Abstract
Designing a model to quickly obtain an accurate matching cost is a vital problem in the stereo matching method. We present an algorithm called MC-HDCNN, which is based on hybrid dilated convolution neural network, for computing matching cost of two image patches. HDCNN uses the dilated convolution of the series to obtain a larger receptive field, while avoiding the “gridding” effect and ensuring the integrity of the receptive field. In addition, by adding batch normalization layer after each layer of the convolution, the gradient dispersion in the backward propagation and the generalization of the network can be improved effectively. We evaluate our method on the KITTI stereo data set. The results show that the proposed algorithm has certain advantages in accuracy and speed.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. In: IEEE SMBV, pp. 131–140 (2001)
Žbontar, J., LeCun, Y.: Stereo matching by training a convolutional neural network to compare image patches. JMLR 17(1), 2287–2318 (2016)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456 (2015)
Yoon, K.J., Kweon, I.S.: Adaptive support-weight approach for correspondence search. IEEE Trans. Pattern Anal. Mach. Intell. 28, 650–656 (2006)
Lei, C., Selzer, J., Yang, Y.H.: Region-tree based stereo using dynamic programming optimization. In: IEEE CVPR, pp. 2378–2385 (2006)
Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: IEEE ICCV, pp. 508–515 (2001)
Hirschmüller, H.: Semi-global matching-motivation, developments and applications. Photogram. Week 11, 173–184 (2011)
Žbontar, J., LeCun, Y.: Computing the stereo matching cost with a convolutional neural network. In: IEEE CVPR, pp. 1592–1599 (2015)
Luo, W., Schwing, A.G., Urtasun, R.: Efficient deep learning for stereo matching. In: IEEE CVPR, pp. 5695–5703 (2016)
Park, H., Lee, K.M.: Look wider to match image patches with convolutional neural networks. IEEE Signal Process. Lett. 24, 1788–1792 (2017)
Mayer, N., Ilg, E., Häusser, P., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: IEEE CVPR, pp. 4040–4048 (2016)
Kendall, A., Martirosyan, H., Dasgupta, S., et al.: End-to-end learning of geometry and context for deep stereo regression. In: IEEE ICCV, pp. 66–75 (2017)
Song, X., Zhao, X., Hu, H., Fang, L.: EdgeStereo: a context integrated residual pyramid network for stereo matching. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11365, pp. 20–35. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20873-8_2
Wang, P., Chen, P., Yuan, Y., et al.: Understanding convolution for semantic segmentation. In: IEEE WACV, PP. 1451–1460 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, Y., Huang, Y. (2019). MC-HDCNN: Computing the Stereo Matching Cost with a Hybrid Dilated Convolutional Neural Network. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1142. Springer, Cham. https://doi.org/10.1007/978-3-030-36808-1_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-36808-1_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36807-4
Online ISBN: 978-3-030-36808-1
eBook Packages: Computer ScienceComputer Science (R0)