175 lines
6.0 KiB
Plaintext
175 lines
6.0 KiB
Plaintext
# MediaPipe graph to detect/predict pose landmarks and optionally segmentation
|
|
# within an ROI. (GPU input, and inference is executed on GPU.)
|
|
#
|
|
# It is required that "pose_landmark_lite.tflite" or
|
|
# "pose_landmark_full.tflite" or "pose_landmark_heavy.tflite" is available at
|
|
# "mediapipe/modules/pose_landmark/pose_landmark_lite.tflite" or
|
|
# "mediapipe/modules/pose_landmark/pose_landmark_full.tflite" or
|
|
# "mediapipe/modules/pose_landmark/pose_landmark_heavy.tflite"
|
|
# path respectively during execution, depending on the specification in the
|
|
# MODEL_COMPLEXITY input side packet.
|
|
#
|
|
# EXAMPLE:
|
|
# node {
|
|
# calculator: "PoseLandmarkByRoiGpu"
|
|
# input_side_packet: "MODEL_COMPLEXITY:model_complexity"
|
|
# input_side_packet: "ENABLE_SEGMENTATION:enable_segmentation"
|
|
# input_stream: "IMAGE:image"
|
|
# input_stream: "ROI:roi"
|
|
# output_stream: "LANDMARKS:landmarks"
|
|
# output_stream: "SEGMENTATION_MASK:segmentation_mask"
|
|
# }
|
|
|
|
type: "PoseLandmarkByRoiGpu"
|
|
|
|
# GPU image. (GpuBuffer)
|
|
input_stream: "IMAGE:image"
|
|
# ROI (region of interest) within the given image where a pose is located.
|
|
# (NormalizedRect)
|
|
input_stream: "ROI:roi"
|
|
|
|
# Whether to predict the segmentation mask. If unspecified, functions as set to
|
|
# false. (bool)
|
|
input_side_packet: "ENABLE_SEGMENTATION:enable_segmentation"
|
|
|
|
# Complexity of the pose landmark model: 0, 1 or 2. Landmark accuracy as well as
|
|
# inference latency generally go up with the model complexity. If unspecified,
|
|
# functions as set to 1. (int)
|
|
input_side_packet: "MODEL_COMPLEXITY:model_complexity"
|
|
|
|
# Pose landmarks within the given ROI. (NormalizedLandmarkList)
|
|
# We have 33 landmarks (see pose_landmark_topology.svg), and there are other
|
|
# auxiliary key points.
|
|
# 0 - nose
|
|
# 1 - left eye (inner)
|
|
# 2 - left eye
|
|
# 3 - left eye (outer)
|
|
# 4 - right eye (inner)
|
|
# 5 - right eye
|
|
# 6 - right eye (outer)
|
|
# 7 - left ear
|
|
# 8 - right ear
|
|
# 9 - mouth (left)
|
|
# 10 - mouth (right)
|
|
# 11 - left shoulder
|
|
# 12 - right shoulder
|
|
# 13 - left elbow
|
|
# 14 - right elbow
|
|
# 15 - left wrist
|
|
# 16 - right wrist
|
|
# 17 - left pinky
|
|
# 18 - right pinky
|
|
# 19 - left index
|
|
# 20 - right index
|
|
# 21 - left thumb
|
|
# 22 - right thumb
|
|
# 23 - left hip
|
|
# 24 - right hip
|
|
# 25 - left knee
|
|
# 26 - right knee
|
|
# 27 - left ankle
|
|
# 28 - right ankle
|
|
# 29 - left heel
|
|
# 30 - right heel
|
|
# 31 - left foot index
|
|
# 32 - right foot index
|
|
#
|
|
# NOTE: If a pose is not present within the given ROI, for this particular
|
|
# timestamp there will not be an output packet in the LANDMARKS stream. 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:landmarks"
|
|
# Auxiliary landmarks for deriving the ROI in the subsequent image.
|
|
# (NormalizedLandmarkList)
|
|
output_stream: "AUXILIARY_LANDMARKS:auxiliary_landmarks"
