Sistema de Multicamadas para Detecção de Placas Sinalizadoras em Tempo Real
##plugins.themes.bootstrap3.article.main##
Resumo
O desenvolvimento de sistemas de assistência ao condutor (ADAS, Advanced Driver Assistance Systems) originou uma demanda de técnicas de detecção de placas sinalizadoras em imagens digitais, que estão se tornando cada vez mais robustas. Porém, essas técnicas necessitam de muito recurso computacional para serem executadas em tempo real (30 quadros por segundo). Neste artigo, é apresentado um sistema de detecção de placas sinalizadoras capturadas por câmeras digitais. O modelo proposto consiste de 2 fases de detecção, com o objetivo de juntar técnicas de busca e extração de características, que utilizam o menor custo computacional possível. O modelo possui uma taxa de acurácia acima de 90% na base de dados GTSDB (German Traffic Sign Detection Benchmark) assim como os melhores modelos do estado da arte, porém possui um menor tempo de resposta. Por fim, o sistema foi testado em um ambiente real, por meio de uma câmera digital.
Downloads
Não há dados estatísticos.
##plugins.themes.bootstrap3.article.details##
Como Citar
Bezerra, B., Leite, R., & Fernandes, B. (2018). Sistema de Multicamadas para Detecção de Placas Sinalizadoras em Tempo Real. Revista De Engenharia E Pesquisa Aplicada, 3(2). https://doi.org/10.25286/repa.v3i2.572
Seção
Engenharia da Computação
Referências
[1] S. Houben, J. Stallkamp, J. Salmen, M. Schlipsing and C. Igel, "Detection of traffic signs in real-world images: The German traffic sign detection benchmark," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-8.
[2] S. Salti, A. Petrelli, F. Tombari, N. Fioraio and L. Di Stefano, "A traffic sign detection pipeline based on interest region extraction," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-7.
[3] A. F. De Souza et al., "Traffic sign detection with VG-RAM weightless neural networks," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-9.
[4] G. Wang, G. Ren, Z. Wu, Y. Zhao and L. Jiang, "A robust, coarse-to-fine traffic sign detection method," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-5.
[5] H. Chenini, J. P. Dèrutin and T. Tixier, "Fast parking control of mobile robot based on multi-layer neural network on homogeneous architecture," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-10.
[6] M. Mathias, R. Timofte, R. Benenson and L. Van Gool, "Traffic sign recognition — How far are we from the solution?," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-8.
[7] Z. Karel, Contrast limited adaptive histogram equalization. In: Graphics gems IV. Academic Press Professional, Inc., 1994. p. 474-485.
[8] S., Agung W. et al, Color retinal image enhancement using clahe. In: ICT for Smart Society (ICISS), 2013 International Conference on. IEEE, 2013. p. 1-3.
[9] M. Liang, M. Yuan, X. Hu, J. Li, and H. Liu, “Traffic sign detection by roi extraction and histogram features-based recognition,” in Neural Networks (IJCNN), The 2013 International Joint Conference on. IEEE, 2013, pp. 1–8.
[10] Y. Wu, Y. Liu, J. Li, H. Liu and X. Hu, "Traffic sign detection based on convolutional neural networks," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-7.
[11] Q. Xu, S. Varadarajan, C. Chakrabarti, and L. J. Karam, “A distributed canny edge detector: algorithm and fpga implementation,” Image Processing, IEEE Transactions on, vol. 23, no. 7, pp. 2944–2960, 2014.
[12] D., Navneet; TRIGGS, Bill. Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). IEEE, 2005. p. 886-893.
[13] Z., Qiang et al. Fast human detection using a cascade of histograms of oriented gradients. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06). IEEE, 2006. p. 1491-1498.
[14] LAFUENTE-ARROYO, S. et al. Traffic sign shape classification evaluation I: SVM using distance to borders. In: IEEE Proceedings. Intelligent Vehicles Symposium, 2005. IEEE, 2005. p. 557-562.
[15] V., Kushal; HAN, Yan; ORUKLU, Erdal. Traffic sign recognition based on prevailing bag of visual words representation on feature descriptors. In: 2015 IEEE International Conference on Electro/Information Technology (EIT). IEEE, 2015. p. 489-493.
