Artificial sensory neuron enables high-precision, multi-color, near-infrared object recognition

November 13, 2025

The GIST Artificial sensory neuron enables high-precision, multi-color, near-infrared object recognition

Lisa Lock

scientific editor

Robert Egan

associate editor

Editors' notes

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

peer-reviewed publication

trusted source

proofread

Near-infrared (NIR) photon detection and object recognition are crucial technologies for all-weather target identification. Conventional NIR detection systems that rely on photodetectors and von Neumann computing algorithms are energy inefficient. Artificial sensory neurons based on infrared-sensitive volatile memristors offer a promising solution.

In a study published in Advanced Materials, a team led by Dr. Wang Jiahong from the Shenzhen Institute of Advanced Technology of the Chinese Academy of Sciences developed an artificial sensory neuron based on a vanadium carbide/oxide (V2C/V2O5-x) heterostructure via topochemical conversion, enabling multi-color near-infrared response and high-precision object recognition in complex scenarios.

Researchers engineered a two-dimensional V2C/V2O5-x heterostructure with a natural fusion interface through a precisely controlled mild-oxidation topochemical conversion of V2CTx. This unique integration of metallic V2C and dielectric vacancy-enriched V2O5-x granted the heterostructure NIR responsivity and threshold-type volatile resistance switching (RS) ability.

The V2C/V2O5-x memristor demonstrated robust volatile capability with low coefficients of variation of merely 1.62% and 1.7% for the set and reset voltages, respectively. Its threshold voltage could be effectively modulated by power density and wavelength of NIR light. The correlation between wavelength and threshold firing voltage was consistent with photoelectric response, showing tunable photoelectric control of the V2C/V2O5-x memristor via photonic parameter modulation.

"Our photoelectric programmability enables multi-color infrared discrimination through characteristic threshold voltage signatures, and the distinct wavelength responses can be encoded in the artificial sensory neuron for near-infrared object recognition," said Dr. Wang.

Based on the multi-color NIR modulable RS characteristics and the YOLOv7 algorithm model, an artificial neural network architecture achieved average recognition accuracies of 89.6% for cars and 85.9% for persons on the FLIR dataset.

The study presents a promising memristor-based neuromorphic system that significantly enhances the efficiency and accuracy in object detection and recognition, which paves the way for advancements in autonomous systems, robotics, and intelligent environments.

More information: Yuanduo Qu et al, 2D Vanadium Carbide/Oxide Heterostructure‐Based Artificial Sensory Neuron for Multi‐Color Near‐Infrared Object Recognition, Advanced Materials (2025). DOI: 10.1002/adma.202512238

Journal information: Advanced Materials Provided by Chinese Academy of Sciences Citation: Artificial sensory neuron enables high-precision, multi-color, near-infrared object recognition (2025, November 13) retrieved 13 November 2025 from https://techxplore.com/news/2025-11-artificial-sensory-neuron-enables-high.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Explore further

Semiconductor neuron mimics brain's memory and adaptive response abilities