There is currently no accurate measurement of dietary intake.  All current methodologies of assessing food intake have inaccuracy rates of 30-70%. Yet accurate assessment of nutritional intake is a prerequisite to define the nutritional status, nutritional needs of a population and to monitor the effectiveness of public health interventions to maintain nutritional health. To this end, it is necessary to develop tools that facilitate accurate assessment of nutritional intake in populations without affecting their normal routines. Existing dietary methods are labour-intensive, expensive, and do not report nutritional intake accurately or social hierarchy of food intake.  To address this gap in dietetics, the group aims to develop a passive dietary monitoring system for accurate nutritional intake analysis. Example of our recent works:

• An Intelligent Nutritional Assessment System for Handheld Food Items via Weakly-Supervised Point Cloud Completion
• Clustering Egocentric Images in Passive Dietary Monitoring with Self-Supervised Learning
• A Computer Vision-based Passive Dietary Intake Monitoring System for Assessing Dietary Intake in Low-and Middle-Income Countries (LMICs)
• An ergocentric approach for counting bites and recognizing consumed food
•  A Vision-based Dietary Assessment Approach using View Synthesis