Project import generated by Copybara.
GitOrigin-RevId: 33adfdf31f3a5cbf9edc07ee1ea583e95080bdc5
This commit is contained in:
MediaPipe Team
@@ -92,12 +92,12 @@ each project.
|
||||
and copy
|
||||
[the binary graph](https://github.com/google/mediapipe/blob/master/mediapipe/examples/android/src/java/com/google/mediapipe/apps/facedetectiongpu/BUILD#L41)
|
||||
and
|
||||
[the face detection tflite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_front.tflite).
|
||||
[the face detection tflite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_short_range.tflite).
|
||||
|
||||
```bash
|
||||
bazel build -c opt mediapipe/graphs/face_detection:face_detection_mobile_gpu_binary_graph
|
||||
cp bazel-bin/mediapipe/graphs/face_detection/face_detection_mobile_gpu.binarypb /path/to/your/app/src/main/assets/
|
||||
cp mediapipe/modules/face_detection/face_detection_front.tflite /path/to/your/app/src/main/assets/
|
||||
cp mediapipe/modules/face_detection/face_detection_short_range.tflite /path/to/your/app/src/main/assets/
|
||||
```
|
||||
|
||||
|
||||
@@ -117,7 +117,6 @@ each project.
|
||||
implementation 'com.google.flogger:flogger-system-backend:0.3.1'
|
||||
implementation 'com.google.code.findbugs:jsr305:3.0.2'
|
||||
implementation 'com.google.guava:guava:27.0.1-android'
|
||||
implementation 'com.google.guava:guava:27.0.1-android'
|
||||
implementation 'com.google.protobuf:protobuf-java:3.11.4'
|
||||
// CameraX core library
|
||||
def camerax_version = "1.0.0-beta10"
|
||||
@@ -125,7 +124,7 @@ each project.
|
||||
implementation "androidx.camera:camera-camera2:$camerax_version"
|
||||
implementation "androidx.camera:camera-lifecycle:$camerax_version"
|
||||
// AutoValue
|
||||
def auto_value_version = "1.6.4"
|
||||
def auto_value_version = "1.8.1"
|
||||
implementation "com.google.auto.value:auto-value-annotations:$auto_value_version"
|
||||
annotationProcessor "com.google.auto.value:auto-value:$auto_value_version"
|
||||
}
|
||||
|
||||
Binary file not shown.
+14
-38
@@ -55,46 +55,22 @@ See also
|
||||
[MediaPipe Models and Model Cards](https://google.github.io/mediapipe/solutions/models)
|
||||
for ML models released in MediaPipe.
|
||||
|
||||
## MediaPipe in Python
|
||||
|
||||
MediaPipe offers customizable Python solutions as a prebuilt Python package on
|
||||
[PyPI](https://pypi.org/project/mediapipe/), which can be installed simply with
|
||||
`pip install mediapipe`. It also provides tools for users to build their own
|
||||
solutions. Please see
|
||||
[MediaPipe in Python](https://google.github.io/mediapipe/getting_started/python)
|
||||
for more info.
|
||||
|
||||
## MediaPipe on the Web
|
||||
|
||||
MediaPipe on the Web is an effort to run the same ML solutions built for mobile
|
||||
and desktop also in web browsers. The official API is under construction, but
|
||||
the core technology has been proven effective. Please see
|
||||
[MediaPipe on the Web](https://developers.googleblog.com/2020/01/mediapipe-on-web.html)
|
||||
in Google Developers Blog for details.
|
||||
|
||||
You can use the following links to load a demo in the MediaPipe Visualizer, and
|
||||
over there click the "Runner" icon in the top bar like shown below. The demos
|
||||
use your webcam video as input, which is processed all locally in real-time and
|
||||
never leaves your device.
