A Complete Confidence Framework for Optical Flow
Assessing the performance of optical flow in the absence of ground truth is of prime importance for a correct interpretation and application. Thus, in recent years, the interest in developing confidence measures has increased. However, by its complexity, assessing the capability of such measures for detecting areas of poor performance of optical flow is still unsolved.
We define a confidence measure in the context of numerical stability of the optical flow scheme and also a protocol for assessing its capability to discard areas of non-reliable flows. Results on the Middlebury database validate our framework and show that, unlike existing measures, our measure is not biased towards any particular image feature.
KeywordsOptical flow confidence measures sparsification plots error prediction plots
Unable to display preview. Download preview PDF.
- 1.Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: DARPA IU Workshop, pp. 121–130 (1981)Google Scholar
- 3.Horn, B., Schunck, B.: Determining optical flow. AI 17, 185–203 (1981)Google Scholar
- 5.Sun, D., Roth, S., Black, M.J.: Secrets of optical flow estimation and their principles. In: CVPR, pp. 2432–2439 (2010)Google Scholar
- 7.Bruhn, A., Weickert, J., Schnörr, C.: Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods. IJCV 61(2), 221–231 (2005)Google Scholar
- 11.Bruhn, A., Weickert, J.: A confidence measure for variational optic flow methods. In: Geometric Properties for Incomplete Data, pp. 283–298 (2006)Google Scholar
- 12.Kybic, J., Nieuwenhuis, C.: Bootstrap optical flow confidence and uncertainty measure. Computer Vision and Image Understanding, 1449–1462 (2011)Google Scholar
- 13.Cheney, W., Kincaid, D.: Numerical Mathematics and Computing, 6th edn. Bob Pirtle, USA (2008)Google Scholar
- 15.Haussecker, H., Spies, H.: Handbook of Computer Vision and Applications, vol. 2. Academic Press (1999)Google Scholar
- 16.Shi, J., Tomasi, C.: Good features to track, pp. 593–600 (1994)Google Scholar
- 17.Newbold, P., Carlson, W., Thorne, B.: Statistics for Business and Economics. Pearson Education (2007)Google Scholar
- 18.Liu, C.: Beyond pixels: exploring new representations and applications for motion analysis. Ph.D. dissertation, Cambridge, MA, USA (2009)Google Scholar