512KiB RAM Is Enough! Live Camera Face Recognition DNN on MCU

Maxim Zemlyanikin, Alexander Smorkalov, Tatiana Khanova, Anna Petrovicheva, Grigory Serebryakov

ICCVW 2019 pp. 2493-2500

doi:10.1109/ICCVW.2019.00305 /iccvw/2019/zemlyanikin2019iccvw-512kib/

Abstract

Small factor and ultra-low power devices are becoming more and more smart and capable even for deep learning network inference. And as the devices are "small", the challenge is becoming tougher. This paper covers full development and deployment pipeline of Face Recognition with a live camera - from model training and quantization to porting to RISC-V MCU with 512 kilobytes of internal RAM. Authors provide GreenWaves GAP8 SoC overview and the approaches for DNN model optimization and inference in the extreme environment. As the project outcome, authors were able to run Face Detection and Recognition with live QVGA camera and display preview on a battery-powered board.

ICCVW Semantic Scholar

Cite

Text

Zemlyanikin et al. "512KiB RAM Is Enough! Live Camera Face Recognition DNN on MCU." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00305

Markdown

[Zemlyanikin et al. "512KiB RAM Is Enough! Live Camera Face Recognition DNN on MCU." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/zemlyanikin2019iccvw-512kib/) doi:10.1109/ICCVW.2019.00305

BibTeX

@inproceedings{zemlyanikin2019iccvw-512kib,
  title     = {{512KiB RAM Is Enough! Live Camera Face Recognition DNN on MCU}},
  author    = {Zemlyanikin, Maxim and Smorkalov, Alexander and Khanova, Tatiana and Petrovicheva, Anna and Serebryakov, Grigory},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {2493-2500},
  doi       = {10.1109/ICCVW.2019.00305},
  url       = {https://mlanthology.org/iccvw/2019/zemlyanikin2019iccvw-512kib/}
}