Optical Flow Estimation with Prior Models Obtained from Phase Correlation

Motion estimation is one of the most important tasks in computer vision. One popular technique for computing dense motion fields consists in defining a large enough set of candidate motion vectors, and assigning one of such vectors to each pixel, so that a given cost function is minimized. In this work we propose a novel method for finding a small set of adequate candidates, making the minimization process computationally more efficient. Based on this method, we present algorithms for the estimation of dense optical flow using two minimization approaches: one based on a classic block-matching procedure, and another one based on entropy-controlled quadratic Markov measure fields which allow one to obtain smooth motion fields. Finally, we present the results obtained from the application of these algorithms to examples taken from the Middlebury database.

[1]  Amir Averbuch,et al.  Pseudopolar-based estimation of large translations, rotations, and scalings in images , 2005, IEEE Transactions on Image Processing.

[2]  Michel Barlaud,et al.  Deterministic edge-preserving regularization in computed imaging , 1997, IEEE Trans. Image Process..

[3]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[4]  Mariano Rivera,et al.  Entropy-Controlled Quadratic Markov Measure Field Models for Efficient Image Segmentation , 2007, IEEE Transactions on Image Processing.

[5]  C. Morandi,et al.  Registration of Translated and Rotated Images Using Finite Fourier Transforms , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Masatoshi Okutomi,et al.  Sub-Pixel Estimation Error Cancellation on Area-Based Matching , 2005, International Journal of Computer Vision.

[7]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[8]  B. N. Chatterji,et al.  An FFT-based technique for translation, rotation, and scale-invariant image registration , 1996, IEEE Trans. Image Process..

[9]  Michael J. Black,et al.  Secrets of optical flow estimation and their principles , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[11]  Jens Rannacher,et al.  Realtime 3 D Motion Estimation on Graphics Hardware , 2010 .

[12]  Paul A. Viola,et al.  Robust Real-time Object Detection , 2001 .

[13]  T. Higuchi,et al.  A Sub-Pixel Correspondence Search Technique for Computer Vision Applications , 2004 .

[14]  Hassan Foroosh,et al.  Extension of phase correlation to subpixel registration , 2002, IEEE Trans. Image Process..

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

[16]  Takafumi Aoki,et al.  Robust Motion Estimation for Video Sequences Based on Phase-Only Correlation , 2004 .

[17]  Takafumi Aoki,et al.  A High-Accuracy Passive 3D Measurement System Using Phase-Based Image Matching , 2006, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[18]  Yoel Shkolnisky,et al.  The angular difference function and its application to image registration , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[20]  Alex Zelinsky,et al.  Learning OpenCV---Computer Vision with the OpenCV Library (Bradski, G.R. et al.; 2008)[On the Shelf] , 2009, IEEE Robotics & Automation Magazine.

[21]  Driss Aboutajdine,et al.  An efficient fast full search block matching algorithm using FFT algorithms , 2006 .