The keypoint detection format used in the Microsoft COCO project.
Below, learn the structure of COCO Keypoint.
{
"info": {
"year": "2024",
"version": "1",
"description": "Exported from roboflow.com",
"contributor": "",
"url": "https://public.roboflow.com/object-detection/undefined",
"date_created": "2024-09-10T07:12:44+00:00"
},
"licenses": [
{
"id": 1,
"url": "https://creativecommons.org/licenses/by/4.0/",
"name": "CC BY 4.0"
}
],
"categories": [
{
"id": 0,
"name": "glue-Qg7R",
"supercategory": "none"
},
{
"id": 1,
"name": "glue",
"supercategory": "glue-Qg7R",
"keypoints": [
"bottom",
"top"
],
"skeleton": [
[
1,
2
]
]
}
],
"images": [
{
"id": 0,
"license": 1,
"file_name": "IMG_4900_JPG_jpg.rf.21d9ecc535939df6226dbf15204e64a1.jpg",
"height": 640,
"width": 640,
"date_captured": "2024-09-10T07:12:44+00:00"
},
]
}
With Roboflow supervision, an open source Python package with utilities for completing computer vision tasks, you can merge and split detections in COCO Keypoint. Read our dedicated guides to learn how to merge and split COCO Keypoint detections.
Below, see model architectures that require data in the COCO Keypoint format when training a new model.
On each page below, you can find links to our guides that show how to plot predictions from the model, and complete other common tasks like detecting small objects with the model.