|
|
|
|
# Pose world landmarks within the given ROI. (LandmarkList)
|
|
# World landmarks are real-world 3D coordinates in meters with the origin at the
|
|
# center between hips. WORLD_LANDMARKS shares the same landmark topology as
|
|
# LANDMARKS. However, LANDMARKS provides coordinates (in pixels) of a 3D object
|
|
# projected onto the 2D image surface, while WORLD_LANDMARKS provides
|
|
# coordinates (in meters) of the 3D object itself.
|
|
output_stream: "WORLD_LANDMARKS:world_landmarks"
|
|
|
|
# Segmentation mask on GPU in RGBA with the same mask values in R and A. (Image)
|
|
output_stream: "SEGMENTATION_MASK:segmentation_mask"
|
|
|
|
# Retrieves the image size.
|
|
node {
|
|
calculator: "ImagePropertiesCalculator"
|
|
input_stream: "IMAGE_GPU:image"
|
|
output_stream: "SIZE:image_size"
|
|
}
|
|
|
|
# Crops and transforms the specified ROI in the input image into an image patch
|
|
# represented as a tensor of dimension expected by the corresponding ML model,
|
|
# while maintaining the aspect ratio of the ROI (which can be different from
|
|
# that of the image patch). Therefore, there can be letterboxing around the ROI
|
|
# in the generated tensor representation.
|
|
node: {
|
|
calculator: "ImageToTensorCalculator"
|
|
input_stream: "IMAGE_GPU:image"
|
|
input_stream: "NORM_RECT:roi"
|
|
output_stream: "TENSORS:input_tensors"
|
|
output_stream: "LETTERBOX_PADDING:letterbox_padding"
|
|
output_stream: "MATRIX:transformation_matrix"
|
|
options: {
|
|
[mediapipe.ImageToTensorCalculatorOptions.ext] {
|
|
output_tensor_width: 256
|
|
output_tensor_height: 256
|
|
keep_aspect_ratio: true
|
|
output_tensor_float_range {
|
|
min: 0.0
|
|
max: 1.0
|
|
}
|
|
gpu_origin: TOP_LEFT
|
|
}
|
|
}
|
|
}
|
|
|
|
# Loads the pose landmark TF Lite model.
|
|
node {
|
|
calculator: "PoseLandmarkModelLoader"
|
|
input_side_packet: "MODEL_COMPLEXITY:model_complexity"
|
|
output_side_packet: "MODEL:model"
|
|
}
|
|
|
|
# Runs model inference on GPU.
|
|
node {
|
|
calculator: "InferenceCalculator"
|
|
input_side_packet: "MODEL:model"
|
|
input_stream: "TENSORS:input_tensors"
|
|
output_stream: "TENSORS:output_tensors"
|
|
}
|
|
|
|
# Decodes the tensors into the corresponding landmark and segmentation mask
|
|
# representation.
|
|
node {
|
|
calculator: "TensorsToPoseLandmarksAndSegmentation"
|
|
input_side_packet: "ENABLE_SEGMENTATION:enable_segmentation"
|
|
input_stream: "TENSORS:output_tensors"
|
|
output_stream: "LANDMARKS:roi_landmarks"
|
|
output_stream: "AUXILIARY_LANDMARKS:roi_auxiliary_landmarks"
|
|
output_stream: "WORLD_LANDMARKS:roi_world_landmarks"
|
|
output_stream: "SEGMENTATION_MASK:roi_segmentation_mask"
|
|
}
|
|
|
|
# Projects the landmarks and segmentation mask in the local coordinates of the
|
|
# (potentially letterboxed) ROI back to the global coordinates of the full input
|
|
# image.
|
|
node {
|
|
calculator: "PoseLandmarksAndSegmentationInverseProjection"
|
|
input_stream: "IMAGE_SIZE:image_size"
|
|
input_stream: "NORM_RECT:roi"
|
|
input_stream: "LETTERBOX_PADDING:letterbox_padding"
|
|
input_stream: "MATRIX:transformation_matrix"
|
|
input_stream: "LANDMARKS:roi_landmarks"
|
|
input_stream: "AUXILIARY_LANDMARKS:roi_auxiliary_landmarks"
|
|
input_stream: "WORLD_LANDMARKS:roi_world_landmarks"
|
|
input_stream: "SEGMENTATION_MASK:roi_segmentation_mask"
|
|
output_stream: "LANDMARKS:landmarks"
|
|
output_stream: "AUXILIARY_LANDMARKS:auxiliary_landmarks"
|
|
output_stream: "WORLD_LANDMARKS:world_landmarks"
|
|
output_stream: "SEGMENTATION_MASK:segmentation_mask"
|
|
}
|