FoodTrack: Estimating Handheld Food Portions with Egocentric Video
This provides a more accurate and adaptable solution for nutrition and health monitoring by directly measuring food volume without relying on specific camera angles or gesture assumptions.
The paper tackles the problem of tracking food consumption by estimating the volume of handheld food items from egocentric video, achieving an absolute percentage loss of approximately 7.01%, which improves upon a previous approach with 16.40% error under less flexible conditions.
Accurately tracking food consumption is crucial for nutrition and health monitoring. Traditional approaches typically require specific camera angles, non-occluded images, or rely on gesture recognition to estimate intake, making assumptions about bite size rather than directly measuring food volume. We propose the FoodTrack framework for tracking and measuring the volume of hand-held food items using egocentric video which is robust to hand occlusions and flexible with varying camera and object poses. FoodTrack estimates food volume directly, without relying on intake gestures or fixed assumptions about bite size, offering a more accurate and adaptable solution for tracking food consumption. We achieve absolute percentage loss of approximately 7.01% on a handheld food object, improving upon a previous approach that achieved a 16.40% mean absolute percentage error in its best case, under less flexible conditions.