Research Areas
Microlens for Vision Correcting Display
Nearsightedness is a type of vision problem that prevents people from observing objects clearly at a far distance. Instead of using eyeglasses, we strive to solve this problem with the Vision Correction Display (VCD) technology and microlens arrays, a type of optical device placed in front of the display screen. With a combination of the optical device and a specially designed computer program to regenerate the displayed image, people with nearsightedness are able to observe sharp images without eyeglasses. Users can enter their myopia degrees to generate customized images on the screen without changing optical devices. This technology makes correction customizable, light-weighted, and with smaller aberrations.
Assistive Technology for Human Computer Interface
Our team is pioneering an innovative project aimed at enhancing accessibility through a groundbreaking two-handed gesture control suite. This system utilizes webcam technology to interpret hand gestures, providing a seamless and disability-friendly interface. Without the need for traditional input devices like keyboards or mice, this project enables intuitive control over various computer functions, including cursor navigation and air writing, redefining the standards of contactless interaction. This project can be separated into two main areas of research: eye tracking, and multi-frame gestures
Autonomous Senior Helper System for Enhanced Safety and Well-Being
In today’s society, the proportion of seniors within the population has increased significantly due to advances in healthcare and the decline in the birth rate. According to research conducted by the Pew Research Center, about 27% of adults ages 60 and older live alone in America. With no one to take care of them, seniors who live alone are exposed to many risks such as falls, heart attacks, and overlooked symptoms or illnesses. For seniors who live at home by themselves, it is quite difficult for them to seek help when such incidents happen. Therefore, our goal is to develop a light-weighted computer vision system that can monitor the activities of old adults through cameras and raises an alert to notify their family members, the emergency department, and any other related parties when seniors being monitored fall or have a heart attack, so that they can be helped as soon as possible. We aim to build a reliable system that can be easily deployed and does not rely on advanced hardware like GPUs. It should serve as a guardian that can look out for seniors 24/7. Despite all the great functionalities, it should still be affordable to most seniors in need.
Compressive Deconvolution for Vision Correcting Display
Our group explores compressed-sensing based deconvolution of images and videos with traditional linear algebraic and signal processing methods, as well as deep learning-based approaches. We also expand the support for compressive deconvolution to higher-order aberrations which cannot be corrected with eyeglasses.
Sign Language Processing
The Full Story Sign Language Processing Some people with hand disabilities have trouble controlling the computer with a mouse. The goal of our project is to develop an intelligent assistant using sign language recognition to help people with hand disability to navigate the computer without physically manipulating a mouse. We are also trying to increase the accuracy of sign language recognition using an ensemble of multiple models including SPOTER, I3D, and TimeSformer models.
