Active Machine Perception of Humans in Dynamic Scenes for Safer Intelligent Systems
The Centre for Vision Speech and Signal Processing (CVSSP) seeks applications from high-quality students for a fully funded studentship, on Active Machine Perception. Active machine perception is essential to develop intelligent systems capable of safely interacting with humans and their surroundings. The aim of this PhD is to significantly advance machine perception to enable machines to function autonomously in our day-to-day environment. The student will be based at CVSSP in the UK with the opportunity to collaborate with Agency for Science, Technology and Research (A*STAR), Singapore during the project.
Start date1 October 2021
DurationStandard project duration is 4 years.
Funding sourceThe University of Surrey, Project-led Studentship Award.
The funding package for this studentship award is as follows:
- Full tuition fee covered (UK, EU and International)
- Stipend at £15,609 p.a. (2021/22)
- Research Training Support Grant of £1,000 p.a.
- Personal Computer (provided by the department)
Active machine perception (AMP) is essential to develop intelligent systems capable of safely and intelligently interacting with humans and their surroundings. The goal of this PhD is to significantly advance AMP of humans in our day-to-day environment to better understand social human behaviour by identifying users, understanding and predicting their actions.
Existing methods in AMP either work for a single task (3D/Action detection/prediction) or simple scenes (1-2 people). The PhD aims to address the following objectives:
- 4D (3D tracked in time) semantic modelling of general scenes.
- Action detection and prediction exploiting the motion and semantic reconstruction.
- Multi-task active machine perception (AMP) of humans in real-world scenes.
The project will explore human-like scene understanding on dynamic scenes from single-view/multiple-view videos exploiting recent advances in Artificial intelligence (AI). This research will solve an open challenging problem and enable machines to function autonomously in real-world social scenes, creating an impact in various fields such as autonomous driving and robotics.
The PhD will be jointly supervised by Dr. Armin Mustafa and Prof. Adrian Hilton based at the Centre for Vision Speech and Signal Processing (CVSSP). There will be collaboration opportunities with A*STAR, Singapore.
Related linksCentre for Vision, Speech and Signal Processing (CVSSP)
Candidates must hold a first class or 2:1 honours degree (or equivalent overseas qualification) in an appropriate discipline (e.g. engineering, computer science, signal processing, applied mathematics, and physics).
Candidates should be able to demonstrate excellent mathematical, analytic, programming skills.
Previous experience in computer vision and machine/deep learning would be advantageous.
IELTS requirements: IELTS 6.5 or above (or equivalent) with no sub-test of less than 6.
This studentship is open to UK, EU and international students.
How to apply
Applications should be made through our Vision Speech and Signal Processing PhD programme page and should specify the point of contact as Prof. Adrian Hilton.
You must also attach a CV, certified copies of degree certificates and transcripts, a personal statement describing relevant experience (maximum 2 pages), two references, and proof of eligibility (eg. passport or residence permit). Shortlisted applicants will be contacted directly to arrange a suitable time for an interview.