Advanced Methods in Hyperspectral Imagery Analysis for Smart Sensing Applications University of Dundee

Programme Structure

This project will have the following objectives:

• develop dimension reduction techniques to condense the high-dimensional hyperspectral data into more manageable formats without losing critical information. This will improve computational efficiency and facilitate more effective analysis.

• enhance band selection to identify the most relevant wavelengths for a given application. This allows customization of multispectral cameras to reduce costs, improving practicality of hyperspectral imaging.

• the project will apply these advanced techniques to key computer vision tasks, specifically change detection and anomaly detection, to enhance decision-making in smart sensing applications. This includes diverse areas such as land mapping in remote sensing; retina and brain image analysis, aiding in early and accurate clinical diagnosis; non-destructive inspection for material characterization.