© The Institution of Engineering and Technology
Optical flow estimation has bottlenecks such as large displacement and motion blur. In this Letter, the authors propose a geodesic-based probability propagation (GeoFlow) method combining the global geodesic with local spatial similarity to build a non-local superpixel graph. To achieve efficient belief propagation, a probabilistic framework for optimising the Markov random field (MRF) objective is proposed. In this way, the limitation of local propagation can be tackled in the global image level, and the probabilistic framework reduces computational complexity in the optimisation. In experiments, their method showed promising performance by improving the results on two public large displacement benchmark datasets.
References
-
-
1)
-
10. Brox, T., Bregler, C., Malik, J.: ‘Large displacement optical flow’. IEEE Conf. Computer Vision and Pattern Recognition, Miami, FL, USA, June 2009, pp. 41–48.
-
2)
-
7. Min, D., Choi, S., Lu, J., Han, B., Sohn, K.: ‘Fast global image smoothing based on weighted least squares’, Trans. Image Process., 2014, 23, pp. 5638–5653 (doi: 10.1109/TIP.2014.2366600).
-
3)
-
11. Kroeger, T., Timofte, R., Dai, D., et al: ‘Fast optical flow using dense inverse search’. European Conf. Computer Vision, Amsterdam, Netherlands, October 2016, pp. 471–488.
-
4)
-
1. Li, Y., Min, D., Brown, M.S., et al: ‘SPM-BP: sped-up PatchMatch belief propagation for continuous MRFs’. IEEE Conf. Computer Vision, Santiago, Chile, December 2015, pp. 4006–4014.
-
5)
-
3. Monzĺőn, N., Salgado, A., Sĺćnchez, J.: ‘Regularization strategies for discontinuity-preserving optical flow methods’, Trans. Image Process., 2016, 25, (4), pp. 1580–1591 (doi: 10.1109/TIP.2016.2526903).
-
6)
-
4. Revaud, J., Weinzaepfel, P., Harchaoui, Z., et al: ‘EpicFlow: edge-preserving interpolation of correspondences for optical flow’. IEEE Conf. Computer Vision and Pattern Recognition, Boston, MA, USA, June 2015, pp. 1164–1172.
-
7)
-
8)
-
12. Richardt, C., Kim, H., Valgaerts, L., et al: ‘Dense wide-baseline scene flow from two handheld video cameras’. IEEE Conf. 3D Vision, Stanford, CA, USA, October 2016, pp. 276–285.
-
9)
-
2. Ranjan, A., Black, M.J.: ‘Optical flow estimation using a spatial pyramid network’. IEEE Conf. Computer Vision and Pattern Recognition, Honolulu, HI, USA, July 2017, pp. 1696–1704.
-
10)
-
7. Butler, D.J., Wulff, J., Stanley, G.B., et al: ‘A naturalistic open source movie for optical flow evaluation’. European Conf. Computer Vision, Firenze, Italy, October 2012, pp. 611–625.
-
11)
-
7. Achanta, R., Shaji, A., Smith, K., et al: ‘SLIC superpixels compared to state-of-the-art superpixel methods’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (11), pp. 2274–2282 (doi: 10.1109/TPAMI.2012.120).
-
12)
-
9. Kennedy, R., Taylor, C.J.: ‘Hierarchically-constrained optical flow’. IEEE Conf. Computer Vision and Pattern Recognition, Boston, MA, USA, June 2015, pp. 3340–3348.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2018.0394
Related content
content/journals/10.1049/el.2018.0394
pub_keyword,iet_inspecKeyword,pub_concept
6
6