A Graphical Model for Rapid Obstacle Image-Map Estimation from Unmanned Surface Vehicles

  • Matej KristanEmail author
  • Janez Perš
  • Vildana Sulič
  • Stanislav Kovačič
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9004)


Obstacle detection plays an important role in unmanned surface vehicles (USV). Continuous detection from images taken onboard the vessel poses a particular challenge due to the diversity of the environment and the obstacle appearance. An obstacle may be a floating piece of wood, a scuba diver, a pier, or some other part of a shoreline. In this paper we tackle this problem by proposing a new graphical model that affords a fast and continuous obstacle image-map estimation from a single video stream captured onboard a USV. The model accounts for the semantic structure of marine environment as observed from USV by imposing weak structural constraints. A Markov random field framework is adopted and a highly efficient algorithm for simultaneous optimization of model parameters and segmentation mask estimation is derived. Our approach does not require computationally intensive extraction of texture features and runs faster than real-time. We also present a new, challenging, dataset for segmentation and obstacle detection in marine environments, which is the largest annotated dataset of its kind. Results on this dataset show that our model compares favorably in accuracy to the related approaches, requiring a fraction of computational effort.


Markov Random Field Obstacle Detection Dynamic Obstacle Unmanned Ground Vehicle Water Edge 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This work was supported in part by the Slovenian research agency programs P2-0214, P2-0094, and projects J2-4284, J2-3607, J2-2221. We also thank HarphaSea d.o.o. for their hardware used to capture the dataset.


