Researchers have developed a new intelligent photonic sensing-computing chip that can process, transmit and reconstruct images of a scene within nanoseconds.
Researchers at Tsinghua University in China have developed a new photonic chip that processes, transmits, and reconstructs images in nanoseconds.
The chip achieves this feat by skipping the optical to electronic data conversion deployed by conventional chips.
Machine vision is an evolving field in which cameras, sensors, and algorithms work in tandem to make sense of the world around them and perform specific tasks. In the past, technology relied on moving this data over long distances, where it can be analyzed and appropriate responses taken and executed.
“The world is entering an AI era, but AI is very time- and energy-exhaustive,” said Lu Fang, associate professor at the Department of Electronic Engineering at Tsinghua University in China. In a fast-moving world, machine vision now demands that data is processed on the device, called edge computing, to aid faster decision-making.
“The growth of edge devices, such as smartphones, intelligent cars and laptops has resulted in explosive growth of image data to be processed, transmitted and displayed. We are working to advance machine vision by integrating sensing and computing in the optical domain,” Fang added.
Doing away with optical-electro conversions
Edge tasks like autonomous driving are slowed by millisecond optical-to-electronic conversions.
“Capturing, processing and analyzing images for edge-based tasks such as autonomous driving is currently limited to millisecond-level speeds due to the necessity of optical-to-electronic conversions,” said Fang.
Currently, images captured by machine vision devices need to be transferred from their optical nature to electronic versions for the computers to make sense of the data.
Under Fang’s guidance, the researchers have built an optical parallel computational array (OPCA) chip with a sensing-computing array made using ring resonators. This design allows the photonic chip to convert an optical image into a two-dimensional representation of its light intensity that can be guided onto the chip using a micro-lens array.
The OPCA chip has a processing bandwidth of up to a hundred billion pixels and a response time of just six nanoseconds.
The new intelligent optical computational array (OPCA) chip performs end-to-end image processing, transmission and reconstruction by integrating sensing and computing on one chip. Image credit:
All optical neural network
Since the data is processed as light signals, the researchers used them to develop an all-optical neural network and deploy it for classification tasks typically carried out on the edge.
“Because each sensing-computing element of this chip is reconfigurable, they can each operate as a programmable neuron that generates light modulation output based on the input and weight,” added Fang in the press release.
RECOMMENDED ARTICLES
“The neural network connects all the sensing-computing neurons with a single waveguide, facilitating an all-optical full connection between the input information and the output.”
The research team deployed the chip for tasks such as image classification of hand-drawn images and image convolution to demonstrate how the chip works. In the latter approach, a filter is used on an image to extract certain features from it.
The successful completion of these tasks demonstrates that the chip architecture is competent in handling such tasks. In the future, the research team aims to increase the overall size of the OPCA chip and improve the neural network’s processing capacity to bring it closer to commercial usage.
The research findings were published in the journal Optica.
0COMMENT
NEWSLETTER
The Blueprint Daily
Stay up-to-date on engineering, tech, space, and science news with The Blueprint.
By clicking sign up, you confirm that you accept this site's Terms of Use and Privacy Policy
ABOUT THE EDITOR
Ameya Paleja Ameya is a science writer based in Hyderabad, India. A Molecular Biologist at heart, he traded the micropipette to write about science during the pandemic and does not want to go back. He likes to write about genetics, microbes, technology, and public policy.
