VARVO: un Método Novedoso para la Detección Rápida de Eventos de Choques de Vehículos a Partir de Solo Datos de Video

##plugins.themes.bootstrap3.article.main##

Mario Moreno Pallares

Sang Guun Yoo

Wilbert Geovanny Aguilar Castillo


Palabras clave:
Applications of AI, Computer Vision, Machine learning, Traffic incidents Aplicaciones de la IA, Visión Computacional, Aprendizaje Automático, Incidentes de Tráfico

Resumen

Alrededor de 1,35 millones de personas a nivel mundial mueren anualmente por incidentes de tráfico y se estima que 50 millones sufren lesiones graves. Este panorama es particularmente dramático en la Región Andina donde el número de muertes por accidentes de tránsito asciende a 127 muertes por millón de habitantes. Recientemente, el despliegue de Sistemas Inteligentes de Transporte (SITs) en países desarrollados ha ayudado a reducir la mortalidad por accidentes de tránsito. Una parte integral de un SIT es la detección automática de incidentes de tráfico a partir de datos de video y sensores. Sin embargo, la escasez de conjuntos de datos, especialmente de casos positivos de incidentes de tráfico, obstaculizan el desarrollo de aplicaciones de inteligencia artificial para el dominio de la investigación del tráfico. En este contexto, presentamos la siguiente pregunta de investigación: ¿Es posible detectar colisiones de automóviles mediante aprendizaje automático supervisado, basado en la velocidad estimada de los autos a partir de datos de video? Como resultado presentamos VARVO, un algoritmo para la detección de incidentes de tráfico que no depende de sensores para la detección de la velocidad de los automóviles, el cual realiza una clasificación supervisada usando la detección de objetos basada en red convolucional y seguimiento bidireccional. También se describe cómo los modelos implementados en VARVO pueden mejorar su precisión de clasificación aplicando un algoritmo de sobremuestreo para clases desequilibradas. Creemos que el despliegue de VARVO podría vincularse a cámaras de video estáticas de tráfico y ser parte de los SITs en la Región Andina.

Descargas

Descargas

Los datos de descargas todavía no están disponibles.




Detalles del artículo

Biografías de los autores/as

Sang Guun Yoo, Escuela Politécnica Nacional, Departamento de Informática y Ciencias de la Computación, Quito, Ecuador

(Senior Member, IEEE) received the Ph.D. degree from the Department of Computer Science and Engineering, Sogang University, Seoul, South Korea, in 2013. He is one of the co-founders of ExtremoSoftware, where he has worked as the CTO, from 2001 to 2005. From 2005 to 2007, he has collaborated as a Professor with the Department of Computer Science and Multimedia, International University of Ecuador. He is currently a Professor with the Departamento de Informática y Ciencias de la Computación, Escuela Politécnica Nacional. He is also a National Contact Point of European Commission’s H2020 Programme and a Senior Member of SCIEI.

Wilbert Geovanny Aguilar Castillo, Escuela Politécnica Nacional, Departamento de Informática y Ciencias de la Computación, Quito, Ecuador

received the Ph.D. degree from the Department of Systems Engineering, Automation and Industrial Informatics, Universitat Politècnica de Catalunya UPC-BarcelonaTech, Barcelona, Spain, in 2015. He worked as a linked researcher at BarcelonaTech. He has collaborated as a Doctoral and Master's Degree Professor with the Department of Informatics and Computer Science, National Polytechnic School, Ecuador. He was also a Professor of Master's degree at Higher Polytechnic School of Chimborazo. He is currently a Professor with the Department of Electrical, Electronic and Telecommunications, Armed Forces University, Ecuador. He was also a Professor of Master's degree at Higher Polytechnic School of Chimborazo.

Citas

Cheng, G., Zhou, P., & Han, J. (2016). Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 54(12), 7405–7415. https://doi.org/10.1109/TGRS.2016.2601622

Dalve, S., & Pinto, A. (2015). Estrategia de Seguridad Vial. Banco Interamericano de Desarrollo, 201. https://doi.org/10.1177/002088170704400203

Danelljan, M., Häger, G., Khan, F. S., & Felsberg, M. (2014). Accurate Scale Estimation for Robust Visual Tracking. BMVC 2014 - Proceedings of the British Machine Vision Conference 2014. https://doi.org/10.5244/c.28.65

Dhaya, R. (2020). CCTV Surveillance for Unprecedented Violence and Traffic Monitoring. Journal of Innovative Image Processing, 2(1), 25–34. https://doi.org/10.36548/jiip.2020.1.003

Dr. Chen personal webpage. (2019). Charlotte University Faculty Webpages. Retrieved January 30, 2023, from https://webpages.charlotte.edu/cchen62/dataset.html

Festag, A. (2014). Cooperative intelligent transport systems standards in Europe. IEEE Communications Magazine, 52(12), 166–172. https://doi.org/10.1109/MCOM.2014.6979970

Géron, A. (2017). Hands-on machine learning with Scikit-Learn and TensorFlow : concepts, tools, and techniques to build intelligent systems. In O'Reilly Media

Granada, I. (2018). Sistemas inteligentes de transporte para la movilidad universal. Bid. http://dx.doi.org/10.18235/0001390

