Projects Proposed Projects
Please see propose projects for Spring and Winter upcoming semesters. This is a 4 academic point course. For further details please contact the laboratory engineer Yaron Honen (04-8295535, room 441).
Emotional ChatBot - Reading Human Emotions by Ro/Bots
Robots and bots using a simple webcam will communicate better with humans, improve their ability to influence human consumers, and understand their preferences. Imagine that the Chat-Bot will have eyes and the ability to recognize human emotion. This capability will leverage the bot's cognitive understanding of human preferences and intentions.
Knowledge in network communication
Excellent relevant programming skills
High Perceptual Quality Single Image Super Resolution
The vast work in deep learning has led to a leap in image restoration research. Given a degraded image (e.g., a noisy image), current solutions usually provide only one restoration candidate with sub-optimal visual quality (for instance, a restored image which minimizes the Mean-Squared-Error loss). In this project, we aim to tackle the Single Image Super-Resolution (SISR) task from a completely new perspective, aiming to produce many possible high resolution candidates (with high perceptual quality) for each low resolution input. We will use a novel GAN-based approach that recently won the Amdocs Best Project contest and was demonstrated on image denoising https://arxiv.org/pdf/2103.04192.pdf . This project is research oriented, and will require a lot of dedication. The end goal is to publish a paper (but first, of course, to do excellent research).
Optionally, to have experience in GANs (Generative Adversarial Networks), background in image processing and computer vision, expertise with multi-GPU training
Analysis of teachers movements in classroom
Using videos of apprentice teachers in classroom, we will inspect their body movements and face orientation. Quantitative and qualitative results will help them perform better in class.
Computer Vision Based Bike Fit
In this project we will implement a system that can find the right parameters for adapting the bicycle to the rider. We will use 3D or 2D camera to capture the scene and than analyze the angles and distances.