Keywords
Ecuador
accidentes
ð¾ð‘šâˆ’ð‘šð‘’ð‘Žð‘›ð‘
ð¾âˆ’ð‘ð‘
SVM
HOG.
How to Cite
Abstract
En el mundo y en el Ecuador, las altas tasas de accidentes de tráfico son generadas, principalmente, por la falta de respeto a la normativa vial por parte de los usuarios viales, generando costos humanos y materiales de importancia. En este sentido, la localización y el reconocimiento de las señales de tráfico es esencial para la construcción de dispositivos capaces de prevenir situaciones que puedan generar accidentes de tráfico. Por lo tanto, en este trabajo se presenta un nuevo enfoque para la construcción de un sistema para la detección de señales de tráfico, usando las siguientes innovaciones, i) un método de segmentación por color para la generación de regiones de interés (ROIs) basado en los algoritmos ð‘˜âˆ’ð‘ð‘, con ð¾ð‘šâˆ’ð‘šð‘’ð‘Žð‘›ð‘ , ii) una nueva versión del descriptor HOG (Histograms of oriented gradients) para la extracción de características, y iii) el entrenamiento del algoritmo SVM no-lineal para multi-clasificación. El enfoque propuesto ha sido probado sobre las señales de tráfico ecuatorianas de Pare y Ceda el Paso. Un sinnúmero de experimentos han sido desarrollados sobre varias secuencias de videos capturadas con vehículo experimental en condiciones reales de conducción en varias ciudades ecuatorianas, bajo diferentes condiciones de iluminación como son normal, soleado y nublado. Este sistema ha mostrado un rendimiento de 98.7% para la segmentación, 99.49% para la clasificación y una precisión del 96% para la detección.
References
World Economic Forum. (2016). Global competitiveness report 2015-2016. Competitiveness rankings. A. transport infrastructure. Recuperado el 12 de noviembre de 2017 de: http://reports.weforum.org/global-competitiveness-report-2015-2016/competitiveness-rankings/#indicatorId=GCI.A.02.01
Agencia Nacional de Tránsito del Ecuador. (2015) Siniestros octubre 2015. Recuperado el 12 de diciembre de 2017 de: http://www.ant.gob.ec/index.php/descargable/file/3265-siniestros-octubre-2015
Nguyen, B. T., Ryong, S. J., & Kyu, K. J. (2014, Julio). Fast traffic sign detection under challenging conditions. In Audio, Language and Image Processing (ICALIP), 2014 International Conference on (pp. 749-752). IEEE.
Shaout, A., Colella, D., & Awad, S. (2011, Diciembre). Advanced driver assistance systems-past, present and future. In Computer Engineering Conference (ICENCO), 2011 Seventh International(pp. 72-82). IEEE.
Møgelmose, A., Liu, D., & Trivedi, M. M. (2015). Detection of US traffic signs. IEEE Transactions on Intelligent Transportation Systems, 16(6), 3116-3125.
Perez-Perez, S. E., Gonzalez-Reyna, S. E., Ledesma-Orozco, S. E., & Avina-Cervantes, J. G. (2013, November). Principal component analysis for speed limit Traffic Sign Recognition. In Power, Electronics and Computing (ROPEC), 2013 IEEE International Autumn Meeting on (pp. 1-5). IEEE.
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.
R. Duda, P. Hart, and D. Stork. (2001). Pattern Classification, 2nd ed., 2001.
Cristianini, N., & Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge university press.
Salti, S., Petrelli, A., Tombari, F., Fioraio, N., & Di Stefano, L. (2015). Traffic sign detection via interest region extraction. Pattern Recognition, 48(4), 1039-1049.
Li, H., Sun, F., Liu, L., & Wang, L. (2015). A novel traffic sign detection method via color segmentation and robust shape matching. Neurocomputing, 169, 77-88.
Hastie, T., Tibshirani, R., & Friedman, J. (2009). Unsupervised learning. In The elements of statistical learning (pp. 485-585). Springer, New York, NY.
Lillo-Castellano, J. M., Mora-Jiménez, I., Figuera-Pozuelo, C., & Rojo-Álvarez, J. L. (2015). Traffic sign segmentation and classification using statistical learning methods. Neurocomputing, 153, 286-299.
Chen, T., & Lu, S. (2016). Accurate and Efficient Traffic Sign Detection Using Discriminative AdaBoost and Support Vector Regression. IEEE Trans. Vehicular Technology, 65(6), 4006-4015.
Han, Y., Virupakshappa, K., & Oruklu, E. (2015, Mayo). Robust traffic sign recognition with feature extraction and k-NN classification methods. In Electro/Information Technology (EIT), 2015 IEEE International Conference on (pp. 484-488). IEEE.
