PhD Studentship - Combined audio-visual 3D scene analysis

Employer
University of Southampton
Location
Southampton, United Kingdom
Posted
May 01, 2021
Closes
Jun 25, 2021
Ref
166517
Organization Type
University and College
Hours
Full Time
Supervisory Team: Dr Hansung Kim, Dr Filippo Maria Fazi

Project description

This project aims to unlock the potential of combined Audio-Visual Machine Perception to underpin advances in the science of machine perception for future intelligent technologies. This project requires collaboration of highly intelligent technologies, including machine learning, computer vision and audio signal processing.

Combined audio-visual scene analysis is inspired by human multi-modal perception of reality and has the obvious potential to overcome the limitations of scene analysis performed with either audio or video sensors alone. Audio and vision approaches are complementary to each other for scene understanding. In this project, a complete semantic scene understanding method using an off-the-shelf 360 panoramic camera and microphone arrays will be investigated. The goal is holistic understanding of a scene by joint audio and visual data analysis using deep learning. The work will investigate the application of AI algorithm to combined audio-visual scene analysis and will also explore the use of computer vision algorithms for audio processing and vice-versa.

Scene-centric analysis of 3D geometry can reveal semantic information and provide functional cues to enhance scene understanding tasks. The key objectives of this project will be designing, realising and testing a system that can perform a complete geometrical and acoustical reconstruction of an environment. The system will consist of: 1) a 360 camera, 2) one or more microphones, 3) one or more loudspeakers, and 4) a stand-alone computing unit with AI and signal processing capabilities. We will explore the possibility of embedding a system with similar capabilities on a head-mounted VR/AR set or on autonomous vehicle.

This project is funded through the UKRI MINDS Centre for Doctoral Training (www.mindscdt.ai). This is one of 16 PhD training centres in the UK with a unique focus on advancing AI techniques in the context of real-world engineered systems with a remit that spans novel hardware for AI, AI and machine learning, pervasive systems and IoT, and human-AI collaboration. We provide enhanced cross-disciplinary training in electronics and AI, entrepreneurship, responsible research and innovation, communication strategies, outreach and impact development as part of an integrated 4-year iPhD programme.

The MINDS CDT is based in a dedicated laboratory on Highfield Campus at the University of Southampton. The lab provides a supportive environment for individual research, ideas sharing and collaboration, and the wider campus provides access to substantial high-performance computing (including dedicated GPU servers), maker and cleanroom facilities. You will take part in our annual, student-designed innovation camps, be able to work with industry and government partners through our internship scheme and be able to take part in exchanges with international university partners.

Entry Requirements

A very good undergraduate degree (at least a UK 2:1 honours degree, or its international equivalent).

Funding: full tuition for UK Students an enhanced stipend £18,285, tax-free per annum for 4 years.

How To Apply

Applications should be made online. Select programme type (Research), 2021/22, Faculty of Physical Sciences and Engineering, next page select iPhD Machine Intelligence for Nano-electronic Devices and Systems. (Full time). In Section 2 of the application form you should insert the project title and name of the supervisor.

Applications should include:
  • Research Proposal
  • Curriculum Vitae
  • Two reference letters
  • Degree Transcripts to date


Apply online here

For further information please contact: feps-pgr-apply@soton.ac.uk

We aim to be an equal opportunities employer and welcome applications from all sections of the community.

Similar jobs

Similar jobs