|
||||
|
||||
|
||||
|
||||
* [MediaPipe Face Detection](https://viz.mediapipe.dev/demo/face_detection)
|
||||
* [MediaPipe Iris](https://viz.mediapipe.dev/demo/iris_tracking)
|
||||
* [MediaPipe Iris: Depth-from-Iris](https://viz.mediapipe.dev/demo/iris_depth)
|
||||
* [MediaPipe Hands](https://viz.mediapipe.dev/demo/hand_tracking)
|
||||
* [MediaPipe Hands (palm/hand detection only)](https://viz.mediapipe.dev/demo/hand_detection)
|
||||
* [MediaPipe Pose](https://viz.mediapipe.dev/demo/pose_tracking)
|
||||
* [MediaPipe Hair Segmentation](https://viz.mediapipe.dev/demo/hair_segmentation)
|
||||
|
||||
## Getting started
|
||||
|
||||
Learn how to [install](https://google.github.io/mediapipe/getting_started/install)
|
||||
MediaPipe and
|
||||
[build example applications](https://google.github.io/mediapipe/getting_started/building_examples),
|
||||
and start exploring our ready-to-use
|
||||
[solutions](https://google.github.io/mediapipe/solutions/solutions) that you can
|
||||
further extend and customize.
|
||||
To start using MediaPipe
|
||||
[solutions](https://google.github.io/mediapipe/solutions/solutions) with only a few
|
||||
lines code, see example code and demos in
|
||||
[MediaPipe in Python](https://google.github.io/mediapipe/getting_started/python) and
|
||||
[MediaPipe in JavaScript](https://google.github.io/mediapipe/getting_started/javascript).
|
||||
|
||||
To use MediaPipe in C++, Android and iOS, which allow further customization of
|
||||
the [solutions](https://google.github.io/mediapipe/solutions/solutions) as well as
|
||||
building your own, learn how to
|
||||
[install](https://google.github.io/mediapipe/getting_started/install) MediaPipe and
|
||||
start building example applications in
|
||||
[C++](https://google.github.io/mediapipe/getting_started/cpp),
|
||||
[Android](https://google.github.io/mediapipe/getting_started/android) and
|
||||
[iOS](https://google.github.io/mediapipe/getting_started/ios).
|
||||
|
||||
The source code is hosted in the
|
||||
[MediaPipe Github repository](https://github.com/google/mediapipe), and you can
|
||||
|
||||
@@ -45,6 +45,15 @@ section.
|
||||
|
||||
Naming style and availability may differ slightly across platforms/languages.
|
||||
|
||||
#### model_selection
|
||||
|
||||
An integer index `0` or `1`. Use `0` to select a short-range model that works
|
||||
best for faces within 2 meters from the camera, and `1` for a full-range model
|
||||
best for faces within 5 meters. For the full-range option, a sparse model is
|
||||
used for its improved inference speed. Please refer to the
|
||||
[model cards](./models.md#face_detection) for details. Default to `0` if not
|
||||
specified.
|
||||
|
||||
#### min_detection_confidence
|
||||
|
||||
Minimum confidence value (`[0.0, 1.0]`) from the face detection model for the
|
||||
@@ -72,6 +81,7 @@ install MediaPipe Python package, then learn more in the companion
|
||||
|
||||
Supported configuration options:
|
||||
|
||||
* [model_selection](#model_selection)
|
||||
* [min_detection_confidence](#min_detection_confidence)
|
||||
|
||||
```python
|
||||
@@ -83,7 +93,7 @@ mp_drawing = mp.solutions.drawing_utils
|
||||
# For static images:
|
||||
IMAGE_FILES = []
|
||||
with mp_face_detection.FaceDetection(
|
||||
min_detection_confidence=0.5) as face_detection:
|
||||
model_selection=1, min_detection_confidence=0.5) as face_detection:
|
||||
for idx, file in enumerate(IMAGE_FILES):
|
||||
image = cv2.imread(file)
|
||||
# Convert the BGR image to RGB and process it with MediaPipe Face Detection.
|
||||
@@ -103,7 +113,7 @@ with mp_face_detection.FaceDetection(
|
||||
# For webcam input:
|
||||
cap = cv2.VideoCapture(0)
|
||||
with mp_face_detection.FaceDetection(
|
||||
min_detection_confidence=0.5) as face_detection:
|
||||
model_selection=0, min_detection_confidence=0.5) as face_detection:
|
||||
while cap.isOpened():
|
||||
success, image = cap.read()
|
||||
if not success:
|
||||
@@ -139,6 +149,7 @@ and the following usage example.
