Abstract
To recognize road intersections using cycling trajectories accurately is vital to the quality of the digital map that cycling navigation apps use. However, the existing approaches mainly identify road intersections based on motor vehicles’ trajectories, and they fail to tackle unique challenges posed by cycling trajectories: (i) Cycling trajectories of minor intersections and their adjacent road segments are quite sparse. (ii) Turning behaviors occur at different areas in intersections of various sizes. To address the above challenges, in this paper, we propose a precision-enhanced road intersection recognition method using cycling trajectories, called PICT. Initially, to enhance the representations of minor intersections, a grid topology representation module is designed to extract intersection topology. Then an intersection inference module based on multi-scale feature learning is put forward to identify the intersections of different scales correctly. Finally, extensive comparative experiments on two real-world datasets demonstrate that PICT significantly outperforms the state-of-the-art methods by 52.13% in the F1-score of intersection recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wang, J., Wang, C., Song, X., Raghavan, V.: Automatic intersection and traffic rule detection by mining motor-vehicle gps trajectories. Comput. Environ. Urban Syst. 64, 19–29 (2017)
Huang, Y., Xiao, Z., Xiaoyou, Yu., Wang, D., Havyarimana, V., Bai, J.: Road network construction with complex intersections based on sparsely sampled private car trajectory data. TKDD 13(3), 1–28 (2019)
Zhao, L., et al.: Automatic calibration of road intersection topology using trajectories. In: ICDE, pp. 1633–1644 (2020)
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR (2020)
Chao, P., Hua, W., Mao, R., Jiajie, X., Zhou, X.: A survey and quantitative study on map inference algorithms from GPS trajectories. IEEE Trans. Knowl. Data Eng. 34(1), 15–28 (2020)
Wang, T., Mao, J., Jin, C.: HyMU: a hybrid map updating framework. In: DASFAA, pp. 19–33 (2017)
He, S., et al.: Roadrunner: improving the precision of road network inference from GPS trajectories. In: SIGSPATIAL, pp. 3–12 (2018)
Biagioni, J., Eriksson, J.: Map inference in the face of noise and disparity. In: SIGSPATIAL, pp. 79–88 (2012)
Li, L., Li, D., Xing, X., Yang, F., Rong, W., Zhu, H.: Extraction of road intersections from GPS traces based on the dominant orientations of roads. ISPRS Int. J. Geo Inf. 6(12), 403 (2017)
Ruan, S., et al.: Learning to generate maps from trajectories. In: AAAI vol. 34, pp. 890–897 (2020)
Karagiorgou, S., Pfoser, D.: On vehicle tracking data-based road network generation. In: SIGSPATIAL, pp. 89–98 (2012)
Pu, M., Mao, J., Du, Y., Shen, Y., Jin, C.: Road intersection detection based on direction ratio statistics analysis. In: MDM, pp. 288–297 (2019)
Wang, C., Hao, P., Wu, G., Qi, X., Barth, M.J.: Intersection and stop bar position extraction from vehicle positioning data. IEEE Trans. Intell. Transp. Syst. (2020)
Qing, R., Liu, Y., Zhao, Y., Liao, Z., Liu, Y.X.: Using feature interaction among GPS data for road intersection detection. In: HUMA @ ACM Multimedia, pp. 31–37 (2021)
Rong, H., Yong, X., Chen, H., Zou, F.: A novel method for the detection of road intersections and traffic rules using big floating car data. IET Intel. Transp. Syst. 16(8), 983–997 (2022)
Máttyus, G., Luo, W., Urtasun, R.: Deeproadmapper: extracting road topology from aerial images. In ICCV, pp. 3438–3446 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Dai, Y., Wu, Y., Zhou, F., Barnard, K.: Asymmetric contextual modulation for infrared small target detection. In: WACV, pp. 950–959 (2021)
Veličković, P., et al.: Graph attention networks. In: ICLR (2017)
Parmar, N., et al.: Image transformer. In: ICML, pp. 4055–4064. PMLR (2018)
Li, F., Zhang, H., Liu, S., Zhang, L., Ni, L.M., Shum, H.-Y., et al.: Mask DINO: lards a unified transformer-based framework for object detection and segmentation. arXiv preprint arXiv:2206.02777 (2022)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR, pp. 779–788 (2016)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961–2969 (2017)
Wang, X., Zhang, R., Kong, T., Li, L., Shen, C.: Solov2: dynamic and fast instance segmentation. NeurIPS 33, 17721–17732 (2020)
Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR, pp. 1290–1299 (2022)
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Acknowledgments
This work is supported by NSFC (Nos.62072180 and U191 1203), and CCF-DiDi GAIA Collaborative Research Funds for Young Scholars.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Ethics declarations
Ethical Statement
This paper involves the development and evaluation of a road intersection recognition method using cycling trajectories, which has meaningful implications in cycling navigation. We value the importance of ethical considerations in the field of data mining and guarantee that our research does not involve the collection and inference of personal data, and will not cause adverse effects on society.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, W. et al. (2023). PICT: Precision-enhanced Road Intersection Recognition Using Cycling Trajectories. In: De Francisci Morales, G., Perlich, C., Ruchansky, N., Kourtellis, N., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14175. Springer, Cham. https://doi.org/10.1007/978-3-031-43430-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-43430-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43429-7
Online ISBN: 978-3-031-43430-3
eBook Packages: Computer ScienceComputer Science (R0)