Abstract
Traditional approaches for optical flow estimation always build an energy function which contains data term and smoothness term. However, optimizing the complex function is usually time-consuming. Nowadays, convolution neural networks have been applied in optical flow area. Most of them use large dataset for learning optical flow end-to-end, which can learn motion information from a large amount of prior information prepared in advance. However, these methods rely excessively on the learning ability of the network while ignoring some of well-proven assumptions in traditional approaches. In this paper, inspired by traditional methods, we present a network for learning optical flow, which combines traditional constraints with a supervised network. In the process of network optimization, the brightness constancy, gradient constancy and spatial smoothness assumptions are used to guide the training of network. Moreover, we stack several sub-networks integrated with prior constraints to form a large network for iterative refinement. Our method is tested on several public datasets, such as MPI-Sintel, KITTI2012, KITTI2015, Middlebury. The experimental results show that adding the prior constraints during training can obtain more refined and accurate flow. Compared with other recent methods, our method can achieve state-of-the-art performance on several public benchmarks.
Similar content being viewed by others
References
Ahmadi A, Patras I (2016) Unsupervised convolutional neural networks for motion estimation. In: 2016 IEEE international conference on image processing (ICIP), pp 1629–1633
Banerjee B, Murino V (2017) Efficient pooling of image based CNN features for action recognition in videos. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 2637–2641
Bao L, Yang Q, Jin H (2014) Fast edge-preserving patchmatch for large displacement optical flow. In: 2014 IEEE conference on computer vision and pattern recognition, pp 3534–3541. https://doi.org/10.1109/CVPR.2014.452
Bao L, Yang Q, Jin H (2014) Fast edge-preserving patchmatch for large displacement optical flow. In: 2014 IEEE conference on computer vision and pattern recognition, pp 3534–3541
Brox T, Bruhn A, Papenberg N, Weickert J (2004) High accuracy optical flow estimation based on a theory for warping. In: European conference on computer vision (ECCV), Lecture Notes in Computer Science, vol. 3024. Springer, pp 25–36
Brox T, Malik J (2011) Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Trans Pattern Anal Mach Intell 33(3):500–513. https://doi.org/10.1109/TPAMI.2010.143
Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. IEEE Trans Pattern Anal Mach Intell 40(4):834–848. https://doi.org/10.1109/TPAMI.2017.2699184
Chen Z, Jin H, Lin Z, Cohen S, Wu Y (2013) Large displacement optical flow from nearest neighbor fields. In: 2013 IEEE conference on computer vision and pattern recognition, pp 2443–2450. https://doi.org/10.1109/CVPR.2013.316
Cheng J, Tsai YH, Wang S, Yang MH (2017) Segflow: joint learning for video object segmentation and optical flow. In: 2017 IEEE international conference on computer vision (ICCV), pp 686–695
Dosovitskiy A, Fischery P, Ilg E, Husser P, Hazirbas C, Golkov V, van der Smagt P, Cremers D, Brox T (2015) Flownet: learning optical flow with convolutional networks. In: 2015 IEEE international conference on computer vision (ICCV), pp 2758–2766
Gao Z, Wang L, Zhou L, Zhang J (2017) Hep-2 cell image classification with deep convolutional neural networks. IEEE J Biomed Health Inform 21(2):416–428
Horn BK, Schunck BG (1981) Determining optical flow. Artif Intell 17(1):185–203
Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 2261–2269. https://doi.org/10.1109/CVPR.2017.243
Ilg E, Mayer N, Saikia T, Keuper M, Dosovitskiy A, Brox T (2017) Flownet 2.0: evolution of optical flow estimation with deep networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 1647–1655. https://doi.org/10.1109/CVPR.2017.179
