cassdlcm/mediapipe
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge 2a8d65707f into 39309bedba

Browse Source
This commit is contained in:
Justwant 2020-12-16 16:44:29 +08:00 committed by GitHub
commit b1c48da2a5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/solutions/hands.md
View File

@ -91,7 +91,7 @@ To detect initial hand locations, we designed a
mobile real-time uses in a manner similar to the face detection model in mobile real-time uses in a manner similar to the face detection model in
[MediaPipe Face Mesh](./face_mesh.md). Detecting hands is a decidedly complex [MediaPipe Face Mesh](./face_mesh.md). Detecting hands is a decidedly complex
task: our task: our
[model](https://github.com/google/mediapipe/tree/master/mediapipe/models/palm_detection.tflite) has [model](https://github.com/google/mediapipe/blob/master/mediapipe/modules/palm_detection/palm_detection.tflite) has
to work across a variety of hand sizes with a large scale span (~20x) relative to work across a variety of hand sizes with a large scale span (~20x) relative
to the image frame and be able to detect occluded and self-occluded hands. to the image frame and be able to detect occluded and self-occluded hands.
Whereas faces have high contrast patterns, e.g., in the eye and mouth region, Whereas faces have high contrast patterns, e.g., in the eye and mouth region,
@ -119,7 +119,7 @@ just 86.22%.
### Hand Landmark Model ### Hand Landmark Model
After the palm detection over the whole image our subsequent hand landmark After the palm detection over the whole image our subsequent hand landmark
[model](https://github.com/google/mediapipe/tree/master/mediapipe/models/hand_landmark.tflite) [model](https://github.com/google/mediapipe/blob/master/mediapipe/modules/hand_landmark/hand_landmark.tflite)
performs precise keypoint localization of 21 3D hand-knuckle coordinates inside performs precise keypoint localization of 21 3D hand-knuckle coordinates inside
the detected hand regions via regression, that is direct coordinate prediction. the detected hand regions via regression, that is direct coordinate prediction.
The model learns a consistent internal hand pose representation and is robust The model learns a consistent internal hand pose representation and is robust