|
||||
|
||||
Supported configuration options:
|
||||
|
||||
* [modelSelection](#model_selection)
|
||||
* [minDetectionConfidence](#min_detection_confidence)
|
||||
|
||||
```html
|
||||
@@ -189,6 +200,7 @@ const faceDetection = new FaceDetection({locateFile: (file) => {
|
||||
return `https://cdn.jsdelivr.net/npm/@mediapipe/[email protected]/${file}`;
|
||||
}});
|
||||
faceDetection.setOptions({
|
||||
modelSelection: 0
|
||||
minDetectionConfidence: 0.5
|
||||
});
|
||||
faceDetection.onResults(onResults);
|
||||
@@ -255,10 +267,6 @@ same configuration as the GPU pipeline, runs entirely on CPU.
|
||||
* Target:
|
||||
[`mediapipe/examples/desktop/face_detection:face_detection_gpu`](https://github.com/google/mediapipe/tree/master/mediapipe/examples/desktop/face_detection/BUILD)
|
||||
|
||||
### Web
|
||||
|
||||
Please refer to [these instructions](../index.md#mediapipe-on-the-web).
|
||||
|
||||
### Coral
|
||||
|
||||
Please refer to
|
||||
|
||||
@@ -69,7 +69,7 @@ and renders using a dedicated
|
||||
The
|
||||
[face landmark subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_landmark/face_landmark_front_gpu.pbtxt)
|
||||
internally uses a
|
||||
[face_detection_subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_front_gpu.pbtxt)
|
||||
[face_detection_subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_short_range_gpu.pbtxt)
|
||||
from the
|
||||
[face detection module](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection).
|
||||
|
||||
|
||||
@@ -51,7 +51,14 @@ to visualize its associated subgraphs, please see
|
||||
|
||||
### Web
|
||||
|
||||
Please refer to [these instructions](../index.md#mediapipe-on-the-web).
|
||||
Use [this link](https://viz.mediapipe.dev/demo/hair_segmentation) to load a demo
|
||||
in the MediaPipe Visualizer, and over there click the "Runner" icon in the top
|
||||
bar like shown below. The demos use your webcam video as input, which is
|
||||
processed all locally in real-time and never leaves your device. Please see
|
||||
[MediaPipe on the Web](https://developers.googleblog.com/2020/01/mediapipe-on-web.html)
|
||||
in Google Developers Blog for details.
|
||||
|
||||
|
||||
|
||||
## Resources
|
||||
|
||||
|
||||
@@ -176,6 +176,16 @@ A list of pose landmarks. Each landmark consists of the following:
|
||||
* `visibility`: A value in `[0.0, 1.0]` indicating the likelihood of the
|
||||
landmark being visible (present and not occluded) in the image.
|
||||
|
||||
#### pose_world_landmarks
|
||||
|
||||
Another list of pose landmarks in world coordinates. Each landmark consists of
|
||||
the following:
|
||||
|
||||
* `x`, `y` and `z`: Real-world 3D coordinates in meters with the origin at the
|
||||
center between hips.
|
||||
* `visibility`: Identical to that defined in the corresponding
|
||||
[pose_landmarks](#pose_landmarks).
|
||||
|
||||
#### face_landmarks
|
||||
|
||||
A list of 468 face landmarks. Each landmark consists of `x`, `y` and `z`. `x`
|
||||
@@ -245,6 +255,9 @@ with mp_holistic.Holistic(
|
||||
mp_drawing.draw_landmarks(
|
||||
annotated_image, results.pose_landmarks, mp_holistic.POSE_CONNECTIONS)
|
||||
cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)
|
||||
# Plot pose world landmarks.
|
||||
mp_drawing.plot_landmarks(
|
||||
results.pose_world_landmarks, mp_holistic.POSE_CONNECTIONS)
|
||||
|
||||
# For webcam input:
|
||||
cap = cv2.VideoCapture(0)
|
||||
|
||||
+12
-2
@@ -69,7 +69,7 @@ and renders using a dedicated
|
||||
The
|
||||
[face landmark subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_landmark/face_landmark_front_gpu.pbtxt)
|
||||
internally uses a
|
||||
[face detection subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_front_gpu.pbtxt)
|
||||
[face detection subgraph](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_short_range_gpu.pbtxt)
|
||||
from the
|
||||
[face detection module](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection).
