Automated tool to collect vehicle trajectories using drone images and computer vision techniques
DOI:
https://doi.org/10.58922/transportes.v31i3.2886Keywords:
Urban traffic, Urban streets, YOLO, Deep SORTAbstract
The main objective of this work is to propose a procedure for automated collection of vehicle trajectories using a computer vision tool, applied to videos recorded by drone. The algorithm was trained to automatically detect, classify, and track vehicles, and the data were processed to obtain the trajectories in 4 sites in Fortaleza. The test results indicate a good performance to detect and classify, mainly cars, motorcycles, and trucks (98% to 99% true positive rate). It was verified the importance of correcting the position of objects to compensate for the drone movements caused by winds. The vehicle passage times and the headways obtained were similar to those recorded using a semiautomatic tool, with 98.6% of time differences between 0.0 and 0.2 s and 95.3% of headway differences between -0.1 and +0.1 s.
Downloads
References
Agerholm, N.; C. Tønning e T. K. O. Madsen et al. (2017) Road user behaviour analyses based on video detections: status and best practice examples from the RUBA software. In Proceedings of the 24th ITS World Congress. Montreal, Canada: ITS World, p. 1-10.
Amrutsamanvar, R.B.; B.R. Muthurajan e L.D. Vanajakshi (2019) Extraction and analysis of microscopic traffic data in disordered heterogeneous traffic conditions, Transportation Letters, v. 13, n. 1, p. 1-20. DOI: 10.1080/19427867.2019.1695563. DOI: https://doi.org/10.1080/19427867.2019.1695563
Barceló, J. e M. Kuwahara (2010) Traffic Data Collection and its Standardization. New York: Springer. DOI: 10.1007/978-1-4419-6070-2. DOI: https://doi.org/10.1007/978-1-4419-6070-2
Barmpounakis, E.N.; E.I. Vlahogianni e J.C. Golias (2016) Vision-based multivariate statistical modeling for powered two-wheelers maneuverability during overtaking in urban arterials, Transportation Letters, v. 8, n. 3, p. 167-76. DOI: 10.1179/1942787515Y.0000000020. DOI: https://doi.org/10.1179/1942787515Y.0000000020
Barmpounakis, E.N.; E.I. Vlahogianni e J.C. Golias (2018) Identifying predictable patterns in the unconventional overtaking decisions of PTW for cooperative ITS. IEEE Transactions on Intelligent Vehicles, v. 3, n. 1, p. 102-11. DOI: 10.1109/TIV.2017.2788195. DOI: https://doi.org/10.1109/TIV.2017.2788195
Bewley, A.; Z. Ge; L. Ott et al. (2016) Simple online and realtime tracking. In: IEEE Int. on Image Process. New York: IEEE, p. 3464-3468. DOI: 10.1109/ICIP.2016.7533003. DOI: https://doi.org/10.1109/ICIP.2016.7533003
Bochkovskiy, A.; C. Wang e H.M. Liao (2020) YOLOv4: Optimal Speed and Accuracy of Object Detection. ArXiv. DOI: 10.48550/arXiv.2004.10934.
Câmara, S.M.; D.A. Santos e F.J.C. Cunto (2015) Avaliação do uso da estratégia de visão computacional region based em pesquisas volumétricas em áreas urbanas. In Anais do XXIX Congresso de Pesquisa e Ensino em Transportes. Rio de Janeiro: ANPET, p. 1530-1541.
Castro-Junior, F.A.B.; M.M. Castro Neto e F.J.C. Cunto (2021) Análise do atraso e da brecha aceita dos pedestres em travessias semaforizadas: um estudo na cidade de fortaleza utilizando técnicas de visão computacional baseadas em deep learning. In Anais do XXXV Congresso de Pesquisa e Ensino em Transportes. Rio de Janeiro: ANPET, p. 2470- 2481.
