Engineering and Technology

Dynamic machine vision with retinomorphic photomemristor-reservoir computing

H. Tan and S. V. Dijken

This groundbreaking research by Hongwei Tan and Sebastiaan van Dijken introduces an innovative dynamic machine vision system that revolutionizes real-time motion recognition and prediction through advanced in-sensor processing, making strides towards enhanced applications in robotics and autonomous driving.

00:00

Playback language: English

Index

Abstract

This paper presents a novel approach to dynamic machine vision (DMV) using recurrent photomemristor networks. The system utilizes a retinomorphic photomemristor array (PMA) as a dynamic vision reservoir, embedding past motion frames as hidden states into the present frame. This in-sensor processing eliminates redundant data flows and enables real-time motion recognition and prediction, crucial for applications like video analysis, robotics, and autonomous driving.

Publisher

Nature Communications

Published On

Apr 15, 2023

Authors

Hongwei Tan, Sebastiaan van Dijken

Related Publications

Explore these studies to deepen your understanding of the subject.

Engineering and Technology

Toward grouped-reservoir computing: organic neuromorphic vertical transistor with distributed reservoir states for efficient recognition and prediction

C. Gao, D. Liu, et al.

Computer Science

Configured Quantum Reservoir Computing for Multi-Task Machine Learning

W. Xia, J. Zou, et al.

Engineering and Technology

Adaptative machine vision with microsecond-level accurate perception beyond human retina

L. Li, S. Li, et al.

Earth Sciences

Regional sensitivity patterns of Arctic Ocean acidification revealed with machine learning

J. P. Krasting, M. D. Palma, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny