Realtime Facial Expression Recognition: Neuromorphic Hardware vs. Edge AI Accelerators
This work addresses the challenge of energy-efficient hardware selection for real-time facial expression recognition in applications like social robotics, though it is incremental as it compares existing hardware options.
The paper tackled the problem of deploying real-time facial expression recognition models at the edge by comparing neuromorphic hardware (Intel Loihi) with edge AI accelerators, finding that Loihi achieved about two orders of magnitude reduction in power dissipation and one order of magnitude energy savings compared to the least power-intensive edge accelerator while maintaining comparable accuracy and real-time latency.
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.