New Delhi: Rice University with the Indian Institute of Technology (IIT), Madras, US has developed an algorithm for lensless, miniature cameras supported with augmented reality or virtual reality, security, smart weaving, and robotics where cost, Form-factor, and weight major constraints.
Lensless cameras do not have a lens that, in a conventional camera, acts as a focusing element that allows the sensor to capture a sharp picture of the scene. Due to the absence of this focusing element, the lensless camera captures a multiplexed or globally blurred measurement of the scene.
Researchers have developed an intensive learning algorithm to produce photo-realistic images from blurred lensless capture.
Dr. Kaushik Mitra, Head of Computational Imaging Laboratory, IIT Madras and Assistant Professor in the Department of Electrical Engineering, said, "The existing algorithms of déballer images generate low-resolution is yield noise images' based on traditional optimization schemes.
He adds that "Our research team used 'Deep Learning' to develop a reconstruction algorithm called 'FlatNet' for lensless cameras, resulting in a significant improvement over traditional optimization-based algorithms. Flatness tested various real And performed on challenging scenarios and found effective in de-blurring images captured by lensless cameras.
The research was funded by the National Science Foundation and NSF EXPEDITIONS, US, Neural Engineering Systems Design (NESD), Defense Advanced Research Projects Agency (DARPA), US, National Institutes of Health (NIH) Grant, US and Qualcomm Innovation Fellowship India 2020. has gone.
Posts
