Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Unsupervised, explainable image segmentation/classification using Hyperspectral data


   Department of Computer Science

  Prof X Hong,  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

Hyperspectral data is acquired by sensors that record data for hundreds to thousands of electromagnetic wavelengths as individual bands. The rich information in the various wavelengths is particularly useful in remote sensing applications, such as identification of vegetation, water bodies, and roads, as different landscapes have distinct spectral signatures. The high dimensionality of hyperspectral data, poses unique challenges in computer vision. Unsupervised and self-learning is desired as supervised learning would be very limited due to lack of labels.

This project is focused on research on advanced pre-processing algorithms of Hyperspectral data so that conventional computer vision algorithms may be applied. The objectives include new algorithms of dimensionality reduction, band selection, super pixel algorithms for various applications that are amenable to explainability. 

Requirements: UK honours equivalent in Computer Science, Maths, Engineering

For further details contact:

Computer Science (8) Information Services (20)

Register your interest for this project



Where will I study?