Stack Overflow
Stack Overflow

Questions tagged [mediapipe]

When you are facing any implementation issue for mediapipe in your android, iOS or desktop application, When you want any clarification on concept , methods on mediapipe etc ask question with this tag.

MediaPipe is a framework for building multimodal (eg. video, audio, any time series data), cross platform (i.e Android, iOS, web, edge devices) applied ML pipelines. With MediaPipe, a perception pipeline can be built as a graph of modular components, including, for instance, inference models (e.g., TensorFlow, TFLite) and media processing functions.

585 questions
1
vote
2 answers

Mediapipe in Mac M1 pro machine with ARM, facing issue with AUTORELEASEPOOL while bazel build for hello_world

I am using the latest Mac M1 pro (ARM) machine and was trying to install mediapipe as per this tutorial - https://google.github.io/mediapipe/getting_started/install.html#installing-on-macos. I was consistently getting the following error during this…
hemant kshirsagar
  • 59
  • 4
1
vote
0 answers

Hand Tracking program on Mac (Python) Is outputting very low FPS

I have been following some tutorials online on how to make a hand tracking program which can control the volume of my PC via OpenCV. I am on a macbook pro with the M1 chip, using Python 3.8.2, and MacOS Big Sur 11.6. Whenever I run my program, I get…
Christian Lillelund Nissen
  • 11
  • 1
1
vote
2 answers

Mediapipe hands python result does not have multi_hand_world_landmarks

I try to use MediaPipe in Python. It works fine, but the result of hands.process() has multi_hand_world_landmarks, and does not have multi_hand_world_landmarks and I get AttributeError: type object 'SolutionOutputs' has no attribute…
Vladimir Ilyin
  • 99
  • 1
  • 7
1
vote
6 answers

Getting errors with opencv and mediapipe for making Hand Tracking Module in Python 3.7.9

I am getting the following error whenever I try to run my code, I am following a tutorial for hand tracking, I followed the steps correctly but I still to have some sort of error. Link to Video:…
FunkySplash48
  • 11
  • 1
  • 3
1
vote
1 answer

calculator node for pose based action recognition

I want to add a action_reconition calculator node to the pose_landmark detector (pose_landmark_gpu.pbtxt). Does anyone know if there is already a calculator implementation suited for that purpose? i.e. Input: pose landmarks Inference via tflite…
mcExchange
  • 6,154
  • 12
  • 57
  • 103
1
vote
1 answer

Full Memory Usage at python code, with mediapipe library

I got a big problem at python code, my code is work correct but my laptop's RAM cant erase unused data, I used 'gc' library but it doesn't any help, this problem went appear that I change it to class mode. my code: import cv2 as cv import mediapipe…
Wreza Shafaghi
  • 78
  • 1
  • 9
1
vote
1 answer

Mediapipe process() first 'self' argument

I am trying to use mediapipe to track hands. I am using Python 3.7.9 on Windows 10, my code is below: import cv2 import mediapipe as mp mp_drawing = mp.solutions.drawing_utils mp_hands = mp.solutions.hands cap = cv2.VideoCapture(0) while (True): …
Tom379
  • 11
  • 2
1
vote
3 answers

FileNotFoundError: The path does not exist , while using mediapipe for hand detection

I am trying to accomplish hand detection on webcam feed using mediapipe, but when I run the code I get the following error: **File "D:\HandTracking\handtracking.py", line 9, in hands = mpHands.Hands()** **File…
athanasios kwn
  • 23
  • 1
  • 6
1
vote
0 answers

Locate intersection between the floor and user's feet

I am using MediaPipe Pose to track a person's jump height by calculating the person's time in air. The jump starts when the user's foot index leaves the floor (photo included to show foot index #31 and #32). To measure the time in air I need to to…
Ahmad Khateeb
  • 73
  • 9
1
vote
0 answers

How to create a path drawing algorithm to display specific landmarks of a face mesh in Landmark Detection with Tensorflow.JS and React?

I have currently implemented a version of this tutorial: Real Time AI Face Landmark Detection in 20 Minutes with Tensorflow.JS and React It demonstrates how to implement the Tensorflow.JS facemesh model, and how to display the mesh using a drawPath…
jibreal
  • 81
  • 9
1
vote
0 answers

Importing Tensorflow Prevents Proper Running of other Library

I've recently been trying to use the MediaPipe hand landmark detection library, and it works just fine until I try to import Tensorflow. No matter what code/program I try to run, if I import Tensorflow in any capacity, either the whole module, or a…
Sam Skinner
  • 376
  • 3
  • 12
1
vote
2 answers

can't find findposition :AttributeError: 'HandDetector' object has no attribute 'findPosition'

version('cvzone')=1.5.0 the code is below: while True: success, img = cap.read() img= detector.findHands(img) lmlist,_=detector.findPosition(img) cv2.imshow("Image", img) if cv2.waitKey(1) & 0xFF == ord('q'): …
ysfjoe
  • 51
  • 2
  • 2
  • 4
1
vote
0 answers

How can I use Mediapipe handrecognition (using C++) with video feed from other than webcam

Mediapipe handrecognition example uses webcam to feed itself. Also outputs to screen. I need to feed input stream and get output stream programmaticaly. I cannot find any c++ examples for it. There are python, javascript and android API's. But c++…
DirenD
  • 11
  • 1
1
vote
1 answer

Head Pose Estimation Using Facial Landmarks

I want to implement a vector starting from my nose and pointing in the same direction that I'm looking. The problem is the few examples I have found without dlib using facial landmarks are all broken. I don't want to use dlib because it will not…
Carlos Cuartas
  • 57
  • 6
1
vote
0 answers

mediapipe KNIFT template matching example: using own pics doesn not work properly - how does the example actually work?

i followed the example steps to create an own android app KNIFT template matching example like the 3 dollar bill example on the mediapipe website...did anyone of you build this and know how this really works? I cant get a clear documentation. My…
Fab
  • 13
  • 4
1 2 3
…
38 39