Human action recognition with a large-scale brain-inspired photonic computer
This work addresses the problem of energy-efficient and easily trainable real-time video processing for applications like brain-computer interfaces and surveillance, representing a novel domain-specific advancement.
The authors tackled human action recognition in video streams by proposing a scalable photonic neuro-inspired architecture based on reservoir computing, achieving state-of-the-art accuracy with an experimental optical setup using off-the-shelf components that can scale to hundreds of thousands of nodes.
The recognition of human actions in video streams is a challenging task in computer vision, with cardinal applications in e.g. brain-computer interface and surveillance. Deep learning has shown remarkable results recently, but can be found hard to use in practice, as its training requires large datasets and special purpose, energy-consuming hardware. In this work, we propose a scalable photonic neuro-inspired architecture based on the reservoir computing paradigm, capable of recognising video-based human actions with state-of-the-art accuracy. Our experimental optical setup comprises off-the-shelf components, and implements a large parallel recurrent neural network that is easy to train and can be scaled up to hundreds of thousands of nodes. This work paves the way towards simply reconfigurable and energy-efficient photonic information processing systems for real-time video processing.