Ultrafast single-channel machine vision based on neuro-inspired photonic computing

TL;DR

This paper introduces a novel ultrafast, image-sensor-free machine vision system that uses neuro-inspired photonic computing and random temporal encoding to achieve gigahertz-rate visual processing, enabling high-speed recognition and imaging.

Contribution

It presents a new framework that processes visual information optically with a single channel, overcoming sensor frame rate limitations and enabling ultrafast machine vision applications.

Findings

Demonstrated high-speed image recognition and anomaly detection.

Achieved gigahertz-rate visual processing surpassing conventional methods.

Enabled high-speed imaging of sub-nanosecond phenomena.

Abstract

High-speed machine vision is increasing its importance in both scientific and technological applications. Neuro-inspired photonic computing is a promising approach to speed-up machine vision processing with ultralow latency. However, the processing rate is fundamentally limited by the low frame rate of image sensors, typically operating at tens of hertz. Here, we propose an image-sensor-free machine vision framework, which optically processes real-world visual information with only a single input channel, based on a random temporal encoding technique. This approach allows for compressive acquisitions of visual information with a single channel at gigahertz rates, outperforming conventional approaches, and enables its direct photonic processing using a photonic reservoir computer in a time domain. We experimentally demonstrate that the proposed approach is capable of high-speed image recognition and anomaly detection, and furthermore, it can be used for high-speed imaging. The proposed approach is multipurpose and can be extended for a wide range of applications, including tracking, controlling, and capturing sub-nanosecond phenomena.