Abstract
Urban flow super-resolution (UFSR) can deduce fine-grained urban flow heatmap (UFH) based on coarse-grained observations and plays an essential role in urban planning (traffic prediction, public facility deployment, for instance). However, existing methods fail to capture the internal structural features of sparse UFHs and the external factors that lead to a significant waste of urban resources. To this end, we propose an enhanced super-resolution framework (Urban Flow-aware Super Resolution - Generative Adversarial Network, UrbanSG) to deduce fine-grained UFH for urban resource allocation. Specifically, we employ a conditional-GAN as the backbone, considering external factors as the specified condition. To capture the implicit urban structural correlation, we integrate the flow self-attention mechanism into our model, which focuses on urban grids with active traffic volumes. The evaluations of extensive experiments on two real-world datasets demonstrate the superiority of our framework. Especially when dealing with a sparse dataset, our method reduces error by 15.02% to the state-of-the-art baselines.
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
References
Cai, J., Meng, Z., Ho, C.M.: Residual channel attention generative adversarial network for image super-resolution and noise reduction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2020)
Chen, W., Long, G., Yao, L., Sheng, Q.Z.: AMRNN: attended multi-task recurrent neural networks for dynamic illness severity prediction. In: World Wide Web Conference , pp. 2753–2770 (2020)
Chen, W., Wang, S., Long, G., Yao, L., Sheng, Q.Z., Li, X.: Dynamic illness severity prediction via multi-task RNNs for intensive care unit. In: 2018 IEEE International Conference on Data Mining (ICDM), pp. 917–922. IEEE (2018)
Chen, W., Yue, L., Li, B., Wang, C., Sheng, Q.Z.: DAMTRNN: a delta attention-based multi-task RNN for intention recognition. In: Li, J., Wang, S., Qin, S., Li, X., Wang, S. (eds.) ADMA 2019. LNCS (LNAI), vol. 11888, pp. 373–388. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-35231-8_27
Dun, Y., Da, Z., Yang, S., Qian, X.: Image super-resolution based on residually dense distilled attention network. Neurocomputing 443, 47–57 (2021)
Gong, Y., Li, Z., Zhang, J., Liu, W., Zheng, Y.: Online spatio-temporal crowd flow distribution prediction for complex metro system. IEEE Trans. Knowl. Data Eng. 34, 865–880 (2020)
Gu, J., et al.: Exploiting interpretable patterns for flow prediction in dockless bike sharing systems. IEEE Trans. Knowl. Data Eng. 34(2), 640–652 (2020)
Jo, Y., Kim, S.J.: Practical single-image super-resolution using look-up table. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 691–700 (2021)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 105–114 (2017)
Liang, Y., Ke, S., Zhang, J., Yi, X., Zheng, Y.: Geoman: multi-level attention networks for geo-sensory time series prediction. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, pp. 3428–3434 (2018)
Liang, Y., et al.: Urbanfm: inferring fine-grained urban flows. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery, pp. 3132–3142 (2019)
Liu, J., Zhang, W., Tang, Y., Tang, J., Wu, G.: Residual feature aggregation network for image super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2359–2368 (June 2020)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. Comput. Sci. pp. 2672–2680 (2014)
Noor, D.F., Li, Y., Li, Z., Bhattacharyya, S., York, G.: Gradient image super-resolution for low-resolution image recognition. In: ICASSP 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2332–2336 (2019)
Pan, Z., et al.: Spatio-temporal meta learning for urban traffic prediction. IEEE Trans. Knowl. Data Eng. 34(3), 1462–1476 (2022). https://doi.org/10.1109/TKDE.2020.2995855
Wang, R., Lei, T., Zhou, W., Wang, Q., Meng, H., Nandi, A.K.: Lightweight non-local network for image super-resolution. In: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1625–1629 (2021)
Yan, Y., Ren, W., Hu, X., Li, K., Shen, H., Cao, X.: Srgat: Single image super-resolution with graph attention network. IEEE Trans. Image Process. 30, 4905–4918 (2021)
Yang, F., Yang, H., Fu, J., Lu, H., Guo, B.: Learning texture transformer network for image super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5791–5800 (2020)
Yue, L., Tian, D., Chen, W., Han, X., Yin, M.: Deep learning for heterogeneous medical data analysis. World Wide Web 23(5), 2715–2737 (2020)
Zhang, X., et al.: Traffic flow forecasting with spatial-temporal graph diffusion network. In: In Proceedings of the AAAI Conference. vol. 35, pp. 15008–15015 (2021)
Zhou, F., Jing, X., Li, L., Zhong, T.: Inferring high-resolutional urban flow with internet of mobile things. In: ICASSP 2021–2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7948–7952 (2021)
Zhou, F., Li, L., Zhong, T., Trajcevski, G., Zhang, K., Wang, J.: Enhancing urban flow maps via neural odes. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, pp. 1295–1302 (2020)
Acknowledgement
This work was supported by the General Project of National Natural Science Foundation of China under Grant 62072209, the National Natural Science Foundation of authority Youth Fund under Grant 62002123, the Key project of Science and technology development Plan of Jilin Province Grant 20210201082GX, the Jilin Provincial Development and Reform Commission Project Grant 2020C017-2, the Science and technology project of Education Department of Jilin Province under Grand JJKH20221010KJ, and the CCF-Baidu Open Fund under Grant 2021PP15002000.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, X., Xu, Y., Li, Y., Yang, Y. (2023). Fine-Grained Urban Flow Inferring via Conditional Generative Adversarial Networks. In: Li, B., Yue, L., Tao, C., Han, X., Calvanese, D., Amagasa, T. (eds) Web and Big Data. APWeb-WAIM 2022. Lecture Notes in Computer Science, vol 13423. Springer, Cham. https://doi.org/10.1007/978-3-031-25201-3_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-25201-3_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25200-6
Online ISBN: 978-3-031-25201-3
eBook Packages: Computer ScienceComputer Science (R0)