Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

The PUPILLO tracker: next generation eye tracking

Project description

Eye-tracking for reliable cognitive measurement

Accurate measurement of cognitive processes through eye-tracking is hindered by technological limitations, particularly in reliably capturing pupil size changes driven by cognition. Existing commercial eye-trackers often suffer from data loss and unreliable readings, especially in dynamic or challenging environments. This issue is especially pronounced when working with certain populations, such as infants, where traditional systems struggle to maintain accuracy. With this in mind, the ERC-funded PUPILLO project aims to introduce an innovative eye-tracking system that combines advanced hardware and software solutions. Features include offline data retrieval, robotic tracking, and autofocus, ensuring more reliable measurements even with greater participant movement. Pilot studies have shown dramatic improvements, offering a flexible, cost-effective, and precise tool for the research and medical communities.

Objective

Eye-tracking is one of the most valuable tools for measuring human behaviour, applicable to multiple populations and stages of development, and their use has enjoyed an exponential increase both within and outside of research. Pupil size, measurable with eye-trackers, provides a valuable index of a wide range of cognitive functions. However, pupillometry has significant untapped potential because current commercial eye-trackers are unable to provide reliable indications of cognitively driven pupil changes. This results in a restricted design space for research, large loss of data and often unreliable measurement.
We propose a novel architecture of remote eye-tracker for behavioural research, conceived to address both the problem of large data loss, and the problem of reliability of pupil size changes. Our solution addresses these pains at both the hardware and software levels, with a series of innovations including an identical offline mode to retrieve otherwise lost data, and autofocus and robotic tracking to accommodate much greater participant movement. In pilot experiments, with infants, we have increased the proportion of usable data from about 50% with the current state of the art, to close to 100%. We are currently developing procedures and algorithms to compensate for the light reflex so that pupil dynamics data is deconfounded, and acquisition possible over a much larger span of stimuli and situations. PUPILLO aims to become the next generation eye-tracker, providing the research and medical communities and beyond, with a cost-effective, easy-to-use and customizable solution to fully exploit the potential of gaze tracking and pupillometry.

Fields of science (EuroSciVoc)

This project has not yet been classified with EuroSciVoc.
Be the first one to suggest relevant scientific fields and help us improve our classification service

Programme(s)

Topic(s)

Funding Scheme

HORIZON-ERC-POC - HORIZON ERC Proof of Concept Grants

See all projects funded under this funding scheme

Call for proposal

(opens in new window) ERC-2024-POC

See all projects funded under this call

Host institution

KOBENHAVNS UNIVERSITET
Net EU contribution
€ 150 000,00
Address
NORREGADE 10
1165 KOBENHAVN
Denmark
Region
Danmark Hovedstaden Byen København
Activity type
Higher or Secondary Education Establishments
Links
Total cost
No data

Beneficiaries (1)