Abstract
Current deep learning methods for optical flow estimation often use spatial feature pyramids to extract image features. To get the correlation between images, they directly compute the cost volume of the obtained image features. In this process, fine object details tend to be ignored. To solve this fundamental problem, an object-scale adaptive optical flow estimation network is proposed, in which multi-scale features are selectively extracted and exploited using our developed feature selectable block (FSB). As a result, we can obtain the multi-scale receptive fields of objects at different scales in the image. To consolidate all image features generated from all scales, a new cost volume generation scheme called multi-scale cost volume generation block (MCVGB) is further proposed to aggregate information from different scales. Extensive experiments conducted on the Sintel and KITTI2015 datasets show that our proposed method can capture fine details of different scale objects with high accuracy and thus deliver superior performance over a number of state-of-the-art methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-24673-2_3
Brox, T., Malik, J.: Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 33, 500-13 (2011)
C, Y., X, B., Y, F.: LightPIVNet: An effective convolutional neural network for particle image velocimetry. IEEE Trans. Instrum. Meas. 70, 1–1 (2021)
Dosovitskiy, A., et al.: FlowNet: Learning optical flow with convolutional networks. In: International Conference on Computer Vision (ICCV), pp. 2758–2766 (2015)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3354–3361 (2012)
Ghaywate, P., Vyas, F., Telang, S., Mangale, S.: A deep learning approach for motion segmentation using an optical flow technique. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–6 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Hosni, A., Rhemann, C.: Fast cost-volume filtering for visual correspondence and beyond. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 35, 504–511 (2013)
Hui, T., Tang, X., Loy, C.C.: LiteFlowNet: A lightweight convolutional neural network for optical flow estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8981–8989 (2018)
Hur, J., Roth, S.: Iterative residual refinement for joint optical flow and occlusion estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5754–5763 (2019)
Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: Evolution of optical flow estimation with deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1647–1655 (2017)
Jaderberg, M., Simonyan, K., Zisserman, A.: Spatial transformer networks. In: Advances in Neural Information Processing Systems. pp. 2017–2025 (2015)
Jayasundara, V., Roy, D., Fernando, B.: Flowcaps: Optical flow estimation with capsule networks for action recognition. In: IEEE Winter Conference on Applications of Computer Visio (WACV), pp. 3408–3417 (2021)
Jiang, S., Lu, Y., Li, H., Hartley, R.: Learning optical flow from a few matches. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16592–16600 (2021)
Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 510–519 (2019)
Mayer, N., Ilg, E.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4040–4048 (2016)
Papenberg, N., Bruhn, A., Brox, T., Didas, S., Weickert, J.: Highly accurate optic flow computation with theoretically justified warping. IEEE Int. J. Comput. Vision (IJCV) 67, 141–158 (2006)
Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2720–2729 (2017)
Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Epicflow: Edge-preserving interpolation of correspondences for optical flow. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1164–1172 (2015)
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IEEE International J. Comput. Vis. (IJCV) 47, 7–42 (2002)
Scharstein, D., Szeliski, R.: High-resolution optical flow from 1d attention and correlation. In: International Conference on Computer Vision (ICCV), pp. 10478–10487 (2021)
Sun, D., Roth, S., Black, M.J.: A quantitative analysis of current practices in optical flow estimation and the principles behind them. IEEE Int. J. Comput. Vis. (IJCV) 106, 115–137 (2014)
Sun, D., Yang, X., Liu, M., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8934–8943 (2018)
Szegedy, C., Liu, W., Jia, Y.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015)
Teed, Z., Deng, J.: RAFT: Recurrent all-pairs field transforms for optical flow. In: European Conference on Computer Vision (ECCV), pp. 402–419 (2020)
Wang, H., Cai, P., Fan, R., Sun, Y., Liu, M.: End-to-end interactive prediction and planning with optical flow distillation for autonomous driving. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2229–2238 (2021)
Wang, L., Koniusz, P., Huynh, D.: Hallucinating IDT descriptors and I3D optical flow features for action recognition with CNNs. In: International Conference on Computer Vision (ICCV), pp. 8697–8707 (2019)
Wulff, J., Butler, D.J., Stanley, G.B., Black, M.J.: Lessons and insights from creating a synthetic optical flow benchmark. In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012. LNCS, vol. 7584, pp. 168–177. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33868-7_17
Yang, G., Ramanan, D.: Volumetric correspondence networks for optical flow. In: Advances in Neural Information Processing Systems, pp. 793–803 (2019)
Yin, Z., Darrell, T., Yu, F.: Hierarchical discrete distribution decomposition for match density estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6044–6053 (2019)
Zhao, C., Feng, C., Li, D., Li, S.: Optical flow-auxiliary multi-task regression network for direct quantitative measurement, segmentation and motion estimation. In: Association for the Advancement of Artificial Intelligence (AAAI), pp. 1218–1225 (2020)
Zhao, S., Sheng, Y., Dong, Y., Chang, E.I., Xu, Y.: MaskFlowNet: Asymmetric feature matching with learnable occlusion mask. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6277–6286 (2020)
Zuehlke, D., Posada, D.: Autonomous satellite detection and tracking using optical flow. CoRR abs/2204.07025 (2022)
Acknowledgements
This work was supported in part by the Natural Science Foundation of the Jiangsu Higher Education Institutions of China under Grant 21KJA520007, in part by the National Natural Science Foundation of China under Grant 61572341, in part by the Priority Academic Program Development of Jiangsu Higher Education Institutions, in part by Collaborative Innovation Center of Novel Software Technology and Industrialization, and in part by the NTU-WASP Joint Project under Grants M4082184.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, M., Zhong, B.j., Ma, KK. (2022). Object-Scale Adaptive Optical Flow Estimation Network. In: Khanna, S., Cao, J., Bai, Q., Xu, G. (eds) PRICAI 2022: Trends in Artificial Intelligence. PRICAI 2022. Lecture Notes in Computer Science, vol 13631. Springer, Cham. https://doi.org/10.1007/978-3-031-20868-3_44
Download citation
DOI: https://doi.org/10.1007/978-3-031-20868-3_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20867-6
Online ISBN: 978-3-031-20868-3
eBook Packages: Computer ScienceComputer Science (R0)