[16] PANCHAL, P. M.; PANCHAL, S. R.; SHAH, S. K. A comparison of SIFT and SURF. International Journal of Innovative Research in Computer and Communication Engineering, v. 1, n. 2, p. 323-327, 2013.
[17] R., Mohammed et al. Detection and recognition of road signs in a video stream based on the shape of the panels. In: Intelligent Systems: Theories and Applications (SITA-14), 2014 9th International Conference on. IEEE, 2014. p. 1-5.
[18] R., Redia et al. Affine versus projective transformation for SIFT and RANSAC image matching methods. In: 2015 IEEE International Conference on Signal and Image Processing Applications (ICSIPA). IEEE, 2015. p. 447-451.
[2] S. Salti, A. Petrelli, F. Tombari, N. Fioraio and L. Di Stefano, "A traffic sign detection pipeline based on interest region extraction," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-7.
[3] A. F. De Souza et al., "Traffic sign detection with VG-RAM weightless neural networks," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-9.
[4] G. Wang, G. Ren, Z. Wu, Y. Zhao and L. Jiang, "A robust, coarse-to-fine traffic sign detection method," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-5.
[5] H. Chenini, J. P. Dèrutin and T. Tixier, "Fast parking control of mobile robot based on multi-layer neural network on homogeneous architecture," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-10.
[6] M. Mathias, R. Timofte, R. Benenson and L. Van Gool, "Traffic sign recognition — How far are we from the solution?," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-8.
[7] Z. Karel, Contrast limited adaptive histogram equalization. In: Graphics gems IV. Academic Press Professional, Inc., 1994. p. 474-485.
[8] S., Agung W. et al, Color retinal image enhancement using clahe. In: ICT for Smart Society (ICISS), 2013 International Conference on. IEEE, 2013. p. 1-3.
[9] M. Liang, M. Yuan, X. Hu, J. Li, and H. Liu, “Traffic sign detection by roi extraction and histogram features-based recognition,” in Neural Networks (IJCNN), The 2013 International Joint Conference on. IEEE, 2013, pp. 1–8.
[10] Y. Wu, Y. Liu, J. Li, H. Liu and X. Hu, "Traffic sign detection based on convolutional neural networks," Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, 2013, pp. 1-7.
[11] Q. Xu, S. Varadarajan, C. Chakrabarti, and L. J. Karam, “A distributed canny edge detector: algorithm and fpga implementation,” Image Processing, IEEE Transactions on, vol. 23, no. 7, pp. 2944–2960, 2014.
[12] D., Navneet; TRIGGS, Bill. Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). IEEE, 2005. p. 886-893.
[13] Z., Qiang et al. Fast human detection using a cascade of histograms of oriented gradients. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06). IEEE, 2006. p. 1491-1498.
[14] LAFUENTE-ARROYO, S. et al. Traffic sign shape classification evaluation I: SVM using distance to borders. In: IEEE Proceedings. Intelligent Vehicles Symposium, 2005. IEEE, 2005. p. 557-562.
[15] V., Kushal; HAN, Yan; ORUKLU, Erdal. Traffic sign recognition based on prevailing bag of visual words representation on feature descriptors. In: 2015 IEEE International Conference on Electro/Information Technology (EIT). IEEE, 2015. p. 489-493.
[16] PANCHAL, P. M.; PANCHAL, S. R.; SHAH, S. K. A comparison of SIFT and SURF. International Journal of Innovative Research in Computer and Communication Engineering, v. 1, n. 2, p. 323-327, 2013.
[17] R., Mohammed et al. Detection and recognition of road signs in a video stream based on the shape of the panels. In: Intelligent Systems: Theories and Applications (SITA-14), 2014 9th International Conference on. IEEE, 2014. p. 1-5.
[18] R., Redia et al. Affine versus projective transformation for SIFT and RANSAC image matching methods. In: 2015 IEEE International Conference on Signal and Image Processing Applications (ICSIPA). IEEE, 2015. p. 447-451.