Fully Convolutional Neural Network for Malaysian Road Lane Detection

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Recently, a deep learning, Fully Convolutional Neural Network (FCN) has been widely studied because it can demonstrate promising results in the application of detection of objects in an image or video. Hence, the FCN approach has been proposed as one of the solution methods in mitigating the issues pertinent to Malaysia’s road lane detection. Previously, FCN model for lane detection has not been tested in Malaysian road conditions. Therefore, this study investigates the further performance of this model in the Malaysia. The network model is trained and validated using the datasets obtained from Machine Learning NanoDegree. In addition, the real-time data collection has been conducted to collect the data sets for the testing at the highway and urban areas in Malaysia. Then, the collected data is used to test the performance of the FCN network in detecting the lane markings on Malaysia road. The results demonstrated that the FCN method is achieving 99% of the training and validation accuracy.

     

     


  • Keywords


    Fully Convolutional Neural Network (FCN); lane detection; deep learning.

  • References


      [1] Tian, Y., Gelernter, J., Wang, X., Chen, W., Gao, J., Zhang, Y., & Li, X. (2018). Lane marking detection via deep convolutional neural network. Neurocomputing, 280, 46-55.

      [2] Kaur, G., & Kumar, D. (2015). Lane detection techniques: A review. International Journal of Computer Applications, 112(10), 4-8.

      [3] Gurghian, A., Koduri, T., Bailur, S. V., Carey, K. J., & Murali, V. N. (2016). Deeplanes: End-to-end lane position estimation using deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 38-45.

      [4] Wang, Q., Gao, J., & Yuan, Y. (2018). Embedding structured contour and location prior in siamesed fully convolutional networks for road detection. IEEE Transactions on Intelligent Transportation Systems, 19(1), 230-241.

      [5] Ali, M., Radzi, A., & Saad, H. M. (2017). A new approach to highway lane detection by using Hough Transform technique. Journal of ICT, 16(2), 244-260.

      [6] Mongkonyong, P., Nuthong, C., Siddhichai, S., & Yamakita, M. (2018). Lane detection using Randomized Hough Transform. IOP Conference Series: Materials Science and Engineering, 297(1), 1-11.

      [7] Lee, Y., & Kim, H. (2016). Real-time lane detection and departure warning system on embedded platform. Proceedings of the IEEE 6th International Conference on Consumer Electronics, pp. 1-4.

      [8] Zhang, Y., Su, Y., Yang, J., Ponce, J., & Kong, H. (2018). When Dijkstra meets vanishing point: a stereo vision approach for road detection. IEEE Transactions on Image Processing, 27(5), 2176-2188.

      [9] Narote, S. P., Bhujbal, P. N., Narote, A. S., & Dhane, D. M. (2018). A review of recent advances in lane detection and departure warning system. Pattern Recognition, 73, 216-234.

      [10] Virgo, M. (2017). Lane detection with deep learning. https://github.com/mvirgo/MLND%Capstone/blob/master/MLND%20Capstone%20Project%20Report.pdf.

      [11] E-con Systems India Pvt. Ltd. (2017). Camera. e-CAM21_CUMI1290_MOD datasheet.

      [12] Ozhiganov, I. (2016). Using fully convolutional neural networks. https://www.azoft.com/blog/fully-convolutional-neural-networks/.


 

View

Download

Article ID: 20792
 
DOI: 10.14419/ijet.v7i4.11.20792




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.