PhD Study : Computer vision for advertising analytics

Summary

Outdoor impressions have traditionally been measured using traffic counts and daily effective circulation in order to estimate reach. For years, these figures have been the only reliable counts available to measure the reach of out-of-home (OOH) advertising. More recently outdoor impressions take the focus from the number of consumers that can see an advertisement and convert that figure to a more realistic one estimating the number of consumers who actually noticed the advertisement. Often this requires the use of eye-tracking technology and despite the technological advances in making eye-tracking glasses much smaller and lightweight, their use still poses a possible liability in driving situations that some internal review boards are unlikely to approve.

These impression figures (often in weekly increments) are derived from a variety of data, specifically: Daily Effective Circulations (DECs), Census Data, Travel Surveys, Data Modeling, Analytics, and statistical conversion factors, or Visibility Adjustment Indices (VAIs).  VAIs take the physical characteristics into consideration when dealing with an outdoor structure. The index is based on eye-tracking related research and visibility research to form the statistical basis of an VAI model. This model takes various factors into account to arrive at the VAI of each inventory. These factors include the placement of the unit, what side of the road it’s on when viewed, the distance from traffic when viewed, visibility zone, the type of road it’s placed on, whether the unit is illuminated, the size, its angle relative to oncoming traffic and who it’s viewed by (vehicular traffic, pedestrian traffic, or both).  Other considerations include whether the sign is digital, scrolling or static and the size of each. This project will research and develop computational computer vision approaches to outdoor impression measurement through the use of automated sign recognition technology, saliency detection and demographic data.

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.

• Experience using research methods or other approaches relevant to the subject domain

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.

• Masters at 70%

Funding and eligibility

This project is funded by:

• Digital Natives

The scholarships will cover tuition fees and a maintenance award of £15,009 per annum for three years (subject to satisfactory academic performance). Applications are invited from UK, European Union and overseas students.