Aberdeen University Featured PhD Programmes
University of Portsmouth Featured PhD Programmes
University of West London Featured PhD Programmes
University of Kent Featured PhD Programmes
University of Reading Featured PhD Programmes

Illumination-Robust Neural Networks for Computer Vision (GONGHU20SCIEC)


Project Description

We will develop a novel Neural Network (NN) component which offers independence of illumination change (e.g. [1,3]) for general NN-based computer vision tasks such as image segmentation and classification. As a fundamental component like ResNet [2], this will enable the major computer vision systems to work robustly in any lighting conditions. For example, our neural network trained using only a set of cloudy-condition images will have consistent performance for the ‘unseen’ input images with a lot of shadows. With this technology, we can be more certain that our driverless cars will also behave well in complicated light or limited visibility conditions (e.g. foggy weather).

We aim to make this component simple, scalable, efficient and easy-to-integrate so that it can be deployed everywhere from your mobile phone to a computing cloud. We will start experimenting with the task of object recognition before extending the tests to the others (e.g. image segmentation and 3-D reconstruction).

For more information on the project’s supervisor, please visit: https://people.uea.ac.uk/h_gong
Type of programme: PhD
Start date of project: October 2020
Mode of study: full time
Studentship length: funding is available for 3 years
Location: UEA
Entry requirements: acceptable first degree in Computer Science or any other science, engineering, and mathematics
degrees. The standard minimum entry requirement is 2:1

Funding Notes

This PhD project is in a competition for a Faculty of Science funded studentship. Funding is available to UK/EU applicants and comprises home/EU tuition fees and an annual stipend of £15,009 for 3 years. Overseas applicants may apply but they are required to fund the difference between home/EU and overseas tuition fees (which for 2019-20 are detailed on the University’s fees pages at View Website . Please note tuition fees are subject to an annual increase).

References

[1] Alshammari, Naif, Samet Akcay, and Toby P. Breckon. "On the Impact of Illumination-Invariant Image Pre-transformation for Contemporary Automotive Semantic Scene Understanding." 2018 IEEE IVS. 2018.
[2] He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE CVPR. 2016.
[3] Gong, H. “Convolutional Mean: A Simple Convolutional Neural Network for Illuminant Estimation.” BMVC. 2019.

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2020
All rights reserved.