Generic Obstacle Detection for Mobile Devices Using a Dynamic Intermediate Representation

  • Radu Danescu
  • Andra Petrovai
  • Razvan Itu
  • Sergiu Nedevschi
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 427)


Obstacles are environment elements that need to be detected reliably and accurately. While active sensors and stereovision have the advantage of obtaining 3D data directly, monocular vision is easy to set up, and can benefit from the increasing computational power of smart mobile devices. Several driving assistance application are available for mobile devices, but they are mostly targeted for simple scenarios and a limited range of obstacle shapes and poses. This paper presents a technique for generic, shape independent real-time obstacle detection for mobile devices, based on a dynamic, free form 3D representation of the environment: the particle based occupancy grid. Monocular vision is used to update the occupancy grid, and the occupancy grid tracked cells are used for extracting the obstacles as cuboids having position, size, orientation and speed. The easy to set up system is able to reliably detect most obstacles in urban traffic, and its measurement accuracy is comparable to a stereovision system.


Obstacle detection Occupancy grid Monocular vision Advanced driving assistance system Mobile device 



Research supported by grants of the Romanian Authority for Scientific Research, projects PN-II-PCE-2011-3-1086 (MultiSens) and PN-II-PCCA-2011-3.2-0742 (SmartCoDrive).


  1. 1.
    iOnRoad Augmented Driving Pro.
  2. 2.
  3. 3.
  4. 4.
    Sivaraman, S., Trivedi, M.M.: Looking at vehicles on the road: a survey of vision-based vehicle detection, tracking, and behavior analysis. IEEE Trans. Intell. Transp. 14, 1773–1794 (2013)CrossRefGoogle Scholar
  5. 5.
    Petrovai, A., Costea, A., Oniga, F., Nedevschi, S.: Obstacle detection using stereovision for Android-based mobile devices. In: IEEE 10th International Conference on Intelligent Computer Communication and Processing, pp. 141–147. IEEE Press (2014)Google Scholar
  6. 6.
    Haltakov, V., Belzner, H., Ilic, S.: Scene understanding from a moving camera for object detection and free space estimation. In: IEEE Intelligent Vehicles Symposium, pp. 105–110. IEEE Press (2012)Google Scholar
  7. 7.
    Wybo, S., Tsishkou, D., Vestri, C., Abad, F., Bougnoux, S., Bendahan, R.: Monocular vision obstacles detection for autonomous navigation. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4190–4196. IEEE Press (2008)Google Scholar
  8. 8.
    Reisman, P., Mano, O., Avidan, S., Shashua, A.: Crowd detection in video sequences. In: IEEE Intelligent Vehicles Symposium, pp. 66–71. IEEE Press (2004)Google Scholar
  9. 9.
    Zhang, X., Jiang, P., Wang, F.: Overtaking vehicle detection using a spatio-temporal CRF. In: IEEE Intelligent Vehicles Symposium, pp. 338–343. IEEE Press (2014)Google Scholar
  10. 10.
    Graefe, V., Efenberg, W.: A novel approach for the detection of vehicles on freeways by real-time vision. In: IEEE Intelligent Vehicles Symposium, pp. 363–368 (1996)Google Scholar
  11. 11.
    Lim, K.H., Ang, L.M., Seng, K.P., Chin, S.W.: Lane-vehicle detection and tracking. In: International Multi Conference of Engineers and Computer Scientists, pp. 1124–1129 (2009)Google Scholar
  12. 12.
    Sivaraman, S., Trivedi, M.M.: A general active-learning framework for on-road vehicle recognition and tracking. IEEE Trans. Intell. Transp. 11, 267–276 (2010)CrossRefGoogle Scholar
  13. 13.
    Arrospide, J., Salgado, L., Marinas, J.: HOG-like gradient-based descriptor for visual vehicle detection. In: IEEE Intelligent Vehicles Symposium, pp. 223–228. IEEE Press (2012)Google Scholar
  14. 14.
    Bertozzi, M., Broggi, A.: GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection. IEEE Trans. Image Process. 7, 62–81 (1998)CrossRefGoogle Scholar
  15. 15.
    Tuohy, S., O’Cualain, D., Jones, E., Glavin, M.: Distance determination for an automobile environment using inverse perspective mapping in OpenCV. In: IET Signal and Systems Conference, pp. 100–105. IET (2010)Google Scholar
  16. 16.
    Itu, R., Danescu, R.: An efficient obstacle awareness application for android mobile devices. In: IEEE 10th International Conference on Intelligent Computer Communication and Processing, pp. 157–163. IEEE Press (2014)Google Scholar
  17. 17.
    Danescu, R., Oniga, F., Nedevschi, S.: Modeling and tracking the driving environment with a particle-based occupancy grid. IEEE Trans. Intell. Transp. 12, 1331–1342 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Radu Danescu
    • 1
  • Andra Petrovai
    • 1
  • Razvan Itu
    • 1
  • Sergiu Nedevschi
    • 1
  1. 1.Computer Science DepartmentTechnical University of Cluj-NapocaCluj-NapocaRomania

Personalised recommendations