Abstract
High computational cost and low tracking stability make it still a challenging task to acquire nonmotorized traffic parameters at intersections via vision-based method. In order to address the above issues, our study improves a cooperative tracking and classification method, and proposes a vision-based data collection system to monitor nonmotorized traffic at intersections. The system utilizes the combination of two tracking algorithms, Kernelized Correlation Filter and Kalman filter, to ensure the continuous tracking. Based on multivariate feature, K-means clustering and Support Vector Machine are implemented to classify nonmotorized traffic according to the motion and appearance feature respectively. As a result, the proposed system can acquire trajectories of pedestrians and cyclists and extract traffic parameters, including flow and velocity. Our method performs well in both efficiency and accuracy by fusing simple but effective algorithms and is robust in the complex scenario especially at large-scale intersections with limited training samples. The experimental results show that it can extract more trajectories with low computational lost. Moreover, the error of flow and velocity result is controlled within acceptable limits, which directly proves it feasible to collect field data in project applications.
Similar content being viewed by others
References
Transport Canada: Canadian Motor Vehicle Traffic Collision 2014. Publication Transport Canada (2016) Available online: https://tc.canada.ca/sites/default/files/migrated/cmvtcs2014_eng.pdf. Accessed 7 Jan 2021
U.S. Government Accountability Office: Pedestrians and cyclists—cities, states, and DOT are implementing actions to improve safety. Publication GAO-16-66. U.S. Government Accountability Office (2015) Available online: https://www.gao.gov/assets/680/673782.pdf. Accessed 7 Jan 2021
Baas, J., Galton, R., Biton, A.: FHWA bicycle-pedestrian count technology pilot project—summary report. FHWA, U.S. Department of Transportation (2016) Available online: https://www.fhwa.dot.gov/environment/bicycle_pedestrian/countpilot/summary_report/fhwahep17012.pdf. Accessed 7 Jan 2021
Shantaiya, S., Verma, K., Mehta, K.: Multiple object tracking using Kalman filter and optical flow. European Journal of Advances in Engineering and Technology. 2(2), 34–39 (2015)
Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. J. IEEE Trans. Pattern. Anal. Mach. Intell. 24(5), 603–619 (2002)
Henriques, J.F., Caseiro, R., Martins, P.: High-Velocity Tracking with Kernelized Correlation Filters. J. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583–596 (2015)
Danelljan, M., Häger, G., Khan, F.S. (eds.): Discriminative Scale Space Tracking. J. IEEE Trans. Pattern Anal. Mach. Intell. 39(8), 1561–1575 (2017)
Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. 2017 IEEE International Conference on Image Processing, Beijing (2017)
Liu, W., Zhang, M., Luo, Z. (eds.): An Ensemble Deep Learning Method for Vehicle Type Classification on Visual Traffic Surveillance Sensors. IEEE Access. 5, 24417–24425 (2017)
Gao, H., Cheng, B., Wang, J. (eds.): Object Classification Using CNN-Based Fusion of Vision and LIDAR in Autonomous Vehicle Environment. IEEE Trans. Ind. Inform. 14(9), 4224–4231 (2018)
Khan, M.A., Ectors, W., Bellemans, T. (eds.): Unmanned Aerial Vehicle-Based Traffic Analysis: A Case Study for Shockwave Identification and Flow Parameters Estimation at Signalized Intersect. J. Remote Sens. 10(3), 458 (2018)
Xin, J., Du, X., Shi, Y.: Classifier Adaptive Fusion: Deep Learning for Robust Outdoor Vehicle Visual Tracking. IEEE Access. 7, 118519–118529 (2019)
Cui, Y., Zhang, J., He, Z. (eds.): Multiple pedestrian tracking by combining particle filter and network flow model. Neurocomputing. 351, 217–227 (2019)
Yu, P., Zhao, Y., Zhang, J. (eds.): Pedestrian detection using multi-channel visual feature fusion by learning deep quality model. J. Vis. Commun. Image Represent. 63, 102579 (2019)
Wang, Z., Cui, J., Zha, H.e.: Foreground Object Detection by Motion-based Grouping of Object Parts. Int. J. Intell. Transp. Syst. Res. 12, 70–82 (2014)
Zhao, Y., Chen, Q., Cao, W. (eds.): Deep Learning for Risk Detection and Trajectory Tracking at Construction Sites. J. IEEE Access. 7, 30905–30912 (2019)
Li, J., Shao, C., Xu, W. (eds.): Real-Time System for Tracking and Classification of Pedestrians and Bicycles. Transport. Res. Rec. 2198(1), 83–92 (2010)
Zhu, J., Chen, S., Tu, W. (eds.): Tracking and Simulating Pedestrian Movements at Intersections Using Unmanned Aerial Vehicles. Remote Sens. 11(8), 925 (2019)
Guo, Y., Sayed, T., Zaki, M.H.: Automated analysis of pedestrian walking behaviour at a signalised intersection in China. IET Intell. Transp. Syst. 11(1), 28–36 (2017)
Shirazi, M.S., Morris, B.T.: Vision-based pedestrian behavior analysis at intersections. J. Electron. Imaging. 25(5), 051203 (2016)
Stauffer, C., Grimson, W.: Adaptive Background Mixture Models for Real-Time Tracking. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Ft. Collins (1999)
Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego (2005)
Lukezic, A., Vojir, T., Zajc, L.C. (eds.): Discriminative Correlation Filter with Channel and Spatial Reliability. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu (2017)
Bolme, D.S., Beveridge, J.R., Draper, B.A. (eds.): Visual object tracking using adaptive correlation filters. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Providence, San Francisco (2010)
Acknowledgments
This study is supported by the National Key Research and Development Program of China (No. 2019YFB1600200), the national nature science foundation of China (No. 51878161) and the China Postdoctoral Science Foundation (No.2020M681466).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, X., Wang, H. & Dong, C. An Improved Method of Nonmotorized Traffic Tracking and Classification to Acquire Traffic Parameters at Intersections. Int. J. ITS Res. 19, 312–323 (2021). https://doi.org/10.1007/s13177-020-00247-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13177-020-00247-w