The Cardiff Undergraduate Research Opportunities Programme (CUROP) programme provides summer placements for Cardiff University undergraduates in the University research environment.
CUROP offers a stipend of £2100 (£262.50 per week) to support a student on a placement of eight weeks duration. It is now considered to be one of the largest undergraduate research schemes in the UK. It offer excellent work experience, experience of working on a research project and looks excellent on any student's CV!
The estimated rate that information enters the human eye is a staggering 72GB/s. Using very sluggish neurons and a power budget of a few watts the human brain processes this information, creates a percept of a stable world and detects important events occurring within the world, significantly outperforming conventional computer vision methods. How does the brain achieve such efficient and fast processing? Predictive coding is a term used by brain scientists to describe an idea that has its roots in the earliest days of psychology, and had a later echo in the field of cybernetics. The theory proposes that in order to drastically reduce the inherent data processing requirements, and thus achieve efficiency, the brain tries to predict incoming sensory information. It does this for two reasons. First, the processing demands for testing a prediction of what something is are considerably lower than for deducing what something is. Second, prediction failures indicate sensory input that merits extra processing resources, where something is changing or incongruent.
The Schools of Computer Science and Psychology in collaboration with School of Engineering Sciences, Bristol University have recently been awarded an EPSRC funded project to build the first artificial predictive vision system. The potential applications of this technology are broad (e.g. healthcare, security, ubiquitous computing), and the technology could be used as part of a standalone computer-based system, or to help or augment a human operator.
The project will have been running for a few months prior to the CUROP project. COMSC and PSYCH share the Human Factors Technology Centre (HFTC), where the student will be based and will use resources available in the Lab (PC, Sensors etc.). This exciting new research builds on the 14 year collaborative experience of Profs Marshall and Rushton and a recently established link Dr. Moran (Bristol). The work strategically aligns with both Schools’ strategic research plans in respective areas of Computer and Human Vision.
The student will gain valuable research experience at the cutting edge of Computer Science, Vision Science and Computational Neuroscience.
In order, to build such a system a unique dataset needs to be assembled. The student will assist in assembling a data capture system – a portable video camera that also records 3D depth plus an inertial sensor to measure camera movement. We plan to take a bike helmet, strap on the system walk and around Cardiff to generate a rich dataset of city scenes. Data will need to captured, processed and archived, a task the student will assist in.
In order to predict scenes, an understanding of the scene captured in the current and previous frames is required. For this purpose, we propose to utilise off-the-shelf publicly available research code (in-house, standard toolboxes etc.). For example, methods that can analyse basic motion in the scene (optical) and from this high level physics based motion (e.g. moving car) or human activity (e.g. walking pedestrian) are required. The student will evaluate current available methods on our newly acquired data set. This provides the student with invaluable exposure to current video analysis methods.
The student will work in Human Factors Technology Centre (HFTC), an interdisciplinary research involving the Schools of Computer Science, Psychology and Engineering and a proven successful CUROP environment. The student will work directly with the supervisors and an RA on a topic aligned with a recent successful EPSRC grant application. To ensure successful completion, including daily 30 minute meetings and longer weekly review meetings.
The project will also involve working with academics, RAs and PhD at the Computational Neuroscience Lab, School of Mathematical Sciences, Bristol University who area partner on the project. There will be regular visits to and from this lab. The student will have the opportunity to meet and interact with other RAs and PhD students working on complimentary research in the HFTC.
The student will attend the weekly COMSC Visual Computing seminars and also attend, if appropriate, weekly Psychology research seminars. The student will attend the weekly (Skype) project meetings and the monthly face-to-face project meeting and present and discuss progress at these meetings.
The student’s skills will be enhanced by:
Essential skills include proficiency with the MATLAB/Pythoin/C++ . Candidates from Computing, Physics, Maths and Engineering are welcome. Please note that final-year students are not eligible.
Project Start/End Dates: Any 8 week period from 18th June 20187 to August 24th 2018.
Contact/Supervisors:
For further details and application forms please see the official Cardiff University CUROP web page.