|
||||
|
||||
@@ -193,7 +193,17 @@ on how to build MediaPipe examples.
|
||||
|
||||
### Web
|
||||
|
||||
Please refer to [these instructions](../index.md#mediapipe-on-the-web).
|
||||
You can use the following links to load a demo in the MediaPipe Visualizer, and
|
||||
over there click the "Runner" icon in the top bar like shown below. The demos
|
||||
use your webcam video as input, which is processed all locally in real-time and
|
||||
never leaves your device. Please see
|
||||
[MediaPipe on the Web](https://developers.googleblog.com/2020/01/mediapipe-on-web.html)
|
||||
in Google Developers Blog for details.
|
||||
|
||||
|
||||
|
||||
* [MediaPipe Iris](https://viz.mediapipe.dev/demo/iris_tracking)
|
||||
* [MediaPipe Iris: Depth-from-Iris](https://viz.mediapipe.dev/demo/iris_depth)
|
||||
|
||||
## Resources
|
||||
|
||||
|
||||
@@ -14,17 +14,27 @@ nav_order: 30
|
||||
|
||||
### [Face Detection](https://google.github.io/mediapipe/solutions/face_detection)
|
||||
|
||||
* Face detection model for front-facing/selfie camera:
|
||||
[TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_front.tflite),
|
||||
* Short-range model (best for faces within 2 meters from the camera):
|
||||
[TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_short_range.tflite),
|
||||
[TFLite model quantized for EdgeTPU/Coral](https://github.com/google/mediapipe/tree/master/mediapipe/examples/coral/models/face-detector-quantized_edgetpu.tflite),
|
||||
[Model card](https://mediapipe.page.link/blazeface-mc)
|
||||
* Face detection model for back-facing camera:
|
||||
[TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_back.tflite),
|
||||
* Full-range model (dense, best for faces within 5 meters from the camera):
|
||||
[TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_full_range.tflite),
|
||||
[Model card](https://mediapipe.page.link/blazeface-back-mc)
|
||||
* Face detection model for back-facing camera (sparse):
|
||||
[TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_back_sparse.tflite),
|
||||
* Full-range model (sparse, best for faces within 5 meters from the camera):
|
||||
[TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/modules/face_detection/face_detection_full_range_sparse.tflite),
|
||||
[Model card](https://mediapipe.page.link/blazeface-back-sparse-mc)
|
||||
|
||||
Full-range dense and sparse models have the same quality in terms of
|
||||
[F-score](https://en.wikipedia.org/wiki/F-score) however differ in underlying
|
||||
metrics. The dense model is slightly better in
|
||||
[Recall](https://en.wikipedia.org/wiki/Precision_and_recall) whereas the sparse
|
||||
model outperforms the dense one in
|
||||
[Precision](https://en.wikipedia.org/wiki/Precision_and_recall). Speed-wise
|
||||
sparse model is ~30% faster when executing on CPU via
|
||||
[XNNPACK](https://github.com/google/XNNPACK) whereas on GPU the models
|
||||
demonstrate comparable latencies. Depending on your application, you may prefer
|
||||
one over the other.
|
||||
|
||||
### [Face Mesh](https://google.github.io/mediapipe/solutions/face_mesh)
|
||||
|
||||
|
||||
+27
-1
@@ -194,10 +194,23 @@ A list of pose landmarks. Each landmark consists of the following:
|
||||
* `z`: Represents the landmark depth with the depth at the midpoint of hips
|
||||
being the origin, and the smaller the value the closer the landmark is to
|
||||
the camera. The magnitude of `z` uses roughly the same scale as `x`.
