2SR Python API

bob.rppg.ssr.ssr_utils.get_skin_pixels(face_frame, index, facewidth, skininit, threshold, bounding_boxes=None, skin_frame=None, plot=False) → skin_pixels[source]

Get a list of skin colored pixels inside the given frame.

Parameters

face_frame (numpy array):
The frame where the face has to be detected.
index (int):
The index of the frame containing the face to be detected.
skininit (boolean):
Flag if you want the parameters of the skin model to be re-estimated.
threshold (float [0-1]):
The threshold on the skin color probability.
bounding_boxes (list of BoundingBoxes):
The face bounding boxes corresponding to the sequence.
skin_frame (numpy array):
The frame where the skin pixels have to be retrieved. If not set, face_frame will be used.
plot (boolean):
Flag to plot the result of skin pixels detection

Returns

skin_pixels (numpy array):
The RGB values of all detected skin colored pixels
bob.rppg.ssr.ssr_utils.get_eigen(skin_pixels) → eigenvalues, eigenvectors[source]

Build the C matrix, get eigenvalues and eigenvectors, sort them.

Parameters

skin_pixels (numpy array):
The RGB values of skin-colored pixels.

Returns

eigenvalues (numpy array):
The eigenvalues of the correlation matrix
eigenvectors (numpy array):
The (sorted) eigenvectors of the correlation matrix
bob.rppg.ssr.ssr_utils.plot_eigenvectors(skin_pixels, eigenvectors, counter)[source]

Plots skin pixel cluster and eignevectors in the RGB space.

Parameters

skin_pixels (numpy array):
The RGB values of skin-colored pixels.
eigenvectors (numpy array):
The eigenvectors of the correlation matrix.
bob.rppg.ssr.ssr_utils.build_P(counter, temporal_stride, eigenvectors, eigenvalues, plot=False) → p[source]

Builds P

Parameters

counter (int):
The frame index
temporal_stride (int):
The temporal stride to use
eigenvectors (numpy array):
The eigenvectors of the c matrix (for all frames up to counter).
eigenvalues (numpy array):
The eigenvalues of the c matrix (for all frames up to counter).
plot (boolean):
If you want something to be plotted

Returns

p (numpy array):
The p signal to add to the pulse.