Abstract
Urban road intersections are the key nodes of urban road network with a mass of traffic flow confliction, which often result in traffic accidents. Therefore, automated conflict detection is crucial for traffic safety analysis. This paper proposes a method to extract traffic conflicts by using deep learning based trajectory detection. The traffic video data is collected by unmanned aircraft in a road intersection in Xi’an, i.e., an ancient city in China. Then, YOLOv5-DeepSORT is employed to extract the vehicle trajectories. Comparing the situation and velocity of vehicles in each time slice, we put forward a method of automatic calculation and extraction of traffic conflict indicator. Moreover, a visualized conflict areas are shown in graphs, which is helpful for the safety analysis of urban road intersections.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Road Traffic Safety Research Center of the Ministry of Public Security: Research Report on Road Traffic Development in China’s Large Cities. People’s Communications Press Co., Ltd., Beijing (2020)
Girshick, R.: Fast R-CNN. arXiv e-prints (2015)
Ren, S., He, K., Girshick, R., Sun, J.: NIPS
Liu, W., et al.: European Conference on Computer Vision, pp. 21–37. Springer, Cham
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. PP, 2999–3007 (2017)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. IEEE (2016)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger, pp. 6517–6525 (2017). IEEE
Redmon, J., Farhadi, A.: YOLOv3: an Incremental Improvement. arXiv e-prints (2018)
Bochkovskiy, A., Wang, C.Y., Liao, H.: YOLOv4: optimal speed and accuracy of object detection (2020)
Xing, L., et al.: Examining traffic conflicts of up stream toll plaza area using vehicles’ trajectory data. Accid. Anal. Prev. 125, 174–187 (2019). https://doi.org/10.1016/j.aap.2019.01.034
Li, M., Wang, X.H., Shi, K.: 8th International Conference on Ambient Systems, Networks and Technologies (ANT)/7th International Conference on Sustainable Energy Information Technology (SEIT), pp. 963–968 (2017)
Liu, H.: Detection and Analysis of Traffic Conflict at Uncontrolled Intersections Based on Deep Learning. Southwest Jiaotong University (2020)
Zheng, L., Sayed, T.: From univariate to bivariate extreme value models: approaches to integrate traffic conflict indicators for crash estimation. Transp. Res. Part C-Emerg. Technol. 103, 211–225 (2019). https://doi.org/10.1016/j.trc.2019.04.015
Long, K., Zhang, Y., Zou, Z., Gu, J., Hao, W.: Non-conflict discrimination between vehicles at signalized intersections based on vehicle trajectory. Transp. Syst. Eng. Inf. 21, 69–74 (2021). https://doi.org/10.16097/j.cnki. 1009-6744.2021.01.011
Lu, Y.C., et al.: Analysis method of traffic conflict at urban road intersection based on risk domain. J. Tongji Univ. Nat. Sci. 49, 8 (2021)
Wang, C.Y., Liao, H., Wu, Y.H., Chen, P.Y., Yeh, I.H.: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Savarese, S.: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Zhu, P., et al.: Detection and tracking meet drones challenge. arXiv e-prints (2020)
Sayed, T., Zaki, M.H., Autey, J.: Automated safety diagnosis of vehicle–bicycle interactions using computer vision analysis. Saf. Sci. 59, 163–172 (2013)
Wang, B., Zhu, Y.Q., Shen, Y., Liu, Q.C.: Traffic conflict detection of vehicle and non-motorized vehicle at intersection based on deep learning (2018)
Guo, Y.: Signaled Intersection Safety Evaluation Technology Based on Traffic Conflict Theory. Southeast University (2016)
Ismail, K., Sayed, T., Saunier, N., Bartlett, M.: A methodology for precise camera calibration for data collection applications in urban traffic scenes. Can. J. Civ. Eng. 40, 57–67 (2013)
Zivkovic, Z.: Proceedings of the 17th International Conference on Pattern Recognition (2004). ICPR 2004
Zivkovic, Z., Heijden, F.: Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recogn. Lett. 27, 773–780 (2006)
Droogenbroeck, M.V., Paquot, O.: Background subtraction: experiments and improvements for ViBe. IEEE (2012)
Zhang, X.W.: Research on the conflict between pedestrians and right-turning vehicles at signal-controlled intersections. Southwest Jiaotong University
Cai, T., Tang, H.: A review of the principle of least squares fitting for Savitzky-Golay smoothing filters. Digit. Commun. 7 (2011)
Hyden, C.: Proceedings of the First Workshop on Traffic Conflicts, pp. 87–89
Acknowledgment
This study is funded by the National Key R & D Program of China [grant number 2019YFE0108000].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Beijing HIWING Sci. and Tech. Info Inst
About this paper
Cite this paper
Zhang, Y., Liu, L., Zhu, T. (2023). Extracting Traffic Conflict at Urban Intersection Using Deep Learning Trajectory Detection. In: Fu, W., Gu, M., Niu, Y. (eds) Proceedings of 2022 International Conference on Autonomous Unmanned Systems (ICAUS 2022). ICAUS 2022. Lecture Notes in Electrical Engineering, vol 1010. Springer, Singapore. https://doi.org/10.1007/978-981-99-0479-2_282
Download citation
DOI: https://doi.org/10.1007/978-981-99-0479-2_282
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0478-5
Online ISBN: 978-981-99-0479-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)