Han, Z., Liang, J., & Li, J. (2018). Design of Intelligent Road Recognition and Warning System for Vehicles Based on Binocular Vision. IEEE Access, 6, 62880–62889. https://doi.org/10.1109/ACCESS.2018.2876702

Haydari, A., & Yilmaz, Y. (2020). Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey. IEEE Transactions on Intelligent Transportation Systems, 1–22. https://doi.org/10.1109/tits.2020.3008612

Jurewicz, C., Sobhani, A., Woolley, J., Dutschke, J., & Corben, B. (2016). Exploration of Vehicle Impact Speed - Injury Severity Relationships for Application in Safer Road Design. Transportation Research Procedia, 14, 4247–4256. https://doi.org/10.1016/j.trpro.2016.05.396

Kurdthongmee, W. (2020). A comparative study of the effectiveness of using popular DNN object detection algorithms for pith detection in cross-sectional images of parawood. Heliyon, 6(2), e03480. https://doi.org/10.1016/j.heliyon.2020.e03480

Kyamakya, K. (2006). Artificial intelligence in Transportation Telematics. OGAI Journal (Oesterreichische Gesellschaft Fuer Artificial Intelligence), 25(3), 2–4.

Maldonado Silveira Alonso Munhoz, P. A., da Costa Dias, F., Kowal Chinelli, C., Azevedo Guedes, A. L., Neves dos Santos, J. A., da Silveira e Silva, W., & Pereira Soares, C. A. (2020). Smart mobility: The main drivers for increasing the intelligence of urban mobility. Sustainability, 12(24), 10675. https://doi.org/10.3390/su122410675

Mohammed, R., Rawashdeh, J., & Abdullah, M. (2020). Machine Learning with Oversampling and Undersampling Techniques: Overview Study and Experimental Results. 2020 11th International Conference on Information and Communication Systems, ICICS 2020, April, 243–248. https://doi.org/10.1109/ICICS49469.2020.239556

Nascimento, J. C., Abrantes, A. J., & Marques, J. S. (1999). Algorithm for centroid-based tracking of moving objects. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 6(1), 3305–3308. https://doi.org/10.1109/icassp.1999.757548

Organización Panamericana de la Salud, & Organización Mundial de la Salud. (2019). Estado de la seguridad vial en la Región de las Américas. https://www.paho.org/hq/index.php?option=com_content&view=article&id=15237:status-of-road-safety-in-the-region-of-the-americas-2019&Itemid=39873&lang=es

Owens, N., Armstrong, A., Sullivan, P., Mitchell, C., Newton, D., Brewster, R., & Trego, T. (2010). Traffic Incident Management Handbook. Science Applications International Corporation American Transportation Research Institute, January 2010, 1–116. https://doi.org/10.1093/her/cys022

Rajib, M. S., Ahmed, J., Rahman, M. M., Abdullah, W. M., & Chauhan, N. S. (2017). A proposed system to estimate the velocity of vehicles from traffic video. Proceedings of the International Conference on IoT in Social, Mobile, Analytics, and Cloud, I-SMAC 2017, 320–324. https://doi.org/10.1109/I-SMAC.2017.8058364

Salazar-Cabrera, R., & Pachón, Á. (2019). Metodología para el Diseño de una Arquitectura de un Sistema Inteligente de Transporte para una Ciudad Intermedia Colombiana. Ingeniería y Competividad, 21(1), 47-61. https://doi.org/10.25100/iyc.v21i1.7654

Santos, M. S., Soares, J. P., Abreu, P. H., Araujo, H., & Santos, J. (2018). Cross-validation for imbalanced datasets: Avoiding overoptimistic and overfitting approaches [Research Frontier]. IEEE Computational Intelligence Magazine, 13(4), 59–76. https://doi.org/10.1109/MCI.2018.2866730

Shah, A. (2016). Videos for the Car Accidents Detection and Prediction Dataset. Google Drive. https://drive.google.com/drive/folders/1ozfZbz8wRoNqKknC59IPXP_twKgmCOaA

Shah, A., Lamare, J. B., Anh, T. N., & Hauptmann, A. (2018). CADP: A Novel Dataset for CCTV Traffic Camera-based Accident Analysis. http://arxiv.org/abs/1809.05782

Sultani, W., Chen, C., & Shah, M. (2018). Real-world Anomaly Detection in Surveillance Videos. http://arxiv.org/abs/1801.04264

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2019). Going Deeper with Convolutions. Designing and Tracking Knowledge Management Metrics, 163–182. https://doi.org/10.1108/978-1-78973-723-320191012

Thomas, S. S., Gupta, S., & Subramanian, V. K. (2017). Event Detection on Roads Using Perceptual Video Summarization. 1–11.

Vadeby, A., & Forsman, Å. (2018). Traffic safety effects of new speed limits in Sweden. Accident Analysis and Prevention, 114, 34–39. https://doi.org/10.1016/j.aap.2017.02.003

Vallejos, S., Alonso, D. G., Caimmi, B., Berdun, L., Armentano, M. G., & Soria, Á. (2021). Mining social networks to detect traffic incidents. Information systems frontiers, 23(1), 115-134. https://doi.org/10.1007/s10796-020-09994-3

Vapnik, V. N. (2013). Empirical Inference - Semi-supervised learning in causal and anti-causal settings.