Bayesian Formulation of Image Patch Matching Using Cross-correlation
A classical solution for matching two image patches is to use the cross-correlation coefficient. This works well if there is a lot of structure within the patches, but not so well if the patches are close to uniform. This means that some patches are matched with more confidence than others. By estimating this uncertainty, more weight can be put on the confident matches than those that are more uncertain. To enable this two distribution functions for two different cases are used: (i) the correlation between two patches showing the same object but with different lighting conditions and different noise realisations and (ii) the correlation between two unrelated patches.
Using these two distributions the patch matching problem is, in this paper, formulated as a binary classification problem. The probability of two patches matching is derived. The model depends on the signal to noise ratio. The noise level is reasonably invariant over time, while the signal level, represented by the amount of structure in the patch or its spatial variance, has to be measured for every frame.
A common application where this is useful is feature point matching between different images. Another application is background/foreground segmentation. This paper will concentrate on the latter application. It is shown how the theory can be used to implement a very fast background/foreground segmentation algorithm by transforming the calculations to the DCT-domain and processing a motion-JPEG stream without uncompressing it. This allows the algorithm to be embedded on a 150 MHz ARM based network camera. It is also suggested to use recursive quantile estimation to estimate the background model. This gives very accurate background models even if there is a lot of foreground present during the initialisation of the model.
KeywordsPatch-matching Lighting variations Background/Foreground-segmentation Bayesian classification
Unable to display preview. Download preview PDF.
- 2.Ardö, H.: Multi-target Tracking Using On-line Viterbi Optimisation and Stochastic Modelling. Centre for Mathematical Sciences LTH, Lund University, Sweden (2009) Google Scholar
- 3.Ardö, H., Ăström, K.: Bayesian formulation of image patch matching using cross-correlation. In: Third ACM/IEEE International Conference on Distributed Smart Cameras (2009) Google Scholar
- 6.Friedman, N., Russell, S.: Image segmentation in video sequences: a probabilistic approach. In: Thirteenth Conference on Uncertainty in Artificial Intelligence, pp. 175–181 (1997). doi: 10.1.1.38.7356. URL http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.38.7356 Google Scholar
- 7.Gordon, G., Darrell, T., Harville, M., Woodfill, J.: Background estimation and removal based on range and color. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1999, vol. 2, p. 464 (1999). doi: 10.1109/CVPR.1999.784721. URL http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=784721 Google Scholar
- 9.Hu, W., Gong, H., Zhu, S.C., Wang, Y.: An integrated background model for video surveillance based on primal sketch and 3d scene geometry. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8 (2008). doi: 10.1109/CVPR.2008.4587541. URL http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4587541 CrossRefGoogle Scholar
- 12.Kohli, P., Torr, P.: Efficiently solving dynamic Markov random fields using graph cuts. In: ICCV 2005, vol. 2, pp. 922–929 (2005) Google Scholar
- 13.Mittal, A., Paragios, N.: Motion-based background subtraction using adaptive kernel density estimation. In: CVPR, vol. 02, pp. 302–309 (2004). URL http://doi.ieeecomputersociety.org/10.1109/CVPR.2004.164 Google Scholar
- 15.Noriega, P., Bernier, O.: Real time illumination invariant background subtraction using local kernel histograms. In: Proc. British Machine Vision Conference, p. III:979 (2006) Google Scholar
- 16.Spanne, S.: Konkret Analys. KFS AB, Solvegatan 22, Lund, Sweden (1997) Google Scholar
- 17.Stauffer, C.: Adaptive background mixture models for real-time tracking. In: Proc. Conf. Computer Vision and Pattern Recognition, pp. 246–252 (1999) Google Scholar
- 19.Toyama, K., Krumm, J., Brumitt, B., Meyers, B.: Wallflower: principles and practice of background maintenance. In: Int. Conf. on Computer Vision, pp. 255–261 (1999) Google Scholar
- 20.Magnus, W.F., Bateman, H., Erdaelyi, A.: Higher Transcendental Functions, vol. II. McGraw–Hill, New York (1953) Google Scholar
- 21.Wayne, P., Johann, P., Schoonees, A.: Understanding background mixture models for foreground segmentation. In: Proceedings Image and Vision Computing (2002). URL http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.5222 Google Scholar