Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.04055 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912363564761088 |
|---|---|
| author | Wang, Ervin Chen, Yuhao |
| author_facet | Wang, Ervin Chen, Yuhao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04055 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FoodTrack: Estimating Handheld Food Portions with Egocentric Video Wang, Ervin Chen, Yuhao Computer Vision and Pattern Recognition 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. |
| title | FoodTrack: Estimating Handheld Food Portions with Egocentric Video |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.04055 |