Multi-objective Optimization for Characterization of Optical Flow Methods

Jose Delpiano, Luis Pizarro, Rodrigo Verschae, Javier Ruiz-del-Solar


Optical flow methods are among the most accurate techniques for estimating displacement and velocity fields in a number of applications that range from neuroscience to robotics. The performance of any optical flow method will naturally depend on the configuration of its parameters. Beyond the standard practice of manual (ad-hoc) selection of parameters for a specific application, in this article we propose a framework for automatic parameter setting that allows searching for an approximated Pareto-optimal set of configurations in the whole parameter space. This final Pareto front characterizes each specific method, enabling proper method comparison. We define two performance criteria, namely the accuracy and speed of the optical flow methods.


  1. Bäck, T. (1996). Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms. Oxford University Press.
  2. Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M., and Szeliski, R. (2011). A database and evaluation methodology for optical flow. International Journal of Computer Vision, 92:1-31.
  3. Barron, J., Fleet, D., and Beauchemin, S. (1994). Performance of optical flow techniques. International Journal of Computer Vision, 12(1):43-77.
  4. Benlian, X. and Zhiquan, W. (2007). A multi-objectiveACO-based data association method for bearings-only multi-target tracking. Communications in Nonlinear Science and Numerical Simulation, 12(8):1360-1369.
  5. Briggs, W., Henson, V., and McCormick, S. (2000). A Multigrid Tutorial. Society for Industrial and Applied Mathematics.
  6. Bruhn, A. (2006). Variational Optic Flow Computation, Accurate Modelling and Efficient Numerics. Ph.D. dissertation, Saarland University.
  7. Bruhn, A., Weickert, J., Feddern, C., Kohlberger, T., and Schnörr, C. (2005a). Variational optical flow computation in real time. IEEE Transactions on Image Processing, 14(5):608-615.
  8. Bruhn, A., Weickert, J., and Schnörr, C. (2005b). Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods. International Journal of Computer Vision, 61(3):1-21.
  9. Changming and Sun (2002). Fast optical flow using 3D shortest path techniques. Image and Vision Computing, 20(13-14):981-991.
  10. Chittka, L., Dyer, A. G., Bock, F., and Dornhaus, A. (2003). Psychophysics: Bees trade off foraging speed for accuracy. Nature, 424(6947):388.
  11. Deb, K. and Kumar, A. (1995). Real-coded genetic algorithms with simulated binary crossover: Studies on multimodel and multiobjective problems. Complex Systems, 9(6):431-454.
  12. Deb, K., Pratap, A., Agarwal, S., and Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation, 6(2):182-197.
  13. Everingham, M., Muller, H., and Thomas, B. (2006). Evaluating image segmentation algorithms using the pareto front. In Heyden, A., Sparr, G., Nielsen, M., and Johansen, P., editors, Computer Vision - ECCV 2002, volume 2353 of Lecture Notes in Computer Science, pages 255-259. Springer Berlin / Heidelberg.
  14. Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley.
  15. Heas, P., Herzet, C., and Memin, E. (2012). Bayesian inference of models and hyperparameters for robust optical-flow estimation. Image Processing, IEEE Transactions on, 21(4):1437-1451.
  16. Horn, B. K. and Schunck, B. G. (1981). Determining optical flow. Artificial Intelligence, 17:185-203.
  17. Krajsek, K. and Mester, R. (2006). A maximum likelihood estimator for choosing the regularization parameters in global optical flow methods. In Image Processing, 2006 IEEE International Conference on, pages 1081- 1084.
  18. Li, Y. and Huttenlocher, D. (2008). Learning for optical flow using stochastic optimization. In Forsyth, D., Torr, P., and Zisserman, A., editors, European Conference on Computer Vision - ECCV 2008, volume 5303 of Lecture Notes in Computer Science, pages 379-391. Springer Berlin / Heidelberg.
  19. Salmen, J., Caup, L., and Igel, C. (2011). Real-time estimation of optical flow based on optimized Haar wavelet features. In Evolutionary MultiCriterion Optimization, pages 448-461. Springer.
  20. Verschae, R., Ruiz-del-Solar, J., Köppen, M., and Garcia, R. V. (2005). Improvement of a face detection system by evolutionary multi-objective optimization. In Proceedings of the Fifth International Conference on Hybrid Intelligent Systems, pages 361-366, Washington, DC, USA. IEEE Computer Society.
  21. Vite-Silva, I., Cruz-Cortés, N., Toscano-Pulido, G., and Fraga, L. G. (2007). Optimal triangulation in 3D computer vision using a multi-objective evolutionary algorithm. In Proceedings of the EvoWorkshops 2007: Applications of Evolutionary Computing, pages 330- 339, Berlin, Heidelberg. Springer-Verlag.

Paper Citation

in Harvard Style

Delpiano J., Pizarro L., Verschae R. and Ruiz-del-Solar J. (2014). Multi-objective Optimization for Characterization of Optical Flow Methods . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 566-573. DOI: 10.5220/0004736305660573

in Bibtex Style

author={Jose Delpiano and Luis Pizarro and Rodrigo Verschae and Javier Ruiz-del-Solar},
title={Multi-objective Optimization for Characterization of Optical Flow Methods},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},

in EndNote Style

JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Multi-objective Optimization for Characterization of Optical Flow Methods
SN - 978-989-758-004-8
AU - Delpiano J.
AU - Pizarro L.
AU - Verschae R.
AU - Ruiz-del-Solar J.
PY - 2014
SP - 566
EP - 573
DO - 10.5220/0004736305660573