|
||||
|
||||
* `visibility`: A value in `[0.0, 1.0]` indicating the likelihood of the
|
||||
landmark being visible (present and not occluded) in the image.
|
||||
|
||||
#### pose_world_landmarks
|
||||
|
||||
*Fig 5. Example of MediaPipe Pose real-world 3D coordinates.* |
|
||||
:-----------------------------------------------------------: |
|
||||
<video autoplay muted loop preload style="height: auto; width: 480px"><source src="../images/mobile/pose_world_landmarks.mp4" type="video/mp4"></video> |
|
||||
|
||||
Another list of pose landmarks in world coordinates. Each landmark consists of
|
||||
the following:
|
||||
|
||||
* `x`, `y` and `z`: Real-world 3D coordinates in meters with the origin at the
|
||||
center between hips.
|
||||
* `visibility`: Identical to that defined in the corresponding
|
||||
[pose_landmarks](#pose_landmarks).
|
||||
|
||||
### Python Solution API
|
||||
|
||||
Please first follow general [instructions](../getting_started/python.md) to
|
||||
@@ -242,6 +255,9 @@ with mp_pose.Pose(
|
||||
mp_drawing.draw_landmarks(
|
||||
annotated_image, results.pose_landmarks, mp_pose.POSE_CONNECTIONS)
|
||||
cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)
|
||||
# Plot pose world landmarks.
|
||||
mp_drawing.plot_landmarks(
|
||||
results.pose_world_landmarks, mp_pose.POSE_CONNECTIONS)
|
||||
|
||||
# For webcam input:
|
||||
cap = cv2.VideoCapture(0)
|
||||
@@ -294,6 +310,7 @@ Supported configuration options:
|
||||
<meta charset="utf-8">
|
||||
<script src="https://cdn.jsdelivr.net/npm/@mediapipe/camera_utils/camera_utils.js" crossorigin="anonymous"></script>
|
||||
<script src="https://cdn.jsdelivr.net/npm/@mediapipe/control_utils/control_utils.js" crossorigin="anonymous"></script>
|
||||
<script src="https://cdn.jsdelivr.net/npm/@mediapipe/drawing_utils/control_utils_3d.js" crossorigin="anonymous"></script>
|
||||
<script src="https://cdn.jsdelivr.net/npm/@mediapipe/drawing_utils/drawing_utils.js" crossorigin="anonymous"></script>
|
||||
<script src="https://cdn.jsdelivr.net/npm/@mediapipe/pose/pose.js" crossorigin="anonymous"></script>
|
||||
</head>
|
||||
@@ -312,8 +329,15 @@ Supported configuration options:
|
||||
const videoElement = document.getElementsByClassName('input_video')[0];
|
||||
const canvasElement = document.getElementsByClassName('output_canvas')[0];
|
||||
const canvasCtx = canvasElement.getContext('2d');
|
||||
const landmarkContainer = document.getElementsByClassName('landmark-grid-container')[0];
|
||||
const grid = new LandmarkGrid(landmarkContainer);
|
||||
|
||||
function onResults(results) {
|
||||
if (!results.poseLandmarks) {
|
||||
grid.updateLandmarks([]);
|
||||
return;
|
||||
}
|
||||
|
||||
canvasCtx.save();
|
||||
canvasCtx.clearRect(0, 0, canvasElement.width, canvasElement.height);
|
||||
canvasCtx.drawImage(
|
||||
@@ -323,6 +347,8 @@ function onResults(results) {
|
||||
drawLandmarks(canvasCtx, results.poseLandmarks,
|
||||
{color: '#FF0000', lineWidth: 2});
|
||||
canvasCtx.restore();
|
||||
|
||||
grid.updateLandmarks(results.poseWorldLandmarks);
|
||||
}
|
||||
|
||||
const pose = new Pose({locateFile: (file) => {
|
||||
|
||||
Reference in New Issue
Block a user