Advertisement

A SSD – OCR Approach for Real-Time Active Car Tracking on Quadrotors

  • Luiz Gustavo Miranda Pinto
  • Félix Mora-Camino
  • Pedro Lucas de Brito
  • Alexandre C. Brandão RamosEmail author
  • Hildebrando F. Castro Filho
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 800)

Abstract

This paper has the goal of presenting a deep neural network algorithm for real-time object tracking called Single Shot MultiBox Detector – SSD as a source of detection, in combination with an Optical Character Recognition – OCR algorithm, both serving as assistance for determining the right position and speed for a quadrotor during an active car track mission. During the experiments, a Tello DJI drone equipped with a frontal camera and a distance sensor were used to receive height measurements. The whole algorithm was implemented in Python programming language as a combination of Tello SDK for software development, Hanyazou’s TelloPy package for video streaming, an OCR algorithm implemented with digital image processing and an SSD system created with TensorFlow. The frontal camera was used as a real-time streaming source for the SSD and OCR systems, being both coordinated by TelloPy, which made it possible to achieve both position and speed control using Tello SDK. The distance sensor under the drone helped to avoid collisions underneath and refine the positioning. Outdoor tests were executed to check the drone’s behavior during the active car track mission. Besides the project is still in its initial stage, satisfactory results were collected and will be used for further analysis and improvements.

Keywords

Car track Drones Image processing Neuro networks 

Notes

Aknowledgement

The authors would like to thank the funding institution FAPEMIG, where without its resources this project wouldn’t be possible.

References

  1. 1.
    Tello: Ryze Robotics. Available in https://www.ryzerobotics.com/tello
  2. 2.
    Amit, Y., Felzenszwalb, P.: Object detection. In: Computer Vision, A Reference Guide. Springer, New York (2014)Google Scholar
  3. 3.
    Anbarjafari, G.: Introduction to image processing. In: Digital Image Processing. University of Tartu, Tartu (2014)Google Scholar
  4. 4.
    Namee, B.M.: Digital Image Processing. Introdution. Dublin Institute of Technology, School of Computer Science, Dublin (2018)Google Scholar
  5. 5.
    Barták, R., Vyškovský, A.: Any object tracking and following by a flying drone. 2015 Fourteenth Mexican International Conference on Artificial Intelligence (2015)Google Scholar
  6. 6.
    Patil, K.: Object Tracking Using Quadcopter. Department of Electrical Engineering, Indian Institute of Technology, Mumbai (2017)Google Scholar
  7. 7.
    Tavarez, D.T., Caurin, G.A.P., Gonzaga, A.: Tesseract OCR: A Case Study for License Plate Recognition in Brazil. Laboratório de Mecatrônica, Departamento de Engenharia Mecânica, EESC-USP (2003)Google Scholar
  8. 8.
    Qadri, M.T., Asif, M.: Automatic number plate recognition system for vehicle identification using optical character recognition. 2009 International Conference on Education Technology and Computer (2009)Google Scholar
  9. 9.
    Liu, W., et al.: SSD: Single Shot MultiBox Detector. The 14th European Conference on Computer Vision, Amsterdam, 29 Dec 2016Google Scholar
  10. 10.
    Hui, J.: Choosing default boundary boxex. In: SSD object detection - single shot MultiBox detector for real-time processing. Deep Learning. Available at: https://medium.com/@jonathan_hui/ssd-object-detection-single-shot-multibox-detector-for-real-time-processing-9bd8deac0e06 (2018)
  11. 11.
    Frossard, D.: VGG in TensorFlow: Model and Pre-trained Parameters for VGG16 in TensorFlow. Department of Computer Science, University of Toronto, Toronto, ON (2016)Google Scholar
  12. 12.
    Eikvil, L.: OCR: Optical Character Recognition. Department of Statistical Analysis, Image Analysis and Pattern Recognition (SAMBA). Norsk Regnesentral Norwegian Computing Center, Oslo (1993)Google Scholar
  13. 13.
    Islam, N., Islam, Z., Noor, N.: A survey on optical character recognition system. J. Inf. Commun. Technol. 10(2), (2016)Google Scholar
  14. 14.
    Srinivasan, S., et al.: Performance Characterization and Acceleration of Optical Character Recognition on Handheld Platforms. 978-1-4244-9296-1/10/$26.00 ©2010 IEEEGoogle Scholar
  15. 15.
    Sabatino, F.: Quadrotor control: modeling, nonlinear control design, and simulation. Master’s Degree Project, KTH Electrical Engineering, Stockholm, Sweden June 2015, XR-EE-RT 2015:XXXGoogle Scholar
  16. 16.
    Luukkonen, T.: Modelling and control of quadcopter. Independent research project in applied mathematics. Aalto University School of Science, Espoo, August 22, 2011Google Scholar
  17. 17.
    Braga, R.G., da Silva, R.C., Ramos, A.C.B.: Collision avoidance based on Reynolds rules: a case study using quadrotors. 14th International Conference on Information Technology. ITNG, (2008)Google Scholar
  18. 18.
    Rize Robotics, Tello SDK 1.3.0.0.: Available in: http://www.ryzerobotics.com, 2018
  19. 19.
    Hanyazou: TelloPy: DJI Tello drone controller python package. Available in: https://github.com/hanyazou/TelloPy, (2018)
  20. 20.
    Hsu, K., Lin, Y., Chuang, Y.: Augmented multiple instance regression for inferring object contours in bounding boxes. IEEE Trans. Image Process. 23(4), (2014)Google Scholar
  21. 21.
    Krause, J., Stark, M., Deng, J., Fei-Fei, L. 3D object representations for fine-grained categorization. 4th IEEE Workshop on 3D Representation and Recognition, at ICCV 2013 (3dRR) (2013)Google Scholar
  22. 22.
    Martins, WM., Braga, R.G., Ramos, Alexandre, C.B., Camino, F.M.: A computer vision based algorithm for obstacle avoidance. In: Springer International Publishing AG (Org.). Advances in Intelligent Systems and Computing, 1st edn, pp. 569–575.-13. Springer, Las Vegas (2018), v. 738. Sydney. 8 Dec 2013Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Luiz Gustavo Miranda Pinto
    • 1
  • Félix Mora-Camino
    • 2
  • Pedro Lucas de Brito
    • 1
  • Alexandre C. Brandão Ramos
    • 1
    Email author
  • Hildebrando F. Castro Filho
    • 3
  1. 1.Institute of Mathematics and Computing, Federal University of ItajubáItajubáBrazil
  2. 2.Federal Fluminense University, Brazil ComputingRio de JaneiroBrazil
  3. 3.Aeronautical Institute of Technology, Brazil ComputingSão José dos CamposBrazil

Personalised recommendations