Automatic Learning with Superpixel Guidance for Hyperspectral Image Classification

The objective of this project is to investigate and develop a novel automatic classification approach for hyperspectral image with superpixel guidance. This project will design a unique and higher dimensional network to capture richer spatial and spectral information. How to combine these advanced techniques and deep learning to match the hyperspectral image in an automatic way is a challenge for this project to address. After obtaining the superpixel map in hyperpsectral image, the project will move forward to output the classification results with superpixel guidance. To achieve this, a statistical technique and the probabilistic perspective evaluated through deep learning are to be applied.

The research of advanced classification algorithms to the hyperspectral image is anticipated to deliver novel and significant research findings that will be of substantive interest to researchers in many interrelated fields, such as machine learning, image processing and geoscience. Application of deep learning to high dimensional images, involving both in segmentation and classification, is highly topical in social academic recently, and the results of that could be attractive to many academia to study.

Globally speaking, remote sensing technique has superiority in environmental monitoring like the global warming detection and drought monitoring. Hyperspectral image classification, as a major application in remote sensing, contribute to understand global climate and environmental change. The timely and automatic classification method in the hyperspectral images can also help to apply to food safety, pharmaceutical process monitoring and quality control, resources exploration, forest protection and so on.

The doctoral student will receive full PhD training during the project, where he/she will receive regular support from an experienced supervisory team, where the expertise from both Bournemouth University and Shenzhen University are complementary. The student will be equipped with advanced machine learning knowledge, convolutional neural network and image processing. He/she will become fully qualified scholar with his/her expertise and skills in conducting the relevant research work independently. Apart from university level training programs the Doctoral College offers, in the Faculty of Science & Technology a series of research presentations and seminars will give the student a wide view and exposure to research methodology and strategy.

The PhD Studentships are open to UK, EU and international students. Candidates for a PhD Studentship should demonstrate outstanding qualities and be motivated to complete a PhD in 4 years and must demonstrate:

a 1st class honours degree and/or a relevant Master’s degree with distinction or equivalent.If English is not your first language you’ll need IELTS (Academic) score of 6.5 minimum (with a minimum 6.0 in each component).

Additional eligibility criteria:

Candidates must demonstrate a strong background in computer science and/or mathematics.

In addition to satisfying minimum entry criteria, BU will look closely at the qualities, skills and background of each candidate and what they can bring to their chosen research project in order to ensure successful completion.

Applicants will be asked to submit an online application form and a proposal (approximately 1500 words) outlining their understanding of the project for which they are applying, the approach they would envisage taking and what qualities they will bring to the research community.

Please note:

Current BU Doctoral students are not eligible to apply for a Studentship
Current MRes/MPhil students can apply, subject to satisfactory completion of their Research Degree prior to being able to take up the award PhD Studentships cannot be used to support BU staff to complete doctoral programmes.

How to apply: Applications are made via our website using the Apply Online button below. If you have an enquiry about this project please contact us via the Email NOW button below, however your application will only be processed once you have submitted an application form as opposed to emailing your CV to us.