Analysis of delays and accepted gaps in signalized crossings: a study in Fortaleza using deep learning computer vision techniques
DOI:
https://doi.org/10.58922/transportes.v31i2.2845Keywords:
Pedestrians crossings, Delay, Accepted gap, Computer visionAbstract
The increasing attention to active transport in developing countries has motivated studies on understanding the factors that affect its users. Delay is one of the main indicators of the level of service of pedestrian crossings and it is affected by the available gaps. This work aims to relate delays and accepted gaps in signalized crossings in Fortaleza, as well as to compare the estimated delays with those obtained by the method of the Highway Capacity Manual – 6th. edition. The data were collected by means of computer vision algorithms, in five crossing located at signalized intersections, resulting in 1642 crossing observations. The method includes a cluster analysis of delay and accepted gap. The results showed similarity of the estimated delays with those obtained with the HCM. Also, the relationship between accepted gap and delay allows an inference about the risk of pedestrian crossings.
Downloads
References
Alhajyaseen, W.K.M. e M. Iryo-Asano (2017) Studying critical pedestrian behavioral changes for the safety assessment at signalized crosswalks. Safety Science, v. 91, p. 351-60. DOI: 10.1016/j.ssci.2016.09.002. DOI: https://doi.org/10.1016/j.ssci.2016.09.002
Alver, Y.; P. Onelcin; A. Cicekli et al. (2021) Evaluation of pedestrian critical gap and crossing speed at midblock crossing using image processing. Accident; Analysis and Prevention, v. 156, n. April, p. 106127. DOI: 10.1016/j.aap.2021.106127. PMid:33865175. DOI: https://doi.org/10.1016/j.aap.2021.106127
Bochkovskiy, A.; C. Wang e H.M. Liao (2020) YOLOv4: Optimal Speed and Accuracy of Object Detection. Disponível em: <http://arxiv.org/abs/2004.10934> (acesso em 04/04/2023).
Forgy, E. (1965) Cluster analysis of multivariate data: efficiency versus interpretability of classifications. Biometrics, v. 21, p. 768-80.
GitHub (2020) theAIGuysCode/yolov4-deepsort. Disponível em: <https://github.com/theAIGuysCode/yolov4- deepsort> (acesso em 13/04/2023).
Jacobsen, A.C. (2011) Microssimulação da travessia de pedestres. Dissertação (mestrado). Universidade Federal do Rio Grande do Sul, Porto Alegre. Disponível em: <https://www.lume.ufrgs.br/handle/10183/32007> (acesso em 04/04/2023).
Li, Q.; Z. Wang; J. Yang et al. (2005) Pedestrian delay estimation at signalized intersections in developing cities. Transportation Research Part A, Policy and Practice, v. 39, n. 1, p. 61-73. DOI: 10.1016/j.tra.2004.11.002. DOI: https://doi.org/10.1016/j.tra.2004.11.002
Lipovac, K.; M. Vujanic; B. Maric et al. (2013) Pedestrian behavior at signalized pedestrian crossings. Journal of Transportation Engineering, v. 139, n. 2, p. 165-72. DOI: 10.1061/(ASCE)TE.1943-5436.0000491. DOI: https://doi.org/10.1061/(ASCE)TE.1943-5436.0000491
Liu, R.; J.P. Silva e A.J. Seco (2000) A bi-modal micro-simulation tool for the assessment of pedestrian delas and traffic management. In 9th International Association of Travel Behavior Research Conference. Gold Coast, Australia: University of Sydney.