Chen, P.; Y. Dang; R. Liang et al. (2017) Real-time object tracking on a drone with multi-inertial sensing data, IEEE Transactions on Intelligent Transportation Systems, v. 19, n. 1, p. 131-139. DOI: 10.1109/TITS.2017.2750091. DOI: https://doi.org/10.1109/TITS.2017.2750091
Cunha, A.L.B.N. (2013) Sistema automático para obtenção de parâmetros do tráfego veicular a partir de imagens de vídeo usando OpenCV. Tese (doutorado). Escola de Engenharia de São Carlos, Universidade de São Paulo, São Paulo, SP. DOI: 10.11606/T.18.2013.tde-19112013-165611. DOI: https://doi.org/10.11606/T.18.2013.tde-19112013-165611
Das, S.; A.K. Budhkar; A.K. Maurya et al. (2019) Multivariate analysis on dynamic car-following data of non-lane-based traffic environments. Transportation in Developing Economies, v. 5, n. 2, p. 17. DOI: 10.1007/s40890-019-0085-5. DOI: https://doi.org/10.1007/s40890-019-0085-5
Franklin, R.J. e Mohana (2020) Traffic signal violation detection using artificial intelligence and deep learning. In Proceedings of the Fifth International Conference on Communication and Electronics Systems. New York: IEEE, p. 839-844. DOI: 10.1109/ICCES48766.2020.9137873. DOI: https://doi.org/10.1109/ICCES48766.2020.9137873
Ismail, K.; T. Sayed; N. Saunier et al. (2009) Automated analysis of pedestrian-vehicle conflicts using video data.
Transportation Research Record: Journal of the Transportation Research Board, v. 2140, n. 1, p. 44-54. DOI: 10.3141/2140-05. DOI: https://doi.org/10.3141/2140-05
Kalman, R. (1960) A new approach to linear filtering and prediction problems, Journal of Basic Engineering, v. 82, n. 1, p. 35-45. DOI: 10.1115/1.3662552. DOI: https://doi.org/10.1115/1.3662552
Kasper-Eulaers, M.; N. Hahn; S. Berger et al. (2021) Short communication: detecting heavy goods vehicles in rest areas in winter conditions using YOLOv5. Algorithms, v. 14, n. 114, p. 114. DOI: 10.3390/a14040114. DOI: https://doi.org/10.3390/a14040114
Kuhn, H.W. (1955) The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, v. 2, n. 1-2, p. 83-97. DOI: 10.1002/nav.3800020109. DOI: https://doi.org/10.1002/nav.3800020109
Leibe, B.; N. Cornelis; K. Cornelis et al. (2007) Dynamic 3D scene analysis from a moving vehicle. In: IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, p. 1-8. DOI: 10.1109/CVPR.2007.383146. DOI: https://doi.org/10.1109/CVPR.2007.383146
Luo, W.; J. Xing; A. Milan et al. (2021) Multiple object tracking: a literature review. Artificial Intelligence, v. 293, p. 103448. DOI: 10.1016/j.artint.2020.103448. DOI: https://doi.org/10.1016/j.artint.2020.103448
Munigety, C.R. e T.V. Mathew (2016) Towards behavioral modeling of drivers in mixed traffic conditions, Transportation in Developing Economies, v. 2, n. 1, p. 6. DOI: 10.1007/s40890-016-0012-y. DOI: https://doi.org/10.1007/s40890-016-0012-y
Rahman, R.; Z. Bin Azad e M.B. Hasan (2021) Densely-populated traffic detection using YOLOv5 and non-maximum suppression ensembling. In: International Conference on Big Data, IoT and Machine Learning. Singapore: Springer, p. 567-578. DOI: 10.1007/978-981-16-6636-0_43. DOI: https://doi.org/10.1007/978-981-16-6636-0_43
Redmon, J.; S. Divvala; R. Girshick et al. (2016) You Only Look Once: Unified, Real-Time Object Detection. ArXiv. DOI: 10.48550/arXiv.1506.02640. DOI: https://doi.org/10.1109/CVPR.2016.91
Rublee, E.; V. Rabaud; K. Konolige et al. (2011) ORB: an efficient alternative to SIFT or SURF. In IEEE International Conference on Computer Vision. New York: IEEE, p. 2564-2571 DOI: 10.1109/ICCV.2011.6126544. DOI: https://doi.org/10.1109/ICCV.2011.6126544
Saunier, N. e T. Sayed (2006) A feature-based tracking algorithm for vehicles in intersections. In Canadian Conference on Computer and Robot Vision. New York: IEEE, p. 59. DOI: 10.1109/CRV.2006.3. DOI: https://doi.org/10.1109/CRV.2006.3
Silva, S.M. e C.R. Jung (2018) License plate detection and recognition in unconstrained scenarios. In European Conference on Computer Vision. Germany: ECCV, p. 593-609. DOI: 10.1007/978-3-030-01258-8_36. DOI: https://doi.org/10.1007/978-3-030-01258-8_36
Tareen, S.A.K. e Z. Saleem (2018) A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK. In: International Conference on Computing, Mathematics and Engineering Technologies. New York: IEEE, p. 1–10. DOI: 10.1109/ICOMET.2018.8346440. DOI: https://doi.org/10.1109/ICOMET.2018.8346440
Tokuda, E.K.; Y. Lockerman; G.B.A. Ferreira et al. (2020) A new approach for pedestrian density estimation using moving sensors and computer vision. ACM Transactions on Spatial Algorithms and Systems, v. 6, n. 4, p. 1-20. DOI: 10.1145/3397575. DOI: https://doi.org/10.1145/3397575
Tzutalin (2015). LabelImg. Disponível em: <https://github.com/tzutalin/labelImg> (acesso em 06/03/2023).
