Object Detection

EventKitchen provides in total 13,482 bounding boxes of 12 object classes including: 1. Bowl, 2. Box, 3. Chopping board, 4. Cup, 5. Fork, 6. Knife, 7. Pan, 8. Plastic packaging, 9. Plate, 10. Spatula, 11. Spoon, and 12. Teapot. Two human annotators are firstly assigned to annotate the synchronized RGB data at an annotation frequency of 1 frame per 4 seconds. Then, the RGB annotations are projected to the synchronized event data streams by the calibration matrix and depth stream. More details of the annotation pipeline and statistics are reported in the paper.

As described in Download, in each recording session tree, the annotated bounding box of the left event camera is saved in objects/cooking_activity_LeftEvent_bbox.csv, of right event camera is saved in objects/cooking_activity_RightEvent_bbox.csv. We also provide the original RGB annotations in objects/cooking_activity_DRGB_bbox.csv. We provide more details of the annotation format and an script to load the annotation in the EventKitchen toolkit