ntu-rris / google-mediapipe Goto Github PK
View Code? Open in Web Editor NEWGoogle MediaPipe Face + Hands + Body + Object
Google MediaPipe Face + Hands + Body + Object
Hi,
I have seen you have also a module based on stereo camera. I wonder if you'd be interested in idea of calculating camera calibration (basically only relative position) using just a pose from 2 cameras?
The idea is that you capture points in 2d and also have a 3d model from world landmarks. We assume that there is one valid model for example from 1st camera. If we apply SolvePNP with first model to 2d points of first and second camera and negate (I think) the 3d coordinates we can get actual pose of the both cameras. This method most likely will be far in precision from chessboard but if we capture few samples and take only most important joints then it might lead to good enough estimate to use it with mediapipe.
I am just writing about this feature in case you are interested and find it applicable to your solution.
If that is not applicable to your project our you simply doesn't have time then sorry and I shall close this issue :)
Thanks,
Greg
Hello.
I was looking at 05_wrist_rom where I can see hand in 3d being properly positioned in all 3 axis, that is left, right and depth with default parameters.
In new mediapipe there is also position in meters but origin is in hips. Could you consider making demo of body pose but located in space same as you have now hand?
Thank you for great examples.
Hi.
I'd like to ask how this demo is supposed to work. I can see in Open3D window the same thing as in "img 2D".
Thanks
This is happening while import the mediapipe module.
**
import mediapipe
Traceback (most recent call last):
File "<pyshell#1>", line 1, in
import mediapipe
File "C:\Users\new user\AppData\Local\Programs\Python\Python37\lib\site-packages\mediapipe_init_.py", line 16, in
from mediapipe.python import *
File "C:\Users\new user\AppData\Local\Programs\Python\Python37\lib\site-packages\mediapipe\python_init_.py", line 17, in
from mediapipe.python._framework_bindings import resource_util
ImportError: DLL load failed: The specified module could not be found.
Hello, how to use a GPU?
python .\code\00_image.py --mode face_detect
Traceback (most recent call last):
File ".\code\00_image.py", line 16, in <module>
from utils_mediapipe import MediaPipeFaceDetect, MediaPipeFace, MediaPipeHand, MediaPipeBody, MediaPipeHolistic
File "D:\CV2022\mymediapipe\code\utils_mediapipe.py", line 9, in <module>
import mediapipe as mp
File "D:\Anaconda3\envs\mediapipe\lib\site-packages\mediapipe\__init__.py", line 17, in <module>
import mediapipe.python.solutions as solutions
File "D:\Anaconda3\envs\mediapipe\lib\site-packages\mediapipe\python\solutions\__init__.py", line 17, in <module>
import mediapipe.python.solutions.drawing_styles
File "D:\Anaconda3\envs\mediapipe\lib\site-packages\mediapipe\python\solutions\drawing_styles.py", line 20, in <module>
from mediapipe.python.solutions.drawing_utils import DrawingSpec
File "D:\Anaconda3\envs\mediapipe\lib\site-packages\mediapipe\python\solutions\drawing_utils.py", line 25, in <module>
from mediapipe.framework.formats import detection_pb2
File "D:\Anaconda3\envs\mediapipe\lib\site-packages\mediapipe\framework\formats\detection_pb2.py", line 16, in <module>
from mediapipe.framework.formats import location_data_pb2 as mediapipe_dot_framework_dot_formats_dot_location__data__pb2
File "D:\Anaconda3\envs\mediapipe\lib\site-packages\mediapipe\framework\formats\location_data_pb2.py", line 16, in <module>
from mediapipe.framework.formats.annotation import rasterization_pb2 as mediapipe_dot_framework_dot_formats_dot_annotation_dot_rasterization__pb2
File "D:\Anaconda3\envs\mediapipe\lib\site-packages\mediapipe\framework\formats\annotation\rasterization_pb2.py", line 36, in <module>
_descriptor.FieldDescriptor(
File "D:\Anaconda3\envs\mediapipe\lib\site-packages\google\protobuf\descriptor.py", line 560, in __new__
_message.Message._CheckCalledFromGeneratedFile()
TypeError: Descriptors cannot not be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:
1. Downgrade the protobuf package to 3.20.x or lower.
2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).
More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates
Can the calibration module in utils_3d_reconstruct.py be used for calibrating more than two cameras ( i.e., not stereo but MVS)?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.