248 lines
8.9 KiB
Plaintext
248 lines
8.9 KiB
Plaintext
|
# MediaPipe graph to detect/predict face landmarks. (CPU input, and inference is
|
||
|
|
# executed on CPU.) This graph tries to skip face detection as much as possible
|
||
|
|
# by using previously detected/predicted landmarks for new images.
|
||
|
|
#
|
||
|
|
# It is required that "face_detection_short_range.tflite" is available at
|
||
|
|
# "mediapipe/modules/face_detection/face_detection_short_range.tflite"
|
||
|
|
# path during execution.
|
||
|
|
#
|
||
|
|
# It is required that "face_landmark.tflite" is available at
|
||
|
|
# "mediapipe/modules/face_landmark/face_landmark.tflite"
|
||
|
|
# path during execution if `with_attention` is not set or set to `false`.
|
||
|
|
#
|
||
|
|
# It is required that "face_landmark_with_attention.tflite" is available at
|
||
|
|
# "mediapipe/modules/face_landmark/face_landmark_with_attention.tflite"
|
||
|
|
# path during execution if `with_attention` is set to `true`.
|
||
|
|
#
|
||
|
|
# EXAMPLE:
|
||
|
|
# node {
|
||
|
|
# calculator: "FaceLandmarkFrontCpu"
|
||
|
|
# input_stream: "IMAGE:image"
|
||
|
|
# input_side_packet: "NUM_FACES:num_faces"
|
||
|
|
# input_side_packet: "USE_PREV_LANDMARKS:use_prev_landmarks"
|
||
|
|
# input_side_packet: "WITH_ATTENTION:with_attention"
|
||
|
|
# output_stream: "LANDMARKS:multi_face_landmarks"
|
||
|
|
# }
|
||
|
|
|
||
|
|
type: "FaceLandmarkFrontCpu"
|
||
|
|
|
||
|
|
# CPU image. (ImageFrame)
|
||
|
|
input_stream: "IMAGE:image"
|
||
|
|
|
||
|
|
# Max number of faces to detect/track. (int)
|
||
|
|
input_side_packet: "NUM_FACES:num_faces"
|
||
|
|
|
||
|
|
# Whether landmarks on the previous image should be used to help localize
|
||
|
|
# landmarks on the current image. (bool)
|
||
|
|
input_side_packet: "USE_PREV_LANDMARKS:use_prev_landmarks"
|
||
|
|
|
||
|
|
# Whether to run face mesh model with attention on lips and eyes. (bool)
|
||
|
|
# Attention provides more accuracy on lips and eye regions as well as iris
|
||
|
|
# landmarks.
|
||
|
|
input_side_packet: "WITH_ATTENTION:with_attention"
|
||
|
|
|
||
|
|
# Collection of detected/predicted faces, each represented as a list of 468 face
|
||
|
|
# landmarks. (std::vector<NormalizedLandmarkList>)
|
||
|
|
# NOTE: there will not be an output packet in the LANDMARKS stream for this
|
||
|
|
# particular timestamp if none of faces detected. However, the MediaPipe
|
||
|
|
# framework will internally inform the downstream calculators of the absence of
|
||
|
|
# this packet so that they don't wait for it unnecessarily.
|
||
|
|
output_stream: "LANDMARKS:multi_face_landmarks"
|
||
|
|
|
||
|
|
# Extra outputs (for debugging, for instance).
|
||
|
|
# Detected faces. (std::vector<Detection>)
|
||
|
|
output_stream: "DETECTIONS:face_detections"
|
||
|
|
# Regions of interest calculated based on landmarks.
|
||
|
|
# (std::vector<NormalizedRect>)
|
||
|
|
output_stream: "ROIS_FROM_LANDMARKS:face_rects_from_landmarks"
|
||
|
|
# Regions of interest calculated based on face detections.
|
||
|
|
# (std::vector<NormalizedRect>)
|
||
|
|
output_stream: "ROIS_FROM_DETECTIONS:face_rects_from_detections"
