Abstract
Road scene segmentation has always been regarded as a pixel-wise task in computer vision studies. In this paper, we introduce a practical and new features fusion structure named “Dual Path Network” for road semantic segmentation. This form aims to reduce the gap between low-level and high-level information, thereby improving features fusion. The Dual Path consists of two subpaths: Context Path and Spatial Path. In the Context Path, we select a pre-trained ResNet-101 model as the backbone and use multi-scale convolution blocks comprise the Spatial Path. Then, we create a fusion residual block and channel attention model to further optimize the network. The results of the experiment confirm a state-of-the-art mean intersection-over-union of 68.5% using the CamVid dataset.
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
Long, J., Shelhamer, E., Darrell, T.: Intelligence, fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation (2017). arXiv:1706.05587
Lin, G., Milan, A., Shen, C., Reid, I.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1925–1934 (2017)
Guo, X., et al.: GAN-based virtual-to-real image translation for urban scene semantic segmentation. Neurocomputing. (2019). https://doi.org/10.1016/j.neucom.2019.01.115
Yu, H., et al.: Methods and datasets on semantic segmentation: a review. Neurocomputing 304, 82–103 (2018)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Proceedings of the International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 234–241 (2015)
Quan, T.M., Hildebrand, D.G., Jeong, W.K.: Fusionnet: a deep fully residual convolutional neural network for image segmentation in connectomics (2016). arXiv:1612.05360
Wang, P., et al.: Understanding convolution for semantic segmentation. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 1451–1460 (2018)
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40, 834–848 (2017)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions (2015). arXiv:1511.07122
Zhang, R., Tang, S., Zhang, Y., Li, J., Yan, S.: Scale-adaptive convolutions for scene parsing. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2031–2039 (2017)
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Learning a discriminative feature network for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1857–1866 (2018)
Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5659–5667 (2017)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Mnih, V., Heess, N., Graves, A.: Recurrent models of visual attention. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 2204–2212 (2014)
Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156–3164 (2017)
Chen, L.-C., Yang, Y., Wang, J., Xu, W., Yuille, A.L.: Attention to scale: scale-aware semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3640–3649 (2016)
Ghiasi, G., Fowlkes, C.C.: Laplacian pyramid reconstruction and refinement for semantic segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 519–534 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211–252 (2015)
Ibtehaz, N., Rahman, M.S.: MultiResUNet: Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation (2019). arXiv:1902.04049
Berman, M., Triki, A.R., Blaschko, M.B.: The Lovász-Softmax loss: a tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4413–4421 (2018)
Jaccard, P.: Étude comparative de la distribution florale dans une portion des Alpes et des Jura. Bull Soc Vaudoise Sci Nat. 37, 547–579 (1901)
Bach, F.: Learning with submodular functions: A convex optimization perspective. Found. Trends® Mach. Learn. 6, 145–373 (2013)
Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian SegNet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding (2015). arXiv:1511.02680
Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation (2016). arXiv:1606.02147
Chaurasia, A., Culurciello, E.: LinkNet: exploiting encoder representations for efficient semantic segmentation. In: Proceedings of the IEEE Visual Communications and Image Processing, pp. 1–4 (2017)
Iglovikov, V., Shvets, A.: TernausNet: U-net with VGG11 encoder pre-trained on imagenet for image segmentation (2018). arXiv:1801.05746
Visin, F., et al.: ReSeg: a recurrent neural network-based model for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 41–48 (2016)
Li, H., Xiong, P., Fan, H., Sun, J.: DFANet: deep feature aggregation for real-time semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9522–9531 (2019)
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Learning a discriminative feature network for semantic segmentation (2018). arXiv:1804.09337
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer-Verlag GmbH Germany, part of Springer Nature
About this chapter
Cite this chapter
Ye, L. et al. (2020). DPNet: A Dual Path Network for Road Scene Semantic Segmentation. In: Pan, Z., Cheok, A., Müller, W., Zhang, M. (eds) Transactions on Edutainment XVI. Lecture Notes in Computer Science(), vol 11782. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-61510-2_6
Download citation
DOI: https://doi.org/10.1007/978-3-662-61510-2_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-61509-6
Online ISBN: 978-3-662-61510-2
eBook Packages: Computer ScienceComputer Science (R0)