Oktoberfest Food Dataset
This dataset addresses the need for specialized object detection data in food service settings, potentially improving efficiency for automated checkout systems, but it is incremental as it applies existing methods to a new domain.
The authors released a realistic and diverse dataset for object detection on images, specifically focusing on 15 categories of food and drink items from a beer tent in Germany, with over 2,500 hand-annotated objects in 1,110 images and additional unlabeled footage. They also provided trained models as a benchmark for applications like automated checkout systems.
We release a realistic, diverse, and challenging dataset for object detection on images. The data was recorded at a beer tent in Germany and consists of 15 different categories of food and drink items. We created more than 2,500 object annotations by hand for 1,110 images captured by a video camera above the checkout. We further make available the remaining 600GB of (unlabeled) data containing days of footage. Additionally, we provide our trained models as a benchmark. Possible applications include automated checkout systems which could significantly speed up the process.