PhD Study : Adversarial Learning for Person Re-ID

Summary

Person identification and re-identification (Re-ID) has recently become a major topic in the field of computer vision and an essential component for the use of robotics in human-robot centric environments. Re-ID is a fundamental robotic capability for long-term interactions with people. It is important to know with whom the robot is interacting, as well as to remember user preferences. The problem is challenging due to a number of issues, not least due to the fact that person recognition systems often rely on visual full face views to enable face recognition but also encounter occlusions, background activity, viewpoint change, illumination conditions etc.

Many approaches to Re-ID are based on the use of images (rather than video) and focus on extracting discriminative features or metric learning. However, in reality, humans recognise each other from any viewpoint in any environment, often using soft biometrics as secondary information to improve the primary biometrics as they can be acquired from a distance. Soft biometrics can include personal attributes like gender, ethnicity, age, and physical characteristics that do not change significantly in adults over time. Hence, utilising soft biometric traits will improve person recognition accuracy.

Adversarial learning is a relatively new research field that lies at the intersection of machine learning and computer security. It aims at enabling the safe adoption of machine learning techniques in adversarial settings such as biometric recognition. Adversarial networks are designed where given a training set, they learn to generate new data with the same statistics as the training set. Based on an assumption that an image is composed of appearance and content factors, this approach removes the effects of changeable appearances.

This project will focus on innovations in computer vision and deep learning to develop novel analytical methods for Re-ID combining computer vision techniques for person identification with soft biometric features. Here, adversarial networks will be used to generate suitable training samples of soft biometric features to allow the system to generalise Re-ID to classes of persons with soft biometric features rather than individuals. The technology may be applied to many areas including human-robot collaboration in home, service and industrial environments. Using popular deep and shallow learning algorithms, we will train a mobile robotic system to readily identify humans in a dynamic human-robot centric environment. Benchmarking performance evaluation will be conducted using the well-known Market-1501, DukeMTMC-reID and CUHK03 datasets.

The Cognitive Robotics team in the Intelligent Systems Research Centre focuses on novel, advanced control methods for autonomous mobile robots, merging approaches from Artificial Intelligence, Cognitive Science and Engineering. Research in Cognitive Robotics at the ISRC ranges from investigating robotics as a science, to applications of robotics such as industrial robotics, assistive robotics and computer vision. The Cognitive Robotic laboratory contains a range of mobile robotics systems (Summit XLs, PR, Pioneers) equipped with 2D/3D vision sensors that can be utilised in this project.

Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

• Research proposal of 1500 words detailing aims, objectives, milestones and methodology of the project
• A demonstrable interest in the research area associated with the studentship

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

• First Class Honours (1st) Degree
• Masters at 70%
• For VCRS Awards, Masters at 75%
• Publications - peer-reviewed
• Experience of presentation of research findings
• Applicants will be shortlisted if they have an average of 75% or greater in a first (honours) degree (or a GPA of 8.75/10). For applicants with a first degree average in the range of 70% to 74% (GPA 3.3): If they are undertaking an Masters, then the average of their first degree marks and their Masters marks will be used for shortlisting.

Funding and eligibility

The University offers the following levels of support:

Vice Chancellors Research Studentship (VCRS)

The following scholarship options are available to applicants worldwide:

• Full Award: (full-time tuition fees + £19,000 (tbc))
• Part Award: (full-time tuition fees + £9,500)
• Fees Only Award: (full-time tuition fees)

These scholarships will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance) and will provide a £900 per annum research training support grant (RTSG) to help support the PhD researcher.

Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Please note: you will automatically be entered into the competition for the Full Award, unless you state otherwise in your application.

Department for the Economy (DFE)

The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).

This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

• Candidates with pre-settled or settled status under the EU Settlement Scheme, who also satisfy a three year residency requirement in the UK prior to the start of the course for which a Studentship is held MAY receive a Studentship covering fees and maintenance.
• Republic of Ireland (ROI) nationals who satisfy three years’ residency in the UK prior to the start of the course MAY receive a Studentship covering fees and maintenance (ROI nationals don’t need to have pre-settled or settled status under the EU Settlement Scheme to qualify).
• Other non-ROI EU applicants are ‘International’ are not eligible for this source of funding.
• Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Due consideration should be given to financing your studies. Further information on cost of living