Explore platform

Foot keypoints

Overview

The ground truth exposed in this modality is a set of foot landmarks that conforms to a standard created by the CMU Perceptual Computing Lab.

This modality consists of the following files:

Relevant file	Location
feet_key_points.json	key_points folder
all_key_points.json	key_points folder

feet_key_points.json

Faces platformHumans in Context platform

This file contains the locations of 3 landmarks on each foot. These keypoints conform to the CMU Perceptual Computing Lab foot landmark standard.

The locations of the 6 foot landmarks developed by the CMU Perceptual Computing Lab. Source: https://cmu-perceptual-computing-lab.github.io/foot_keypoint_dataset/

The file has the following format:

{
    "version": "2.0.1",
    "feet": {
        "left": {
            "heel": {
               // Heel keypoint
            }
            "index": {
               // Index toe keypoint
            }
            "pinky": {
               // Pinky toe keypoint
            }
        }
        "right": {
            "heel": {
               // Heel keypoint
            }
            "index": {
               // Index toe keypoint
            }
            "pinky": {
               // Pinky toe keypoint
            }
        }
    }
}

Objects and fields:

• version: String. Version tracking for this file. Whenever you access this file in a datapoint, make sure to check that the version matches what you expect it to be; otherwise its format and fields may not be recognized.

• left: Object. This object contains 3 objects, heel, index, and pinky, each identifying a specific keypoint in the left foot. Each one has the same format:

  "heel": {
     "global_3d": {
        "x": 0.0649380311369896,
        "y": 0.04291728511452675,
        "z": 0.11093330383300781
     },
     "pixel_2d": {
        "x": 91.42204655475659,
        "y": 31.024237959018187
     },
     "is_visible": "true"
  },
  

  • global_3d: Object. Contains a set of three Floats giving the location of the keypoint in global coordinates: “x”, “y”, and “z”. See About our coordinate systems for details.

  • pixel_2d: Object. Contains a set of two Floats giving the x and y coordinates of the keypoint in the rendered image itself. This provides not only which pixel contains the keypoint but also precisely where the keypoint is inside the pixel. See About our coordinate systems for details.

  • is_visible: Boolean. Indicates whether the keypoint is visible in the images produced by this camera. The value of this field is false if the keypoint is outside the frame or is on the other side of the body from the camera. Otherwise the value is true, even if there is another object between the keypoint and the camera.

• right: Object. This object has the same structure as “left” above, except it identifies the 3 keypoints in the right foot.

Using this ground truth, you can train your model to recognize the shape and location of the human foot.

all_key_points.json

For convenience, this file includes the same set of keypoints as feet_key_points.json above, located at this position in the hierarchy:

{
    "feet": {
        "left": {
            // 3 keypoint objects
        }
        "right": {
            // 3 keypoint objects
        }
    }
}

For details on the structure of the keypoint objects, see feet_key_points.json above.

Note

all_key_points.json also includes additional foot keypoints that represent part of the Body keypoints modality.