Jaderberg M, Simonyan K, Zisserman A, Kavukcuoglu K (2015) Spatial transformer networks. In: Cortes C, Lawrence ND, Lee DD, Sugiyama M, Garnett R (eds) Advances in neural information processing systems, vol 28. Curran Associates, Inc, Red Hook, pp 2017–2025
Kingma D, Ba J (2015) Adam: a method for stochastic optimization. In: International conference on learning representations, pp 1–13
Li Y, Huttenlocher DP (2008) Learning for optical flow using stochastic optimization. In: Forsyth D, Torr P, Zisserman A (eds) Computer Vision - ECCV 2008. Springer, Berlin, Heidelberg, pp 379–391
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: single shot multibox detector. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer Vision - ECCV 2016. Springer International Publishing, Cham, pp 21–37
Lopez AM, Moreno-Noguer F, Sanfeliu A (2017) Joint coarse-and-fine reasoning for deep optical flow. In: 2017 IEEE international conference on image processing (ICIP)
Marban A, Srinivasan V, Samek W, Fernndez J, Casals A (2017) Estimating position velocity in 3d space from monocular video sequences using a deep neural network. In: 2017 IEEE international conference on computer vision workshops (ICCVW), pp 1460–1469. https://doi.org/10.1109/ICCVW.2017.173
Mayer N, Ilg E, Husser P, Fischer P, Cremers D, Dosovitskiy A, Brox T (2016) A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp. 4040–4048. https://doi.org/10.1109/CVPR.2016.438
Ranjan A, Black MJ (2017) Optical flow estimation using a spatial pyramid network. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 2720–2729
Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 6517–6525. https://doi.org/10.1109/CVPR.2017.690
Revaud J, Weinzaepfel P, Harchaoui Z, Schmid C (2015) Epicflow: edge-preserving interpolation of correspondences for optical flow. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 1164–1172. https://doi.org/10.1109/CVPR.2015.7298720
Rosenbaum D, Zoran D, Weiss Y (2013) Learning the local statistics of optical flow
Sun D, Roth S, Black MJ (2010) Secrets of optical flow estimation and their principles. In: 2010 IEEE computer society conference on computer vision and pattern recognition, pp. 2432–2439. https://doi.org/10.1109/CVPR.2010.5539939
Sun D, Roth S, Lewis JP, Black MJ (2008) Learning optical flow. In: Proceedings of the 10th European conference on computer vision: Part III, ECCV ’08. Springer, Berlin, Heidelberg, pp 83–97
Teney D, Hebert M (2017) Learning to extract motion from videos in convolutional neural networks. In: Lai SH, Lepetit V, Nishino K, Sato Y (eds) Computer Vision - ACCV 2016. Springer International Publishing, Cham, pp 412–428
Weinzaepfel P, Revaud J, Harchaoui Z, Schmid C (2013) Deepflow: large displacement optical flow with deep matching. In: 2013 IEEE international conference on computer vision, pp 1385–1392
Wulff J, Black MJ (2015) Efficient sparse-to-dense optical flow estimation using a learned basis and layers. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 120–130
Yu JJ, Harley AW, Derpanis KG (2016) Back to basics: unsupervised learning of optical flow via brightness constancy and motion smoothness. Springer International Publishing, Cham, pp 3–10
Zhang H, Cao X, Ho JKL, Chow TWS (2017) Object-level video advertising: an optimization framework. IEEE Trans Ind Inform 13(2):520–531
Zhang H, Ji Y, Huang W, Liu L (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl. https://doi.org/10.1007/s00521-018-3579-x
Zhu Y, Newsam S (2017) Densenet for dense flow. In: 2017 IEEE international conference on image processing (ICIP)
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China under Grant (61401113), in part by the Natural Science Foundation of Heilongjiang Province of China under Grant (LC201426), and in part by the Fundamental Research Funds for the Central Universities of China under Grant (HEUCF180801).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xiang, X., Zhai, M., Zhang, R. et al. A CNNs-based method for optical flow estimation with prior constraints and stacked U-Nets. Neural Comput & Applic 32, 4675–4688 (2020). https://doi.org/10.1007/s00521-018-3816-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-018-3816-3