3D vision and robotic navigation using Event and Polarisation Cameras

The project will explore the use of emerging imaging modalities such as even and polarisation cameras to perform 3D vision in very dynamic, complex and un-textured environment where classical approaches fail in general.
Description of the Project: 

Optical cameras have been very successfully used for 3D vision and robotic navigation in texture rich environments and good visibility conditions. However, they have strong limitations in more complex scenarios where the environment is either very dynamic or visibility is poor. In this thesis, you will explore new sensor modalities and how they can help solve these problems. Event cameras offer very high frame rates and can be used in extremely dynamic environments (more than 10k frames per second) whilst polarisation can be used to improve visibility in the presence of haze/scattering and help reconstruct structures with low textural content. These two modalities can be used together to provide robust sensing and navigation in complex environments such as the underwater domain which will be the primary application focus of the work.

Resources required: 
Project number: 
First Supervisor: 
Heriot-Watt University
Second Supervisor(s): 
First supervisor university: 
Heriot-Watt University
Essential skills and knowledge: 
Strong programming skills (Matlab and C++) Background in data science (optimization, machine learning, applied mathematics)
Desirable skills and knowledge: 
Experience with Python, ROS