Ma, W.; D. Liao; Y. Liu et al. (2015) Optimization of pedestrian phase patterns and signal timings for isolated intersection. Transportation Research Part C, Emerging Technologies, v. 58, p. 502-14. DOI: 10.1016/j.trc.2014.08.023. DOI: https://doi.org/10.1016/j.trc.2014.08.023
Al Malki, A.; M.M. Rizk; M.A. El-Shorbagy et al. (2016) Hybrid genetic algorithm with K-means for clustering problems. Open Journal of Optimization, v. 5, n. 2, p. 71-83. DOI: 10.4236/ojop.2016.52009. DOI: https://doi.org/10.4236/ojop.2016.52009
Martín, L.E.; T.P. Bandeira; L.D.G. Pinto et al. (2019) Atraso de pedestres em travessias semaforizadas: uma comparação entre as modelagens pelo HCM e pelo microssimulador VISSIM. Transportes, v. 27, n. 1, p. 128-40. DOI: 10.14295/transportes.v27i1.1581. DOI: https://doi.org/10.14295/transportes.v27i1.1581
Mesquita, K.G.A.; F.A.B. Castro Jr e M.G. H. Cunha (2020) Caracterização de pedestres obedientes e oportunistas em travessias semaforizadas de Fortaleza. In Associação Nacional de Pesquisa e Ensino em Transportes (ed.) 34o Congresso de Pesquisa e Ensino em Transporte da ANPET. 100% digital: ANPET, p. 2474-2485. DOI: https://doi.org/10.36229/978-65-5866-111-5.CAP.07
Mohamad Nor, S.N.; B. David Daniel; R. Hamidun et al. (2017) Analysis of pedestrian gap acceptance and crossing decision in Kuala Lumpur. In: MATEC Web of Conferences. Melaka, Malaysia: EDP Sciences. DOI: 10.1051/matecconf/201710308014 DOI: https://doi.org/10.1051/matecconf/201710308014
Redmon, J., e A. Farhadi (2018) YOLOv3: an incremental improvement. Computer Vision and Pattern Recognition. DOI: 10.48550/arXiv.1804.02767
Rouphail, N.; J. Hummer; J. Milazzo et al. (1998) Recommended procedures – Chapeter 13: Pedestrians. In: Transportation Research Board (ed.), Highway Capacity Manual. Washington, DC: Transportation Research Board. (Report FHWA-RD-98-107).
Suh, W.; D. Henclewood; A. Greenwood et al. (2013) Modeling pedestrian crossing activities in an urban environment using microscopic traffic simulation. Simulation, v. 89, n. 2, p. 213-24. DOI: 10.1177/0037549712469843. DOI: https://doi.org/10.1177/0037549712469843
Tang, L.; Y. Liu; J.L. Li et al. (2020) Pedestrian crossing design and analysis for symmetric intersections: efficiency and safety. Transportation Research Part A, Policy and Practice, v. 142, p. 187-206. DOI: 10.1016/j.tra.2020.10.012. DOI: https://doi.org/10.1016/j.tra.2020.10.012
TRB (2016) Highway Capacity Manual (6th ed.). Washington, DC: Transportation Research Board.
Wang, C., A. Bochkovskiy e H.M. Liao (2021) Scaled-YOLOv4: Scaling Cross Stage Partial Network. Disponível em: <https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_ScaledYOLOv4_Scaling_Cross_Stage_Partial_Network_CVPR_2021_paper.pdf> (acesso em 13/04/2023). DOI: https://doi.org/10.1109/CVPR46437.2021.01283
Wang, X. e Z. Tian (2010) Pedestrian delay at signalized intersections with a two-stage crossing design. Transportation Research Record: Journal of the Transportation Research Board, v. 2173, n. 1, p. 133-8. DOI: 10.3141/2173-16. DOI: https://doi.org/10.3141/2173-16
Wojke, N. e A. Bewley (2018) Deep cosine metric learning for person re-identification. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). Lake Tahoe, NV, USA: 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 International Conference on Image Processing.Beijing, China: IEEE, p. 3645-3649. DOI: 10.1109/ICIP.2017.8296962 DOI: https://doi.org/10.1109/ICIP.2017.8296962
Zhang, S.; M. Abdel-Aty; J. Yuan et al. (2020) Prediction of pedestrian crossing intentions at intersections based on long short-term memory recurrent neural network. Transportation Research Record: Journal of the Transportation Research Board, v. 2674, n. 4, p. 57-65. DOI: 10.1177/0361198120912422. DOI: https://doi.org/10.1177/0361198120912422
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Francisco Altanizio Batista de Castro Junior, Manoel Mendonça de Castro Neto, Flávio José Craveiro Cunto
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.
