Submit your paper : editorIJETjournal@gmail.com

Paper Title : Traffic Sign Recognition using CuDNN

ISSN : 2395-1303
Year of Publication : 2020
10.29126/23951303/IJET-V6I2P24

Authors: -Aditya Das,Jishnu De Sarkar,Arka Dasgupta,Mrs. R. Logeshwari

         


Abstract
Object detection has been a prime area of focus for researchers across the world for several years now. With newer technology being developed at a very rapid rate, scientists have forever been on a quest to develop models with highest accuracy. This paper aims at providing a novel approach to the problem of detecting objects and comparing it with the existing methods. It has been observed that CuDNN (NVIDIA CUDA® Deep Neural Network library) can leverage the potential of GPU (Graphical Processor Units) over conventional CPU cores and can hence achieve significantly higher accuracy than other traditional neural network models. We use CLAHE (Contrast Limited Adaptive Histogram Equalization) for the preprocessing of the data and then take the help of CuDNN library to enhance the results even further. Moreover, computations done using CuDNN have been observed to run notably faster.

Reference
[[1] Qing Tang, Kang-Hyun Jo. “Analysis of Various Traffic Sign Detectors Based on Deep Convolutional Network.” Intelligent Transportation Systems Conference 2006. ITSC '06. IEEE, pp. 811-816, 2006. [2] Shaung Xu, Deqing Niu, Bo Tao, Gongfa Li. “Convolutional Neural Network Based Traffic Sign Recognition System.” Biomedical Circuits and Systems Conference (BioCAS) 2014 IEEE, pp. 544-547, 2014. [3] A. W. Setiawan, T. R. Mengko, O. S. Santoso and A. B. Suksmono, "Color retinal image enhancement using CLAHE," International Conference on ICT for Smart Society, Jakarta, 2013, pp. 1-3. [4] S. Jung, U. Lee, J. Jung and D. H. Shim, "Real-time Traffic Sign Recognition system with deep convolutional neural network," 2016 13th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), Xi'an, 2016, pp. 31-34. [5] A.Krizhevsky, I.Sutskever, and G.Hinton, “Image Net classification with deep convolutional neural networks”. In NIPS, 2012. [6] P. Sermanet and Y. Lecun, “Traffic sign recognition with multi-scale convolutional networks.” In Proc. IJCNN, 2011. [7] U. Handmann, T. Kalinke, C. Tzomakas, M. Werner, and W. vonseelen, ”An image processing system for driver assistance,” in Proc. Ieee Int. Conf. Intell. Veh., 1998, pp.481-486. [8] Malik, Z., and Siddiqi, I., “Detection and Recognition of Traffic Signs from Road Scene Images.” International Conference on Frontiers of Information Technology IEEE, 2015:330-335. [9] Wahyono, and Jo, K., H., “A comparative study of classification methods for traffic signs recognition.” IEEE International Conference on Industrial Technology IEEE, 2014:614-619. [10] Le, Guoqing, et al. “Traffic sign recognition based on PCANet.” Advanced Information Management, Communicates, Electronic and Automation Control Conference IEEE, 2017:807-811 [11] R. A. Hummel, “Image Enhancement by Histogram Transformation”. Computer Graphics and Image Processing 6. [12] Thamizharasi Ayyavoo, Jayasudha John “Illumination pre-processing method for face recognition using 2D DWT and CLAHE “ in SuseelaIET Biometrics 7. [13] M.A. Garcia-Garrido, M.A. Sotelo, E. Martin-Gorostiza, "Fast traffic sign detection and recognition under changing lighting conditions", Intelligent Transportation Systems Conference 2013. ITSC '13. IEEE, pp. 629-634, 2013c=

Keywords