Hi, I'm working on pose detection and some data analysis. However, if ones is not fully inside the camera, the landmark outside the image will be a mess and ruin my landmark data.
I found this in description, "If the person was not completely inside the image, the model assigns the missing landmarks coordinates outside the frame and gives them low InFrameConfidence values.". Is there anyway we could use this like confidence threshold on mediapipe?
Hi, I'm working on pose detection and some data analysis. However, if ones is not fully inside the camera, the landmark outside the image will be a mess and ruin my landmark data.
I found this in description, "If the person was not completely inside the image, the model assigns the missing landmarks coordinates outside the frame and gives them low InFrameConfidence values.". Is there anyway we could use this like confidence threshold on mediapipe?