Design and implementation of an application for the detection and recognition of speed limit signs
DOI:
https://doi.org/10.59540/tech.vi5.115Keywords:
Image and video processing, Velocity signal, OpenCV, Machine Vision, CimgAbstract
An analysis was conducted on the application designed to provide a driving assistance solution for the timely detection of traffic signs, specifically speed signs, enabling a timely response by the driver. The objective of this article is to present the design, implementation, and validation of a functional application capable of detecting and recognizing speed limit signs from image or video files or a real-time video stream. The methodology used consists of four processes: image acquisition, image and video processing, sign and speed detection and control, and results visualization. The application was developed in Eclipse using C++ code, using OpenCV image and video processing libraries. Based on the results obtained from the implemented application, optimal performance was achieved, with an accuracy of almost 90% and an error rate of around 1%. In addition, detection difficulties and errors were analyzed, and processing time statistics were established in relation to the characteristics of the hardware used.
Downloads
References
World Health Organization, Global status report on road safety 2018. Geneva, Switzerland: WHO, 2018.
A. Ziebinski, R. Cupek, D. Grzejszczak, and M. Podpora, "A Survey of Advanced Driver-Assistance Systems (ADAS)," 2016 International Conference on Signals and Electronic Systems (ICSES), Krakow, Poland, 2016, pp. 1-6. doi: 10.1109/ICSES.2016.7594341.
G. Bradski and A. Kaehler, Learning OpenCV: Computer Vision with the OpenCV Library. Sebastopol, CA, USA: O'Reilly Media, 2008.
J. A. H. R. Putra, D. A. D. Dewantara, and T. H. N. T. Putri, "Real-time traffic sign recognition system using OpenCV," 2017 International Conference on Sustainable Information Engineering and Technology (SIET), Malang, Indonesia, 2017, pp. 199-203. doi: 10.1109/SIET.2017.8304126.
A. Mogelmose, M. M. Trivedi, and T. B. Moeslund, "Vision-based traffic sign detection and analysis for intelligent driver assistance systems: A survey," IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 4, pp. 1484-1497, Dec. 2012. doi: 10.1109/TITS.2012.2209421.
F. Zaklouta and B. Stanciulescu, "Real-time traffic sign recognition in three stages," Robotics and Autonomous Systems, vol. 62, no. 1, pp. 16-24, Jan. 2014.
J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, "The German Traffic Sign Recognition Benchmark: A multi-class classification competition," The 2011 International Joint Conference on Neural Networks, San Jose, CA, USA, 2011, pp. 1453-1460. doi: 10.1109/IJCNN.2011.6033389.
D. Cireşan, U. Meier, J. Masci, and J. Schmidhuber, "Multi-column deep neural network for traffic sign classification," Neural Networks, vol. 32, pp. 333-338, Aug. 2012.
Y. Li, S. Liu, and H. Wang, "Traffic Sign Recognition Based on Convolutional Neural Network," 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP), Wuxi, China, 2019, pp. 496-500. doi: 10.1109/SIPROCESS.2019.8868623.
S. S. Ardiansyah, E. A. Suprayitno, and D. P. H. Saptomo, "A real-time speed limit sign recognition on embedded system," 2017 4th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), Yogyakarta, Indonesia, 2017, pp. 1-6. doi: 10.1109/EECSI.2017.8239129.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Roberto Alejandro Larrea Luzuriaga, Cristina Alejandra Orozco Cazco
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
El modelo de publicación adoptado por esta revista se fundamenta en el compromiso con la difusión del conocimiento científico bajo estándares de integridad y acceso abierto. En este sentido, todos los artículos y contenidos se distribuyen bajo una licencia Creative Commons Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0). Esta normativa legal permite que las obras sean compartidas, descargadas y difundidas libremente, siempre que se cumplan de manera estricta las condiciones de uso establecidas por la organización internacional Creative Commons.
La implementación de esta licencia implica tres pilares fundamentales para la protección y el uso de la producción académica. En primer lugar, la Atribución exige que se otorgue el crédito correspondiente a los autores originales y se proporcione un enlace a la licencia, indicando si se han realizado menciones de la fuente de manera adecuada. En segundo lugar, el carácter No Comercial restringe el uso de los contenidos para fines que busquen un beneficio económico o una contraprestación comercial. Finalmente, la cláusula Sin Derivadas prohíbe la distribución de material modificado, remezclado o transformado; los artículos deben circular en su forma original para preservar la fidelidad de los datos y los argumentos presentados por los investigadores.
Este marco jurídico busca equilibrar la máxima visibilidad de los hallazgos científicos con la salvaguarda de la autoría, asegurando que la información técnica y académica no sea alterada ni explotada comercialmente por terceros. Al publicar bajo estos términos, la revista garantiza que el conocimiento permanezca accesible para la comunidad global, fomentando un ecosistema de aprendizaje basado en la evidencia y el respeto a la propiedad intelectual.
