El presente trabajo de investigación tiene por objetivo calcular mediante la utilización de visión por computador la densidad vehicular de las ciudades. Para llevar a cabo el estudio, se procedió a capturar vídeos del tráfico vehicular en 8 intersecciones de la ciudad de Loja por medio de un dron y una cámara de alta resolución. Posteriormente se utilizó el lenguaje python y la librería YOLOv8 para realizar el conteo de vehículos de diferentes categorías como son vehículos livianos, pesados y motos. Por medio de fórmulas matemáticas utilizadas en ingeniería de tráfico se obtuvieron los valores de la densidad vehicular, tasa de flujo vehicular y espaciamiento promedio. Como resultados tenemos que el modelo de aprendizaje automático utilizando YOLOv8 tiene una precisión micro del 90% en la detección y clasificación de vehículos, y gracias a su uso se identificó la vía de mayor densidad vehicular. Las aplicaciones prácticas del presente trabajo podrían mejorar el flujo vehicular y ayudar a la toma de decisiones a los organismos competentes relacionados con la gestión del tránsito.
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
Referencias
Ansariyar, A., & Taherpour, A. (2023). Statistical analysis of vehicle-vehicle conflicts with a LIDAR sensor in a signalized intersection. Advances in transportation studies, 60.
Alexandrova, S., Tatlock, Z., & Cakmak, M. (2015, May). RoboFlow: A flow-based visual programming language for mobile manipulation tasks. In 2015 IEEE International Conference on Robotics and Automation (ICRA) (pp. 5537-5544). IEEE.
Cal y Mayor, R., & Cárdenas, J. (2018). “Ingeniería de Tránsito”. Editorial Alfaomega. 9na. edición.
Chek, X. & Uttraphan, C. (2023). 3D Geometric Shape Recognition System using YOLO v8 Implemented on Raspberry Pi. Evolution in Electrical and Electronic Engineering, 4(2), 158-164.
Deepa, D., Sivasangari, A., Roonwal, R., & Nayan, R. (2023). Pothole Detection using Roboflow Convolutional Neural Networks. In 2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS) (pp. 560-564). IEEE.
Dehghani, M., Gritsenko, A., Arnab, A., Minderer, M., & Tay, Y. (2022). Scenic: AJAX library for computer vision research and beyond. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 21393-21398).
Gao, G., Gao, J., Liu, Q., Wang, Q., & Wang, Y. (2020). Cnn-based density estimation and crowd counting: A survey. arXiv preprint arXiv:2003.12783.
Grumiaux, P. A., Kitić, S., Girin, L., & Guérin, A. (2022). A survey of sound source localization with deep learning methods. The Journal of the Acoustical Society of America, 152(1), 107-151.
Guo, M. H., Xu, T. X., Liu, J. J., Liu, Z. N., Jiang, P. T., Mu, T. J., ... & Hu, S. M. (2022). Attention mechanisms in computer vision: A survey. Computational visual media, 8(3), 331-368.
Hasanvand, M., Nooshyar, M., Moharamkhani, E., & Selyari, A. (2023). Machine learning methodology for identifying vehicles using image processing. In Artificial Intelligence and Applications (Vol. 1, No. 3, pp. 170-178).
Hassaballah, M., & Awad, A. I. (Eds.). (2020). Deep learning in computer vision: principles and applications. CRC Press.
Jocher, G., Stoken, A., Chaurasia, A., Borovec, J., Kwon, Y., Michael, K., ... & Thanh Minh, M. (2021). ultralytics/yolov5: v6. 0-YOLOv5n'Nano'models, Roboflow integration, TensorFlow export, OpenCV DNN support. Zenodo.
Kilic, E., & Ozturk, S. (2023). An accurate car counting in aerial images based on convolutional neural networks. Journal of Ambient Intelligence and Humanized Computing, 1-10.
Liu, Y., Sun, P., Wergeles, N., & Shang, Y. (2021). A survey and performance evaluation of deep learning methods for small object detection. Expert Systems with Applications, 172, 114602.
Madhavi, G., Bhavani, A., Reddy, Y., Kiran, A., Chitra, N., & Reddy, P. (2023). Traffic Congestion Detection from Surveillance Videos using Deep Learning. In 2023 International Conference on Computer, Electronics & Electrical Engineering & their Applications (IC2E3) (pp. 1-5). IEEE.
Pillai, A. (2023). Traffic Surveillance Systems through Advanced Detection, Tracking, and Classification Technique. International Journal of Sustainable Infrastructure for Cities and Societies, 8(9), 11-23.
Pineda-Perdomo, G. A., & Villatoro-Flores, H. F. (2023, December). Implementation of a Computer Vision System for Fault and Component Analysis of Computer PCBs. In 2023 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT) (pp. 1-6). IEEE.
Rouf, M., Wu, Q., Yu, X., Iwahori, Y., Wu, H., & Wang, A. (2023). Real-time vehicle detection, tracking and counting system based on YOLOv7. Embedded Selforganising Systems, 10(7), 4-8.
Sohan, M., Sai Ram, T., Reddy, R., & Venkata, C. (2024). A review on yolov8 and its advancements. In International Conference on Data Intelligence and Cognitive Informatics (pp. 529-545). Springer, Singapore.
Talebi, H., & Milanfar, P. (2021). Learning to resize images for computer vision tasks. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 497-506).
Wang, P., Li, P., & Chowdhury, F. R. (2022). Development of an adaptive traffic signal control framework for urban signalized interchanges based on infrastructure detectors and CAV technologies. Journal of Transportation Engineering, Part A: Systems, 148(4), 04022004.
Won, M. (2020). Intelligent traffic monitoring systems for vehicle classification: A survey. IEEE Access, 8, 73340-73358.
Yuan, X., Shi, J., & Gu, L. (2021). A review of deep learning methods for semantic segmentation of remote sensing imagery. Expert Systems with Applications, 169, 114417.
Zhang, J., Xiao, W., Coifman, B., & Mills, J. P. (2020). Vehicle tracking and speed estimation from roadside lidar. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 5597-5608.