Realtime Facial Expression Recognition: Neuromorphic Hardware vs. Edge AI Accelerators
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917613662109696 |
|---|---|
| author | Smith, Heath Seekings, James Mohammadi, Mohammadreza Zand, Ramtin |
| author_facet | Smith, Heath Seekings, James Mohammadi, Mohammadreza Zand, Ramtin |
| contents | The paper focuses on real-time facial expression recognition (FER) systems as an important component in various real-world applications such as social robotics. We investigate two hardware options for the deployment of FER machine learning (ML) models at the edge: neuromorphic hardware versus edge AI accelerators. Our study includes exhaustive experiments providing comparative analyses between the Intel Loihi neuromorphic processor and four distinct edge platforms: Raspberry Pi-4, Intel Neural Compute Stick (NSC), Jetson Nano, and Coral TPU. The results obtained show that Loihi can achieve approximately two orders of magnitude reduction in power dissipation and one order of magnitude energy savings compared to Coral TPU which happens to be the least power-intensive and energy-consuming edge AI accelerator. These reductions in power and energy are achieved while the neuromorphic solution maintains a comparable level of accuracy with the edge accelerators, all within the real-time latency requirements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08792 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Realtime Facial Expression Recognition: Neuromorphic Hardware vs. Edge AI Accelerators Smith, Heath Seekings, James Mohammadi, Mohammadreza Zand, Ramtin Computer Vision and Pattern Recognition Machine Learning Neural and Evolutionary Computing Performance The paper focuses on real-time facial expression recognition (FER) systems as an important component in various real-world applications such as social robotics. We investigate two hardware options for the deployment of FER machine learning (ML) models at the edge: neuromorphic hardware versus edge AI accelerators. Our study includes exhaustive experiments providing comparative analyses between the Intel Loihi neuromorphic processor and four distinct edge platforms: Raspberry Pi-4, Intel Neural Compute Stick (NSC), Jetson Nano, and Coral TPU. The results obtained show that Loihi can achieve approximately two orders of magnitude reduction in power dissipation and one order of magnitude energy savings compared to Coral TPU which happens to be the least power-intensive and energy-consuming edge AI accelerator. These reductions in power and energy are achieved while the neuromorphic solution maintains a comparable level of accuracy with the edge accelerators, all within the real-time latency requirements. |
| title | Realtime Facial Expression Recognition: Neuromorphic Hardware vs. Edge AI Accelerators |
| topic | Computer Vision and Pattern Recognition Machine Learning Neural and Evolutionary Computing Performance |
| url | https://arxiv.org/abs/2403.08792 |