xrmocap.core

estimation

evaluation

smplify hook

train

visualization

xrmocap.data

data_converter

dataloader

dataset

data_visualization

xrmocap.data_structure

xrmocap.human_perception

bbox_detection

keypoints_estimation

xrmocap.io

xrmocap.model

architecture

xrmocap.ops

projection

xrmocap.transform

keypoints3d.optim

xrmocap.utils

xrmocap.utils.project_point_radial(x, R, T, f, c, k, p)

This function is to project a point in 3D space to 2D pixel space with given camera parameters.

Parameters

• x – Nx3 points in world coordinates

• R – 3x3 Camera rotation matrix

• T – 3x1 Camera translation parameters

• f – (scalar) Camera focal length

• c – 2x1 Camera center

• k – 3x1 Camera radial distortion coefficients

• p – 2x1 Camera tangential distortion coefficients

Returns

ypixel.T – Nx2 points in pixel space

xrmocap.utils.unfold_camera_param(camera: dict)

This function is to extract camera extrinsic, intrinsic and distorsion parameters from dictionary.

Parameters

camera (dict) – Dictionary to store the camera parameters.

Returns

• R (Union[np.ndarray, torch.Tensor]) – Extrinsic parameters, rotation matrix.

• T (Union[np.ndarray, torch.Tensor]) – Extrinsic parameters, translation matrix.

• f (Union[np.ndarray, torch.Tensor]) – Focal length in x, y direction.

• c (Union[np.ndarray, torch.Tensor]) – Camera center.

• k (Union[list, torch.Tensor]) – Radial distortion coefficients.

• p (Union[list, torch.Tensor]) – Tangential distortion coefficients.