Multi-objective optimization for characterization of optical flow methods

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]  Étienne Mémin,et al.  Bayesian Inference of Models and Hyperparameters for Robust Optical-Flow Estimation , 2012, IEEE Transactions on Image Processing.

[2]  Jan Salmen,et al.  Real-Time Estimation of Optical Flow Based on Optimized Haar Wavelet Features , 2011, EMO.

[3]  William L. Briggs,et al.  A multigrid tutorial , 1987 .

[4]  Rudolf Mester,et al.  A Maximum Likelihood Estimator for Choosing the Regularization Parameters in Global Optical Flow Methods , 2006, 2006 International Conference on Image Processing.

[5]  Henk L. Muller,et al.  Evaluating Image Segmentation Algorithms Using the Pareto Front , 2002, ECCV.

[6]  Kalyanmoy Deb,et al.  Real-coded Genetic Algorithms with Simulated Binary Crossover: Studies on Multimodal and Multiobjective Problems , 1995, Complex Syst..

[7]  Changming Sun,et al.  Fast optical flow using 3D shortest path techniques , 2002, Image Vis. Comput..

[8]  S. McCormick,et al.  A multigrid tutorial (2nd ed.) , 2000 .

[9]  Wang Zhi-quan,et al.  A multi-objective-ACO-based data association method for bearings-only multi-target tracking , 2007 .

[10]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.

[11]  Gregorio Toscano Pulido,et al.  Optimal Triangulation in 3D Computer Vision Using a Multi-objective Evolutionary Algorithm , 2007, EvoWorkshops.

[12]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[13]  Timo Kohlberger,et al.  Universität Des Saarlandes Fachrichtung 6.1 – Mathematik Variational Optic Flow Computation in Real-time Variational Optic Flow Computation in Real-time , 2022 .

[14]  Richard Szeliski,et al.  A Database and Evaluation Methodology for Optical Flow , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[15]  J. Weickert,et al.  Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods , 2005 .

[16]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[17]  David J. Fleet,et al.  Performance of optical flow techniques , 1994, International Journal of Computer Vision.

[18]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[19]  Thomas Bäck,et al.  Evolutionary algorithms in theory and practice - evolution strategies, evolutionary programming, genetic algorithms , 1996 .

[20]  Daniel P. Huttenlocher,et al.  Learning for Optical Flow Using Stochastic Optimization , 2008, ECCV.

[21]  Mario Köppen,et al.  Improvement of a face detection system by evolutionary multi-objective optimization , 2005, Fifth International Conference on Hybrid Intelligent Systems (HIS'05).

[22]  A. Dornhaus,et al.  Psychophysics: Bees trade off foraging speed for accuracy , 2003, Nature.