|
||
|
|
|
||
|
|
# When the optional input side packet "use_prev_landmarks" is either absent or
|
||
|
|
# set to true, uses the landmarks on the previous image to help localize
|
||
|
|
# landmarks on the current image.
|
||
|
|
node {
|
||
|
|
calculator: "GateCalculator"
|
||
|
|
input_side_packet: "ALLOW:use_prev_landmarks"
|
||
|
|
input_stream: "prev_face_rects_from_landmarks"
|
||
|
|
output_stream: "gated_prev_face_rects_from_landmarks"
|
||
|
|
options: {
|
||
|
|
[mediapipe.GateCalculatorOptions.ext] {
|
||
|
|
allow: true
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
# Determines if an input vector of NormalizedRect has a size greater than or
|
||
|
|
# equal to the provided num_faces.
|
||
|
|
node {
|
||
|
|
calculator: "NormalizedRectVectorHasMinSizeCalculator"
|
||
|
|
input_stream: "ITERABLE:gated_prev_face_rects_from_landmarks"
|
||
|
|
input_side_packet: "num_faces"
|
||
|
|
output_stream: "prev_has_enough_faces"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Drops the incoming image if enough faces have already been identified from the
|
||
|
|
# previous image. Otherwise, passes the incoming image through to trigger a new
|
||
|
|
# round of face detection.
|
||
|
|
node {
|
||
|
|
calculator: "GateCalculator"
|
||
|
|
input_stream: "image"
|
||
|
|
input_stream: "DISALLOW:prev_has_enough_faces"
|
||
|
|
output_stream: "gated_image"
|
||
|
|
options: {
|
||
|
|
[mediapipe.GateCalculatorOptions.ext] {
|
||
|
|
empty_packets_as_allow: true
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
# Detects faces.
|
||
|
|
node {
|
||
|
|
calculator: "FaceDetectionShortRangeCpu"
|
||
|
|
input_stream: "IMAGE:gated_image"
|
||
|
|
output_stream: "DETECTIONS:all_face_detections"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Makes sure there are no more detections than the provided num_faces.
|
||
|
|
node {
|
||
|
|
calculator: "ClipDetectionVectorSizeCalculator"
|
||
|
|
input_stream: "all_face_detections"
|
||
|
|
output_stream: "face_detections"
|
||
|
|
input_side_packet: "num_faces"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Calculate size of the image.
|
||
|
|
node {
|
||
|
|
calculator: "ImagePropertiesCalculator"
|
||
|
|
input_stream: "IMAGE:gated_image"
|
||
|
|
output_stream: "SIZE:gated_image_size"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Outputs each element of face_detections at a fake timestamp for the rest of
|
||
|
|
# the graph to process. Clones the image size packet for each face_detection at
|
||
|
|
# the fake timestamp. At the end of the loop, outputs the BATCH_END timestamp
|
||
|
|
# for downstream calculators to inform them that all elements in the vector have
|
||
|
|
# been processed.
|
||
|
|
node {
|
||
|
|
calculator: "BeginLoopDetectionCalculator"
|
||
|
|
input_stream: "ITERABLE:face_detections"
|
||
|
|
input_stream: "CLONE:gated_image_size"
|
||
|
|
output_stream: "ITEM:face_detection"
|
||
|
|
output_stream: "CLONE:detections_loop_image_size"
|
||
|
|
output_stream: "BATCH_END:detections_loop_end_timestamp"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Calculates region of interest based on face detections, so that can be used
|
||
|
|
# to detect landmarks.
|
||
|
|
node {
|
||
|
|
calculator: "FaceDetectionFrontDetectionToRoi"
|
||
|
|
input_stream: "DETECTION:face_detection"
|
||
|
|
input_stream: "IMAGE_SIZE:detections_loop_image_size"
|
||
|
|
output_stream: "ROI:face_rect_from_detection"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Collects a NormalizedRect for each face into a vector. Upon receiving the
|
||
|
|
# BATCH_END timestamp, outputs the vector of NormalizedRect at the BATCH_END
|
||
|
|
# timestamp.
|
||
|
|
node {
|
||
|
|
calculator: "EndLoopNormalizedRectCalculator"
|
||
|
|
input_stream: "ITEM:face_rect_from_detection"
|
||
|
|
input_stream: "BATCH_END:detections_loop_end_timestamp"
|
||
|
|
output_stream: "ITERABLE:face_rects_from_detections"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Performs association between NormalizedRect vector elements from previous