  1. 1.
    Heidarsson, H., Sukhatme, G.: Obstacle detection from overhead imagery using self-supervised learning for autonomous surface vehicles. In: International Conference on Intelligent Robots and Systems, pp. 3160–3165 (2011)Google Scholar
  2. 2.
    Rasmussen, C., Lu, Y., Kocamaz, M.K.: Trail following with omnidirectional vision. In: International Conference on Intelligent Robots and Systems, pp. 829–836 (2010)Google Scholar
  3. 3.
    Montemerlo, M., Thrun, S., Dahlkamp, H., Stavens, D.: Winning the darpa grand challenge with an ai robot. In: AAAI National Conference on Artificial Intelligence, pp. 17–20 (2006)Google Scholar
  4. 4.
    Dahlkamp, H., Kaehler, A., Stavens, D., Thrun, S., Bradski, G.: Self-supervised monocular road detection in desert terrain. In: RSS, Philadelphia, USA (2006)Google Scholar
  5. 5.
    Ettinger, S.M., Nechyba, M.C., Ifju, P.G., Waszak, M.: Vision-guided flight stability and control for micro air vehicles. Adv. Rob. 17, 617–640 (2003)CrossRefGoogle Scholar
  6. 6.
    Lu, Y., Rasmussen, C.: Simplified markov random fields for efficient semantic labeling of 3D point clouds. In: IROS, pp. 2690–2697 (2012)Google Scholar
  7. 7.
    Scherer, S., Rehder, J., Achar, S., Cover, H., Chambers, A., Nuske, S., Singh, S.: River mapping from a flying robot: state estimation, river detection, and obstacle mapping. Auton. Rob. 33, 189–214 (2012)CrossRefGoogle Scholar
  8. 8.
    Onunka, C., Bright, G.: Autonomous marine craft navigation: on the study of radar obstacle detection. In: ICARCV, pp. 567–572 (2010)Google Scholar
  9. 9.
    Heidarsson, H., Sukhatme, G.: Obstacle detection and avoidance for an autonomous surface vehicle using a profiling sonar. In: ICRA, pp. 731–736 (2011)Google Scholar
  10. 10.
    Rankin, A., Matthies, L.: Daytime water detection based on color variation. In: International Conference on Intelligent Robots and Systems, pp. 215–221 (2010)Google Scholar
  11. 11.
    Elkins, L., Sellers, D., Reynolds, W.M.: The autonomous maritime navigation (amn) project: field tests, autonomous and cooperative behaviors, data fusion, sensors, and vehicles. J. Field Rob. 27, 790–818 (2010)CrossRefGoogle Scholar
  12. 12.
    Hong, T.H., Rasmussen, C., Chang, T., Shneier, M.: Fusing ladar and color image information for mobile robot feature detection and tracking. In: IAS, pp. 124–133 (2002)Google Scholar
  13. 13.
    Santana, P., Mendica, R., Barata, J.: Water detection with segmentation guided dynamic texture recognition. In: IEEE Robotics and Biomimetics (ROBIO), pp. 1836–1841 (2012)Google Scholar
  14. 14.
    Socek, D., Culibrk, D., Marques, O., Kalva, H., Furht, B.: A hybrid color-based foreground object detection method for automated marine surveillance. In: Blanc-Talon, J., Philips, W., Popescu, D.C., Scheunders, P. (eds.) ACIVS 2005. LNCS, vol. 3708, pp. 340–347. Springer, Heidelberg (2005) CrossRefGoogle Scholar
  15. 15.
    Fefilatyev, S., Goldgof, D.: Detection and tracking of marine vehicles in video. In: Proceedings of the International Conference on Pattern Recognition, pp. 1–4 (2008)Google Scholar
  16. 16.
    Wang, H., Wei, Z., Wang, S., Ow, C., Ho, K., Feng, B.: A vision-based obstacle detection system for unmanned surface vehicle. In: International Conference on Robotics, Automation and Mechatronics, pp. 364–369 (2011)Google Scholar
  17. 17.
    Huntsberger, T., Aghazarian, H., Howard, A., Trotz, D.C.: Stereo visionbased navigation for autonomous surface vessels. JFR 28, 3–18 (2011)Google Scholar
  18. 18.
    Khan, S., Shah, M.: Object based segmentation of video using color, motion and spatial information. In: Computer Vision Pattern Recognition, vol. 2, pp. 746–751 (2001)Google Scholar
  19. 19.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59, 167–181 (2004)CrossRefGoogle Scholar
  20. 20.
    Besag, J.: On the statistical analysis of dirty pictures. J. Roy. Stat. Soc. 48, 259–302 (1986)zbMATHMathSciNetGoogle Scholar
  21. 21.
    Boykov, Y., Funka-Lea, G.: Graph cuts and efficient ND image segmentation. Int. J. Comput. Vis. 70, 109–131 (2006)CrossRefGoogle Scholar
  22. 22.
    Wojek, C., Schiele, B.: A dynamic conditional random field model for joint labeling of object and scene classes. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 733–747. Springer, Heidelberg (2008) CrossRefGoogle Scholar
  23. 23.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the International Conference on Machine Learning, pp. 282–289 (2001)Google Scholar
  24. 24.
    Kontschieder, P., Bulo, S., Bischof, H., Pelillo, M.: Structured class-labels in random forests for semantic image labelling. In: ICCV, pp. 2190–2197 (2011)Google Scholar
  25. 25.
    Alpert., S.Galun, M., Basri, R., Brandt, A.: Image segmentation by probabilistic bottom-up aggregation and cue integration. In: CVPR, pp. 1–8 (2012)Google Scholar
  26. 26.
    Ren, X., Malik, J.: Learning a classification model for segmentation. In: ICCV, pp. 10–17 (2003)Google Scholar
  27. 27.
    Li, Z., Wu, X.M., Chang, S.F.: Segmentation using superpixels: a bipartite graph partitioning approach. In: CVPR, pp. 789–796 (2012)Google Scholar
  28. 28.
    Diplaros, A., Vlassis, N., Gevers, T.: A spatially constrained generative model and an EM algorithm for image segmentation. IEEETNN 18, 798–808 (2007)Google Scholar
  29. 29.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88, 303–338 (2010)CrossRefGoogle Scholar
  30. 30.
    Rother, C., Kolmogorov, V., Blake, A.: GrabCut: interactive foreground extraction using iterated graph cuts. In: SIGGRAPH, vol. 23, pp. 309–314 (2004)Google Scholar
  31. 31.
    Bagon, S.: Matlab wrapper for graph cut (2006)Google Scholar
  32. 32.
    Felzenszwalb, P.F., Veksler, O.: Tiered scene labeling with dynamic programming. In: CVPR, pp. 3097–3104 (2010)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Matej Kristan
    • 1
    • 2
    Email author
  • Janez Perš
    • 1
  • Vildana Sulič
    • 1
  • Stanislav Kovačič
    • 1
  1. 1.Faculty of Computer and Information ScienceUniversity of LjubljanaSloveniaLjubljana
  2. 2.Faculty of Electrical EngineeringUniversity of LjubljanaSloveniaLjubljana

Personalised recommendations