Issue No. 05 - May (2013 vol. 35)
Oisin Mac Aodha , Dept. of Comput. Sci., Univ. Coll. London, London, UK
A. Humayun , Sch. of Interactive Comput., Georgia Inst. of Technol., Atlanta, GA, USA
M. Pollefeys , Dept. of Comput. Sci., ETH Zurich, Zurich, Switzerland
G. J. Brostow , Dept. of Comput. Sci., Univ. Coll. London, London, UK
We present a supervised learning-based method to estimate a per-pixel confidence for optical flow vectors. Regions of low texture and pixels close to occlusion boundaries are known to be difficult for optical flow algorithms. Using a spatiotemporal feature vector, we estimate if a flow algorithm is likely to fail in a given region. Our method is not restricted to any specific class of flow algorithm and does not make any scene specific assumptions. By automatically learning this confidence, we can combine the output of several computed flow fields from different algorithms to select the best performing algorithm per pixel. Our optical flow confidence measure allows one to achieve better overall results by discarding the most troublesome pixels. We illustrate the effectiveness of our method on four different optical flow algorithms over a variety of real and synthetic sequences. For algorithm selection, we achieve the top overall results on a large test set, and at times even surpass the results of the best algorithm among the candidates.
Optical imaging, Adaptive optics, Optical variables measurement, Vectors, Prediction algorithms, Supervised learning, Accuracy, algorithm selection, Optical flow, confidence measure, Random Forest, synthetic data
M. Pollefeys, G. J. Brostow, O. Mac Aodha and A. Humayun, "Learning a Confidence Measure for Optical Flow," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 35, no. , pp. 1107-1120, 2013.