PhD Studentship in Computer Vision and Artificial Intelligence

University of Southampton School of Electronics and Computer Science

United Kingdom

PhD Studentship in 3D semantic scene understanding with Computer Vision and Artificial Intelligence

Vision, Learning and Control

Location: Highfield Campus

Closing Date: Thursday 20 August 2020

Reference: 1270520FP

Supervisory Team: Dr. Hansung Kim

Computer Vision is one of the most active areas where artificial intelligence (AI) is being used. This area is extremely expanding and getting a lot of interests and investments these days. Taking advantages of recent advancements in deep learning, active perception of an environment or human behaviours have shown significant improvement in building new knowledge and practical applications in our daily life.

The University of Southampton is ranked in the top 1% of universities worldwide, and the School of Electronics and Computer Science (ECS) is the leading department of its kind in the UK with a long tradition of interdisciplinary research. We actively encourage and support our PhD students to pursue their research and other activity within their fields of interest.

Project Description

Visual scene understanding studies the task of representing a captured scene in a manner emulating human-like understanding of that space. Attaining this understanding is crucial for applications such as entertainment, robotics, smart home, security systems, healthcare, assisted living, etc. The student will investigate the benefits of including human activity information in indoor scene understanding challenges, aiming to demonstrate its potential contributions, applications, and versatility. Various vision sensors can be considered such as normal cameras, depth cameras and 360 spherical cameras. There can be a chance of collaborative research with BBC R&D or Institute of Sound and Vibration Research (ISVR) for application development in audio-visual scene understanding and reproduction.

Requirements

All applicants are required to have a first or upper-second class honours degree (or equivalent). Candidate without a MSc or MEng in computer vision, computer graphics, machine learning or applied mathematics would have to provide strong justification that they would be able to handle the maths and programming necessary to complete a PhD in this field.

The essential selection criteria include:

- Prior knowledge in the areas of computer vision and machine learning (especially deep learning).

- Proficiency in one or more of C++ / Python / Matlab

- Ability to work independently or as part of a team.

The desirable selection criteria include:

- Project experience or working experience in the areas of computer vision and machine learning (especially deep learning)

- Experience in camera systems (vision camera, Kinect, 360 cameras, etc.).

Funding Opportunities

For UK and EU (who live in the UK over 3 years) students, DTP scholarship (3.5-year full tuition fee and stipend £15,285 tax-free per annum) is offered.

Application

Please email me (h.kim@soton.ac.uk) with your CV asap before you officially apply to the university to save time and adjust our schedule.

If you wish to discuss any details of the project informally, please contact Dr. Hansung Kim, VLC/ECS Research Group, Email: h.kim@soton.ac.uk

Closing date: applications should be received no later than 20 August 2020 for standard admissions, but later applications may be considered depending on the funds remaining in place.

How To Apply

Applications should be made online, please select the academic session 2020-21 “PhD Computer Science(Full time)” as the programme. Please enter Hansung Kim under the proposed supervisor.

Applications should include:

Research Proposal

Curriculum Vitae

Two reference letters

Degree Transcripts to date

Apply online:

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

 


In your application, please refer to Polytechnicpositions.com

FACEBOOK
TWITTER
LINKEDIN

baner1

baner10

baner11

baner12

baner14

baner2

baner3

baner4

baner5

baner6

baner8

baner9