Using Fiber Laser Arrays and Deep Learning for Advanced Single-Pixel Imaging


A research team led by Professor Kai Han of the National University of Defense Technology in China has proposed a new method for single-pixel imaging (SPI) using a fiber laser array and an unsupervised deep neural network. This method provides faster imaging speeds than traditional SPI techniques and has potential for remote sensing and target detection applications. The study was published in Limitations of optoelectronics,

Using Fiber Laser Arrays and Deep Learning for Advanced Single-Pixel Imaging
Efficient single-pixel imaging based on fiber laser arrays. Image Credit: Frontiers of Optoelectronics

Its unique advantages compensate for the shortcomings of traditional array-based imaging technologies, which are more expensive or still in their infancy, such as non-visible light imaging and remote sensing.

The refresh rate of the spatial light modulator is a constant constraint on the scanning speed of the SPI. For example, in binary mode, a standard digital micro-mirror device (DMD) has a maximum refresh rate of 22 kHz. As a result of this limitation, achieving real-time SPI is challenging.

Researchers at China's National University of Defense Technology (NUDT) under the direction of Professor Kai Han are interested in SPI and fiber laser arrays. They provide an effective SPI system that uses an unsupervised deep neural network and a phase-controlled fiber laser array.

To create the illuminated light field, the fiber lasers are grouped into a compact hexagonal configuration and coherently integrated. Randomly modulated fiber laser arrays, using high speed electro-optic modulators in each fiber laser module, enable rapid speckle projection onto the object of interest.

To improve the quality of reconstructed images, unsupervised deep neural networks are also used in the image reconstruction process. Based on its ability to generate high emitter power (~kW) and quick modulation (~MHz), researchers anticipate that SPI technology will find applications in target identification, remote sensing, and other related fields.

Journal Reference:

‌ Lai, W., and others, (2024) Efficient single-pixel imaging based on compact fiber laser array and unsupervised neural networks. Limitations of optoelectronics, doi.org/10.1007/s12200-024-00112-8.

Source: https://www.frontiersin.org/journals


Leave a Comment

“The Untold Story: Yung Miami’s Response to Jimmy Butler’s Advances During an NBA Playoff Game” “Unveiling the Secrets: 15 Astonishing Facts About the PGA Championship”