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).
Deep Semantic Shape Reconstruction

Deep Learning architectures have revolutionized the field of Computer Vision, completely altering the way we view 2D and 3D signals. In this project, we tackle the problem of precise and realistic reconstruction of 3D signals by semantic segmentation. The student will take part in creating novel architectures to push current state-of-the-art benchmarks one step further. More details: @https://arxiv.org/abs/2001.09650
Deep Precise Shape Reconstruction

Deep Learning architectures have revolutionized the field of Computer Vision, completely altering the way we view 2D and 3D signals. In this project, we tackle the problem of precise and realistic reconstruction of 3D signals via supervised and unsupervised learning methods. The student will take part in creating novel architectures to push current state-of-the-art benchmarks one step further. More details: @https://arxiv.org/abs/2001.09650
Virtual Try On

Deep Learning architectures have revolutionized the field of Computer Vision, completely altering the way we view 2D and 3D signals. In this project, we tackle the problem of precise and realistic reconstruction of 3D signals by semantic segmentation. The student will take part in creating novel architectures to push current state-of-the-art benchmarks one step further. More details: @https://arxiv.org/abs/2001.09650
ZoomEmotion

In this project, we would like to develop the ZoomEmotion - an algorithm that detects the emotional state of the child in real time and signals the teacher when the child is experiencing a negative emotion. In this project we would like to expand the previous project that dealt with facial expreation to recognize the faces of the children and their emotional state in real time. We would also like to quantify the time that negative emotions are present and to provide a feedback
- Excellence students
- Programming experience in C++ and/or Python
- Advantage courses in Machine/Deep Learning and/or Image Processing
Neuro feedback based Virtual reality for practicing mindfulness principles

In this project we would like to expend the previous project by adding more channels of physiological input from the user together with more sensory feedback to the user. In addition new VR scenes will be designed.
The project’s main objectives are - Getting to know the current system. Integrate new physiological inputs of Heart rate and breathing (which are additional outputs of the muse 2) to the system software. integrate a tactile sensory feedback to the user. Create new VR scenes.
- Excellence students
- Programming experience in C++ and/or Python
- Advantage courses in Machine/Deep Learning and/or Image Processing
Learning based mother-child movement synchronization

Mother-child joint storytelling is known to promote the child's cognitive and emotional skills. Behavioral \ physiological synchrony between parent and child during a joined interaction can give a quantified parameter of their relationship and indicate the interaction session's quality. We can evaluate synchrony between mother and child during mutual interaction sessions using various behavioral and physiological measures. In this project, we will focus on mother-child movement synchronization during collaborative storytelling. We will use an existing data set of videos; each has a recording of a mother telling stories to her child.
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.
Alon Zvirin