International Journal of Advanced Culture Technology

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

The training of convolution neural network for advanced driver assistant system

  • Nam, Kihun (Department of computer engineering, Seokyeong University) ;
  • Jeon, Heekyeong (Department of computer engineering, Seokyeong University)
  • Received : 2016.10.25
  • Accepted : 2016.11.21
  • Published : 2016.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, the learning technique for CNN processor on vehicle is proposed. In the case of conventional CNN processors, weighted values learned through training are stored for use, but when there is distortion in the image due to the weather conditions, the accuracy is decreased. Therefore, the method of enhancing the input image for classification is general, but it has the weakness of increasing the processor size. To solve this problem, the CNN performance was improved in this paper through the learning method of the distorted image. As a result, the proposed method showed improvement of approximately 38% better accuracy than the conventional method.

Keywords

References

  1. http://www.nvidia.com/object/advanced-driver-assistance-systems.html
  2. https://indico.cern.ch/event/395242/attachments/791742/1085286/DEEP_LEARNING_ON_MPPA_MANYCORE_PROCESSOR_V2.2.pdf
  3. Clement Farabet, Berin Martini, Polina Akselrod, Selcuk Talay and Yann LeCun, "Hardware accel-erated convolutional neural networks for synthetic vision systems," Proceedings of 2010 IEEE International Symposium on Circuits and Systems, (2010) May 30 - June 2; Paris, France
  4. Alex Krizhevsky, lya Sutskever and Geoffrey E. Hinton, "ImageNet Classification with Deep Con-volutional Neural Networks," IEEE Transactions on Pattern Analysis and Machine Intelligence. (2016), Vol.38, Issue.10, pp.1943-1955 https://doi.org/10.1109/TPAMI.2015.2502579
  5. Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama and Trevor Darrell, "Caffe: Convolutional Architecture for Fast Feature Embedding," Proceedings of the 22nd ACM international conference on Multimedia, (2014), November 3-7; Florida, USA
  6. Glorot, Xavier, Antoine Bordes, and Yoshua Bengio. "Deep Sparse Rectifier Neural Net-works,"Aistats, (2011), Vol. 15, No. 106.
  7. Hee-kyeong Jeon, Kwang-yeob Lee, Chi-yong Kime Yong-beom Cho, "An implementation of a convolutional accelerator based on a GPGPU for a Deep Learning," Journal of IKEEE, (2016), Vol.20, No.3, pp.303-306 https://doi.org/10.7471/ikeee.2016.20.3.303
  8. Szegedy, Christian, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. "Going deeper with convolutions"
  9. Gold, Steven, and Anand Rangarajan. "Softmax to softassign: Neural network algorithms for combinatorial optimization," Journal of Artificial Neural Networks2.4, (1996), 381-399.
  10. Hecht-Nielsen, Robert. "Theory of the backpropagation neural network,"International Joint Conference on. IEEE, (1989).
  11. Mi-young Kim, Yong-beom Cho, "Comparisons of Recognition Rates for the Off-line Handwritten Hangul using Learning Codes based on Neural Network,"Journal of IKEEE, (1998), Vol.2, No.1, pp.150-159
  12. Bottou, Leon. "Large-scale machine learning with stochastic gradient descent," Proceedings of COMPSTAT'2010. Physica-Verlag HD, (2010), pp.177-186.
  13. Konecny, Jakub, et al. "mS2GD: Mini-batch semi-stochastic gradient descent in the proximal setting," arXiv preprint arXiv:1410.4744 (2014).
  14. http://www.gavrila.net/Datasets/Daimler_Pedestrian_Benchmark_D/daimler_pedestrian_benchmark_d.html