Kaijie Wei

Project Assistant Professor, Keio University

FPGA Design for Autonomous Vehicle Driving Using Binarized Neural Networks


Journal article


Kaijie Wei, Koki Honda, H. Amano
International Conference on Field-Programmable Technology, 2018

Semantic Scholar DBLP DOI
Cite

Cite

APA   Click to copy
Wei, K., Honda, K., & Amano, H. (2018). FPGA Design for Autonomous Vehicle Driving Using Binarized Neural Networks. International Conference on Field-Programmable Technology.


Chicago/Turabian   Click to copy
Wei, Kaijie, Koki Honda, and H. Amano. “FPGA Design for Autonomous Vehicle Driving Using Binarized Neural Networks.” International Conference on Field-Programmable Technology (2018).


MLA   Click to copy
Wei, Kaijie, et al. “FPGA Design for Autonomous Vehicle Driving Using Binarized Neural Networks.” International Conference on Field-Programmable Technology, 2018.


BibTeX   Click to copy

@article{kaijie2018a,
  title = {FPGA Design for Autonomous Vehicle Driving Using Binarized Neural Networks},
  year = {2018},
  journal = {International Conference on Field-Programmable Technology},
  author = {Wei, Kaijie and Honda, Koki and Amano, H.}
}

Abstract

We propose an autonomous vehicle controlled by FPGAs. In our design, considering embedded systems, we apply the binarized neural networks (BNNs) which can realize a satis-fying result in high speed and accuracy to recognize pedestrians and some obstacles on a given road. To detect the traffic light, a passive camera-based pipeline is applied. Furthermore, the implementation of road lane detection is based on color selection algorithm, Canny Edge Detection, and Hough Transformation. The proposed design is realized by two Xilinx boards: PYNQ-Z1 and Zynq-Xc7Z010. These two FPGA boards cooperate with each other through a shared network cable. In the proposed design, the resource used by Zynq-Xc7Z010 can be greatly reduced and the inference time on the FPGA has been thousands times faster than the software implementation.


Share

Tools
Translate to