Have I written custom code (as opposed to using a stock example script provided in MediaPipe)
No
OS Platform and Distribution
Linux ubuntu 20.04
MediaPipe Tasks SDK version
No response
Task name (e.g. Image classification, Gesture recognition etc.)
Detecting pose
Programming Language and version (e.g. C++, Python, Java)
Python
Describe the actual behavior
The code determines the location of the hand relative to the middle of the thigh, but the thigh itself is not in the camera's field of view. How and how accurately are the coordinates calculated?
Describe the expected behaviour
It seems to me that if the hips do not fall into the camera's field of view, the coordinates should count from another center (the middle of the shoulders or nose), depending on what is in the camera's field of view.
Standalone code/steps you may have used to try to get what you need
The program code is standard for example https://github.com/google/mediapipe/issues/4681
Have I written custom code (as opposed to using a stock example script provided in MediaPipe)
No
OS Platform and Distribution
Linux ubuntu 20.04
MediaPipe Tasks SDK version
No response
Task name (e.g. Image classification, Gesture recognition etc.)
Detecting pose
Programming Language and version (e.g. C++, Python, Java)
Python
Describe the actual behavior
The code determines the location of the hand relative to the middle of the thigh, but the thigh itself is not in the camera's field of view. How and how accurately are the coordinates calculated?
Describe the expected behaviour
It seems to me that if the hips do not fall into the camera's field of view, the coordinates should count from another center (the middle of the shoulders or nose), depending on what is in the camera's field of view.
Standalone code/steps you may have used to try to get what you need
Other info / Complete Logs
No response