conference on Computer Vision — ECCV 2002, 2002, 343–357 DOI: 10.1007/3-540-47979-1_23.
• [14] B. Y. Lee, L. H. Liew, W. S. Cheah, Y. C. Wang, “Occlusion Handling in Videos Object Tracking: A Survey”, IOP Conference Series: Earth and Environmental Science, vol. 18, 2014 DOI: 10.1088/1755-1315/18/1/012097.
• [15] “PETS 2009 Benchmark Data”. Binghamton University – State University of New York, http://cs.binghamton.edu/~mrldata/pets2009.html.Accessed on: 2020-02-20.
• [16] B. Benfold, I. Reid, “Stable multi-target tracking in real-time surveillance video”. In: Computer Vision Pattern Recognition CVPR 2011, 2011, 3457–3464 DOI: 10.1109/CVPR.2011.5995667.
• [17] “Expectation Maximization algorithm to obtain Gaussian mixture models for ROS”. Robotics with ROS, https://ros-developer.com/2017/11/16/expectation-maximization-algorithm-obtaingaussian-mixture-models-ros. Accessed on: 2020-02-20.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).