Electrical and Electronic Engineering

This project is about high-fidelity stereo RGBD imaging for Metaverse devices.
This work proposes to design and realize a fast and accurate 3D imaging architecture that Metaverse VR headsets can leverage. Different from the previous imaging framework, we use the prior of optical encoding, and joint optimization structure in deep optics to explore a new and improved framework for high-resolution RGBD imaging. A state-of-the-art stereo-matching algorithm is explored with jointly optimized lenses and an image recovery network. Coventional imaging algorithms consider only the post processing of captured images, which is less fleasible and with high computational complexity. Our deep stereo depth estimation integrates the optical preprossessing and encoding into the advanced decoding neural networks to achieve a higher accuracy of RGBD imaging with higher resolution. It fully utilizes the information obtained from the stereo camera with a pair of asymmetric lens in a Metaverse device to achieve a more extended depth range of all-in-focus imaging.

Holography plays a vital role in the advancement of virtual reality (VR) and augmented reality (AR) display technologies. Its ability to create realistic three-dimensional (3D) imagery is crucial for providing immersive experiences to users. However, existing computer-generated holography (CGH) algorithms used in these technologies are either slow or not 3D-compatible. In this project, we explore four inverse neural network architectures to overcome these issues for real time and 3D applications

Our project is an automatic rubbish disposal car. which is divided into 4 parts.The whole system is operated under the link between a computer and the vehicle, through this link, the computer can sketch the environment and calculate both position and posture of the vehicle, giving the car instructions on movements. The radar module is for outlining​ the surrounding environment. The AI recognition module allows the car to label the spitball that the camera captured, this allows it to find the spitball we wish to throw away. The Robotic Arm module is responsible for grabbing the object and throwing it into the Smart Bin. The Smart Bin should be able to open up automatically when the arm grabs the target as well as when someone’s hand is close to the bin.

We seeks to transform quantum physics education through the creation of an innovative curriculum that prioritizes experiential learning and practical engagement. The Innow Show offers a unique platform that aligns perfectly with our project’s goals of enhancing quantum physics education through experiential learning. By incorporating practical experiences and demonstration kits, our goal is to empower students with a profound understanding of quantum technology, effectively preparing them for future opportunities in this burgeoning field.

SCAVENGER-01 uses AI and computer vision to perform object detection and pick up ping pong balls, without interrupting athletes’ training.

It saves time, improves training efficiency, and prevents injuries.

It can be deployed in ping pong arenas, ideal for ping pong training centres, schools, colleges, clubs, and home settings. Where the robot will pick up the ping pong balls while athletes can focus on their training.

SCAVENGER-01 is a prototype, in the future, we plan to deploy a human avoidance algorithm to avoid colliding into the path of athletes, improve the routing algorithm so it can effectively go through the entire map/arena, and automatic wireless charging so the unmanned robot can head to the wireless charging station for automatic recharging.

This project aim to construct a robot using SLAM and a monocular camera for both SLAM and depth estimates. The system will be able to map the environment correctly and robustly, determining the robot’s location and orientation inside it. The robot can then estimate the depth using a deep learning model and pictures recorded by the monocular camera as input. This research intends to develop robotics and computer vision by investigating the potential of monocular cameras for SLAM and depth estimation, which might have practical applications in autonomous navigation and depth estimation through the use of a neural network model.