mediapipe/mediapipe/graphs/hand_tracking/multi_hand_tracking_desktop.pbtxt
MediaPipe Team 48bcbb115f Project import generated by Copybara.
GitOrigin-RevId: 50714fe28298d7b707eff7304547d89d6ec34a54
2019-11-21 13:20:47 -08:00

128 lines
4.5 KiB
Plaintext

# MediaPipe graph that performs multi-hand tracking on desktop with TensorFlow
# Lite on CPU.
# Used in the example in
# mediapipie/examples/desktop/hand_tracking:multi_hand_tracking_tflite.
# max_queue_size limits the number of packets enqueued on any input stream
# by throttling inputs to the graph. This makes the graph only process one
# frame per time.
max_queue_size: 1
# Decodes an input video file into images and a video header.
node {
calculator: "OpenCvVideoDecoderCalculator"
input_side_packet: "INPUT_FILE_PATH:input_video_path"
output_stream: "VIDEO:input_video"
output_stream: "VIDEO_PRESTREAM:input_video_header"
}
# Determines if an input vector of NormalizedRect has a size greater than or
# equal to the provided min_size.
node {
calculator: "NormalizedRectVectorHasMinSizeCalculator"
input_stream: "ITERABLE:prev_multi_hand_rects_from_landmarks"
output_stream: "prev_has_enough_hands"
node_options: {
[type.googleapis.com/mediapipe.CollectionHasMinSizeCalculatorOptions] {
# This value can be changed to support tracking arbitrary number of hands.
# Please also remember to modify max_vec_size in
# ClipVectorSizeCalculatorOptions in
# mediapipe/graphs/hand_tracking/subgraphs/multi_hand_detection_cpu.pbtxt
min_size: 2
}
}
}
# Drops the incoming image if the previous frame had at least N hands.
# Otherwise, passes the incoming image through to trigger a new round of hand
# detection in MultiHandDetectionSubgraph.
node {
calculator: "GateCalculator"
input_stream: "input_video"
input_stream: "DISALLOW:prev_has_enough_hands"
output_stream: "multi_hand_detection_input_video"
node_options: {
[type.googleapis.com/mediapipe.GateCalculatorOptions] {
empty_packets_as_allow: true
}
}
}
# Subgraph that detections hands (see multi_hand_detection_cpu.pbtxt).
node {
calculator: "MultiHandDetectionSubgraph"
input_stream: "multi_hand_detection_input_video"
output_stream: "DETECTIONS:multi_palm_detections"
output_stream: "NORM_RECTS:multi_palm_rects"
}
# Subgraph that localizes hand landmarks for multiple hands (see
# multi_hand_landmark.pbtxt).
node {
calculator: "MultiHandLandmarkSubgraph"
input_stream: "IMAGE:input_video"
input_stream: "NORM_RECTS:multi_hand_rects"
output_stream: "LANDMARKS:multi_hand_landmarks"
output_stream: "NORM_RECTS:multi_hand_rects_from_landmarks"
}
# Caches a hand rectangle fed back from MultiHandLandmarkSubgraph, and upon the
# arrival of the next input image sends out the cached rectangle with the
# timestamp replaced by that of the input image, essentially generating a packet
# that carries the previous hand rectangle. Note that upon the arrival of the
# very first input image, an empty packet is sent out to jump start the
# feedback loop.
node {
calculator: "PreviousLoopbackCalculator"
input_stream: "MAIN:input_video"
input_stream: "LOOP:multi_hand_rects_from_landmarks"
input_stream_info: {
tag_index: "LOOP"
back_edge: true
}
output_stream: "PREV_LOOP:prev_multi_hand_rects_from_landmarks"
}
# Performs association between NormalizedRect vector elements from previous
# frame and those from the current frame if MultiHandDetectionSubgraph runs.
# This calculator ensures that the output multi_hand_rects vector doesn't
# contain overlapping regions based on the specified min_similarity_threshold.
node {
calculator: "AssociationNormRectCalculator"
input_stream: "prev_multi_hand_rects_from_landmarks"
input_stream: "multi_palm_rects"
output_stream: "multi_hand_rects"
node_options: {
[type.googleapis.com/mediapipe.AssociationCalculatorOptions] {
min_similarity_threshold: 0.5
}
}
}
# Subgraph that renders annotations and overlays them on top of the input
# images (see multi_hand_renderer_cpu.pbtxt).
node {
calculator: "MultiHandRendererSubgraph"
input_stream: "IMAGE:input_video"
input_stream: "DETECTIONS:multi_palm_detections"
input_stream: "LANDMARKS:multi_hand_landmarks"
input_stream: "NORM_RECTS:0:multi_palm_rects"
input_stream: "NORM_RECTS:1:multi_hand_rects"
output_stream: "IMAGE:output_video"
}
# Encodes the annotated images into a video file, adopting properties specified
# in the input video header, e.g., video framerate.
node {
calculator: "OpenCvVideoEncoderCalculator"
input_stream: "VIDEO:output_video"
input_stream: "VIDEO_PRESTREAM:input_video_header"
input_side_packet: "OUTPUT_FILE_PATH:output_video_path"
node_options: {
[type.googleapis.com/mediapipe.OpenCvVideoEncoderCalculatorOptions]: {
codec: "avc1"
video_format: "mp4"
}
}
}