Walha, A.; A. Wali e A.M. Alimi (2014) Video stabilization with moving object detecting and tracking for aerial video surveillance, Multimedia Tools and Applications, v. 74, n. 17, p. 6745-67. DOI: 10.1007/s11042-014-1928-z. DOI: https://doi.org/10.1007/s11042-014-1928-z
Wang, C.; A. Bochkovskiy e H.M. Liao (2022) YOLOv7: Trainable Bag-of-freebies Sets New State-of-the-Art for Real-Time Object Detectors. ArXiv DOI: 10.48550/arXiv.2207.02696. DOI: https://doi.org/10.1109/CVPR52729.2023.00721
Wojke, N. e A. Bewley (2018) Deep cosine metric learning for person re-identification. In IEEE Winter Conference on Applications of Computer Vision. New York: IEEE, p. 748-756. DOI: 10.1109/WACV.2018.00087. DOI: https://doi.org/10.1109/WACV.2018.00087
Wojke, N.; A. Bewley e D. Paulus (2017) Simple online and realtime tracking with a deep association metric. In IEEE Int.Conf. on Image Process. New York: IEEE, p. 3645-3649. DOI: 10.1109/ICIP.2017.8296962. DOI: https://doi.org/10.1109/ICIP.2017.8296962
Wu, T.; T. Wang e Y. Liu (2021) Real-time vehicle and distance detection based on improved Yolo v5 network. In World Symposium on Artificial Intelligence. New York: IEEE, p. 24-28. DOI: 10.1109/WSAI51899.2021.9486316. DOI: https://doi.org/10.1109/WSAI51899.2021.9486316
Zhao, Z.; P. Zheng; S. Xu et al. (2019) Object detection with deep learning: a review. IEEE Transactions on Neural Networks and Learning Systems, v. 30, n. 11, p. 3212-32. DOI: 10.1109/TNNLS.2018.2876865. PMid:30703038. DOI: https://doi.org/10.1109/TNNLS.2018.2876865
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Alessandro Macêdo de Araújo, Thiago Passos Oliveira, Manoel Mendonça de Castro Neto, Diêgo Farias de Oliveira, João Paulo Pordeus Gomes
![Creative Commons License](http://i.creativecommons.org/l/by/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who submit papers for publication by TRANSPORTES agree to the following terms:
- Authors retain copyright and grant TRANSPORTES the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors may enter into separate, additional contractual arrangements for the non-exclusive distribution of this journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in TRANSPORTES.
- Authors are allowed and encouraged to post their work online (e.g., in institutional repositories or on their website) after publication of the article. Authors are encouraged to use links to TRANSPORTES (e.g., DOIs or direct links) when posting the article online, as TRANSPORTES is freely available to all readers.
- Authors have secured all necessary clearances and written permissions to published the work and grant copyright under the terms of this agreement. Furthermore, the authors assume full responsibility for any copyright infringements related to the article, exonerating ANPET and TRANSPORTES of any responsibility regarding copyright infringement.
- Authors assume full responsibility for the contents of the article submitted for review, including all necessary clearances for divulgation of data and results, exonerating ANPET and TRANSPORTES of any responsibility regarding to this aspect.