Huang, Z., Yu, Y., & Gu, J. (2014, Junio). A novel method for traffic sign recognition based on extreme learning machine. In Intelligent Control and Automation (WCICA), 2014 11th World Congress on (pp. 1451-1456). IEEE.
Dalal, N. (2006). Finding people in images and videos (Doctoral dissertation, Institut National Polytechnique de Grenoble-INPG).
Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008). Speeded-up robust features (SURF). Computer vision and image understanding, 110(3), 346-359.
Lau, M. M., Lim, K. H., & Gopalai, A. A. (2015, Julio). Malaysia traffic sign recognition with convolutional neural network. In 2015 IEEE International Conference on Digital Signal Processing (DSP) (pp. 1006-1010). IEEE.
Zhu, Y., Zhang, C., Zhou, D., Wang, X., Bai, X., & Liu, W. (2016). Traffic sign detection and recognition using fully convolutional network guided proposals. Neurocomputing, 214, 758-766.
Caliński, T., & Harabasz, J. (1974). A dendrite method for cluster analysis. Communications in Statistics-theory and Methods, 3(1), 1-27.
Davies, D. L., & Bouldin, D. W. (1979). A cluster separation measure. IEEE transactions on pattern analysis and machine intelligence, (2), 224-227.
Tibshirani, R., Walther, G., & Hastie, T. (2001). Estimating the number of clusters in a data set via the gap statistic. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 63(2), 411-42
Rousseeuw, P. J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of computational and applied mathematics, 20, 53-65.
T. Fawcett. (2004). "Roc graphs: Notes and practical considerations for researchers," Machine learning, vol. 31, no. 1, pp. 1-38.
Pajares Martinsanz, G., García, C., & Jesús, M. (2002). Visión por computador: Imágenes digitales y aplicaciones.
Dalal, N., & Triggs, B. (2005, Junio). Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on (Vol. 1, pp. 886-893). IEEE.
Kohavi, R. (1995, Agosto). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Ijcai(Vol. 14, No. 2, pp. 1137-1145).
Martin, A., Doddington, G., Kamm, T., Ordowski, M., & Przybocki, M. (1997). The DET curve in assessment of detection task performance. National Inst of Standards and Technology Gaithersburg MD.
Gómez-Moreno, H., Maldonado-Bascón, S., Gil-Jiménez, P., & Lafuente-Arroyo, S. (2010). Goal evaluation of segmentation algorithms for traffic sign recognition. IEEE Transactions on Intelligent Transportation Systems, 11(4), 917-930.
Zuo, Z., Yu, K., Zhou, Q., Wang, X., & Li, T. (2017, June). Traffic signs detection based on faster R-CNN. In Distributed Computing Systems Workshops (ICDCSW), 2017 IEEE 37th International Conference on (pp. 286-288). IEEE.
Mobileye. (2018). ADAS - Mobileye. Recuperado el 12 de noviembre de 2017 de: https://www.mobileye.com/our-technology/adas/
Continental-automotive.com. (2018). Continental Automotive. Recuperado el 12 de noviembre de 2017 de: https://www.continental-automotive.com/en-gl/Passenger-Cars/Chassis-Safety/Advanced-Driver-Assistance-Systems/Driving-Functions/Traffic-Sign-Assist
Shi, J. H., & Lin, H. Y. (2017, Junio). A vision system for traffic sign detection and recognition. In Industrial Electronics (ISIE), 2017 IEEE 26th International Symposium on (pp. 1596-1601). IEEE.
Copyright notice
Authors who publish in the journal ACI Avances en Ciencias e Ingenierías accept the following terms:
- The authors will retain their copyright and guarantee the journal the right of first publication of their work, which will be simultaneously subject to the Creative Commons Attribution License that allows third parties to share the work provided that its author and its first publication in this journal is indicated.
- Authors may adopt other non-exclusive license agreements for the distribution of the published version of the work, thereby being able to publish it in a monographic volume or reproduce it in other ways, provided that the initial publication in this journal is indicated.
- Authors are permitted and advised to disseminate their work over the Internet:
- Before submission to the journal, authors can deposit the manuscript in pre-publication files/repositories (preprint servers/repositories), including arXiv, bioRxiv, figshare, PeerJ Preprints, SSRN, and others, which can produce interesting exchanges and increase citations of the published work (see The effect of open access).
- After submission, it is recommended that authors deposit their article in their institutional repository, personal website, or scientific social network (such as Zenodo, ResearchGate or edu).