|
||
|
|
# image and rects based on face detections from the current image. This
|
||
|
|
# calculator ensures that the output face_rects vector doesn't contain
|
||
|
|
# overlapping regions based on the specified min_similarity_threshold.
|
||
|
|
node {
|
||
|
|
calculator: "AssociationNormRectCalculator"
|
||
|
|
input_stream: "face_rects_from_detections"
|
||
|
|
input_stream: "gated_prev_face_rects_from_landmarks"
|
||
|
|
output_stream: "face_rects"
|
||
|
|
options: {
|
||
|
|
[mediapipe.AssociationCalculatorOptions.ext] {
|
||
|
|
min_similarity_threshold: 0.5
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
# Calculate size of the image.
|
||
|
|
node {
|
||
|
|
calculator: "ImagePropertiesCalculator"
|
||
|
|
input_stream: "IMAGE:image"
|
||
|
|
output_stream: "SIZE:image_size"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Outputs each element of face_rects at a fake timestamp for the rest of the
|
||
|
|
# graph to process. Clones image and image size packets for each
|
||
|
|
# single_face_rect at the fake timestamp. At the end of the loop, outputs the
|
||
|
|
# BATCH_END timestamp for downstream calculators to inform them that all
|
||
|
|
# elements in the vector have been processed.
|
||
|
|
node {
|
||
|
|
calculator: "BeginLoopNormalizedRectCalculator"
|
||
|
|
input_stream: "ITERABLE:face_rects"
|
||
|
|
input_stream: "CLONE:0:image"
|
||
|
|
input_stream: "CLONE:1:image_size"
|
||
|
|
output_stream: "ITEM:face_rect"
|
||
|
|
output_stream: "CLONE:0:landmarks_loop_image"
|
||
|
|
output_stream: "CLONE:1:landmarks_loop_image_size"
|
||
|
|
output_stream: "BATCH_END:landmarks_loop_end_timestamp"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Detects face landmarks within specified region of interest of the image.
|
||
|
|
node {
|
||
|
|
calculator: "FaceLandmarkCpu"
|
||
|
|
input_stream: "IMAGE:landmarks_loop_image"
|
||
|
|
input_stream: "ROI:face_rect"
|
||
|
|
input_side_packet: "WITH_ATTENTION:with_attention"
|
||
|
|
output_stream: "LANDMARKS:face_landmarks"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Calculates region of interest based on face landmarks, so that can be reused
|
||
|
|
# for subsequent image.
|
||
|
|
node {
|
||
|
|
calculator: "FaceLandmarkLandmarksToRoi"
|
||
|
|
input_stream: "LANDMARKS:face_landmarks"
|
||
|
|
input_stream: "IMAGE_SIZE:landmarks_loop_image_size"
|
||
|
|
output_stream: "ROI:face_rect_from_landmarks"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Collects a set of landmarks for each face into a vector. Upon receiving the
|
||
|
|
# BATCH_END timestamp, outputs the vector of landmarks at the BATCH_END
|
||
|
|
# timestamp.
|
||
|
|
node {
|
||
|
|
calculator: "EndLoopNormalizedLandmarkListVectorCalculator"
|
||
|
|
input_stream: "ITEM:face_landmarks"
|
||
|
|
input_stream: "BATCH_END:landmarks_loop_end_timestamp"
|
||
|
|
output_stream: "ITERABLE:multi_face_landmarks"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Collects a NormalizedRect for each face into a vector. Upon receiving the
|
||
|
|
# BATCH_END timestamp, outputs the vector of NormalizedRect at the BATCH_END
|
||
|
|
# timestamp.
|
||
|
|
node {
|
||
|
|
calculator: "EndLoopNormalizedRectCalculator"
|
||
|
|
input_stream: "ITEM:face_rect_from_landmarks"
|
||
|
|
input_stream: "BATCH_END:landmarks_loop_end_timestamp"
|
||
|
|
output_stream: "ITERABLE:face_rects_from_landmarks"
|
||
|
|
}
|
||
|
|
|
||
|
|
# Caches face rects calculated from landmarks, and upon the arrival of the next
|
||
|
|
# input image, sends out the cached rects with timestamps replaced by that of
|
||
|
|
# the input image, essentially generating a packet that carries the previous
|
||
|
|
# face rects. Note that upon the arrival of the very first input image, a
|
||
|
|
# timestamp bound update occurs to jump start the feedback loop.
|
||
|
|
node {
|
||
|
|
calculator: "PreviousLoopbackCalculator"
|
||
|
|
input_stream: "MAIN:image"
|
||
|
|
input_stream: "LOOP:face_rects_from_landmarks"
|
||
|
|
input_stream_info: {
|
||
|
|
tag_index: "LOOP"
|
||
|
|
back_edge: true
|
||
|
|
}
|
||
|
|
output_stream: "PREV_LOOP:prev_face_rects_from_landmarks"
|
||
|
|
}
|