<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-07-08T08:44:08Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/0A617E71-E423-4B04-8804-83941CF14EB8" ns1:id="0A617E71-E423-4B04-8804-83941CF14EB8"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/D21CA0D0-2C7D-4E85-BB14-F638BC1522E9" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/6435812F-3533-474F-A08E-0BB3613C621E" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/6435812F-3533-474F-A08E-0BB3613C621E" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2021-04-29T23:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/C3CA0E95-383B-4C71-AADA-71FC4DB5C22F" ns1:rel="FUND" ns1:start="2020-11-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">85837</ns2:identifier></ns2:identifiers><ns2:title>INtelligent FOod Recognition and Monitoring for patient wellbeing (INFORM)</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Collaborative R&amp;D</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>Caloric intake from meals provides crucial data for patients' wellbeing in hospitals, care homes and other places. Such data helps to monitor patients' recovery process and fine tune any required medical attention. At present this data is manually collected by the care assistants which leads to paper trails followed by a data entry to the system. The manual data collection in a hospital or care home poses risk of contamination and spread of infectious diseases especially in the current Covid-19 situation. The manual estimation of the consumption is often not accurate and erroneous. Therefore, there is a gap in the market that can efficiently address these issues, for example, collecting such information accurately in a non-invasive way.

This project proposes to develop a 'Smart Catering Trolley' that uses computer vision and IoT to automatically record how much of each food a patient in hospital, or care home resident, consumes. This will allow care providers to accurately track the nutritional intake of patients and provide increased quality of care, while alleviating the workload of staff, and reduce the chances for the transmission of Covid-19 to the most vulnerable. It will also reduce the quantity of food waste, preserving valuable NHS and care homes resources and reducing environmental impacts. This will be achieved through a collaboration between the Stirling Vision and Image Processing research group at University of Stirling and Falcon Foodservice Equipment.

A set of optical and thermal cameras will be fitted to catering trolley which will capture what is served at what temperature to individual patients using a unique computer vision algorithm deployed on a portable embedded hardware (e.g., Raspberry Pi). The algorithm will calculate how much of each food a patient has eaten, allowing medical professionals to accurately track their diets over the course of their stay, ensuring that they have the nutrients they need to recover as quickly as possible. Additionally, the smart trolley will have capability to store and reheat the food at the point of serving. The generated data will be sent to a computing server using the UK's existing IoT infrastructure for further analysis of the patient nutrient data. The use of IoT networks will reduce the reliance of the system on the Internet which is often not available in the hospital environment. This innovative solution will be useful for a large number of NHS hospitals and care homes across the UK and internationally aiding social distancing which is expected to be the new normal.</ns2:abstractText></ns2:project>