Real-time embedded intelligence system: emotion recognition on Raspberry Pi with Intel NCS

Research output: Contribution to conferencePaper

84 Downloads (Pure)

Abstract

Convolutional Neural Networks (CNNs) have exhibited certain human-like performance on computer vision related tasks. Over the past few years since they have outperformed conventional algorithms in a range of image processing problems. However, to utilise a CNN model with millions of free parameters on a source limited embedded system is a challenging problem. The Intel Neural Compute Stick (NCS) provides a possible route for running largescale neural networks on a low cost, low power, portable unit. In this paper, we propose a CNN based Raspberry Pi system that can run a pre-trained inference model in real time with an average power consumption of 6.2W. The Intel Movidius NCS, which avoids requirements of expensive processing units e.g. GPU, FPGA. The system is demonstrated using a facial image-based emotion recogniser. A fine-tuned CNN model is designed and trained to perform inference on each captured frame within the processing modules of NCS.
Original languageEnglish
Pages801-808
Number of pages8
DOIs
Publication statusPublished - 5 Oct 2018
Event27th International Conference on Artificial Neural Networks - Rhodes, Greece
Duration: 5 Oct 20187 Oct 2018
https://e-nns.org/icann2018/

Conference

Conference27th International Conference on Artificial Neural Networks
Abbreviated titleICANN 2018
CountryGreece
CityRhodes
Period5/10/187/10/18
Internet address

Keywords

  • CNN
  • embedded system
  • low power system
  • SWAP profile

Fingerprint Dive into the research topics of 'Real-time embedded intelligence system: emotion recognition on Raspberry Pi with Intel NCS'. Together they form a unique fingerprint.

  • Cite this

    Xing, Y., Kirkland, P., Di Caterina, G., Soraghan, J., & Matich, G. (2018). Real-time embedded intelligence system: emotion recognition on Raspberry Pi with Intel NCS. 801-808. Paper presented at 27th International Conference on Artificial Neural Networks, Rhodes, Greece. https://doi.org/10.1007/978-3-030-01418-6_78