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
2
votes
1 answer

Aframe based kalidokit 3d body tracking is not working (face tracking works)

I am trying make kalidokit face and body tracking work but no matter what I did I cannot get the body tracking working. Face tracking works perfectly fine. In similar projects such as kalidokit-react face+body tracking works fine, but I guess since…
Caner
  • 1,448
  • 23
  • 38
2
votes
1 answer

MediaPipe Holistic with Flutter for mobile app development

I am looking for ways to use MediaPipe Holistic within the Flutter to develop mobile apps. I know that MediaPipe provide solution API's for: Python Javascript I have also seen that several MediaPipe solutions/models are made available through ML…
Mels Jagt
  • 31
  • 2
2
votes
0 answers

How to fill in mediapipe landmarks using opengl es android

i have a landmarks for lips(i got from MediaPipe), Currently, i created the triangle coordinated and then i tried triangle_strip, triangle_fan to fill the connected lines which i got from mediapipe. is that approach is correct or is any other proper…
Dev007
  • 222
  • 2
  • 9
2
votes
2 answers

Avatar Pupettering with ThreeJS, ReadyPlayerMe, Kalidokit and MediaPipe

I try to animate a ReadyPlayer Me avatar using ThreeJS and Kalidokit (or something else) with MediaPipe Hollisitc Pose. Here is a working JSFiddle : https://jsfiddle.net/nxg5bp2h/1/ It almost works, but the code for Pose Estimation is all…
Jean-Philippe Encausse
  • 1,491
  • 2
  • 22
  • 40
2
votes
0 answers

MacOS Class CaptureDelegate is implemented in both

import mediapipe as mp import time import cv2 class handDetector(): def __init__(self, mode=False, maxHands=2, detectionCon=0.5, trackCon=0.5): self.mode = mode self.maxHands = maxHands self.detectionCon = detectionCon …
Ali Yazici
  • 21
  • 2
2
votes
0 answers

Can you have a selective segmentation mask with MediaPipe's Pose solution?

Is there a way to selectively mask pose landmarks in MediaPipe? MediaPipe allows me to apply a segmentation mask to a pose with the enable_segmentation parameter, but it gives me the entire body. Is it possible to, for example, segment only the…
Ian Hunter
  • 9,466
  • 12
  • 61
  • 77
2
votes
1 answer

MediaPipe Hands gives typeError: hands.Hands is not a constructor

I am trying to build a React widget using Googles MediaPipe Hands library. I get the following error: typeError: hands.Hands is not a constructor Here is my code! const LandmarkExtractionComponent = (): JSX.Element => { useEffect(() => { …
MWB
  • 1,830
  • 1
  • 17
  • 38
2
votes
0 answers

I'm using Mediapipe/ js to detect lips and apply filter on it but by using drawconnectors i'm getting the boundray over lips but i want to fill colour

I'm using Mediapipe js to detect lips and apply a filter on them but by using draw connectors I'm getting the boundary over lips but I want to fill colour within the boundary how can I fill colour within the landmarks detected and not just colour…
Vipul Sharma
  • 21
  • 4
2
votes
1 answer

Coordinates extracted from mediapipe are always same

I am trying to extract coordinates of all features from the mediapipe library using face mesh but for every image that I am testing it's giving the same coordinates. I don't understand what's wrong here. If anyone could help, it would be great! …
Raghav Kavimandan
  • 57
  • 5
2
votes
0 answers

MediaPipe object segmentation mask

I am trying to detect objects in my images, mainly shoes. I am familiar that MediaPipe has the option to detect 3D objects (it is only one mode which can take different models like: 'Shoe', 'Chair', 'Cup', 'Camera') but after running the algorithm,…
begginer
  • 189
  • 2
  • 10
2
votes
5 answers

cv2 not work after install mediapipe library

I want to make handtracker program using python but the tutorial tell me to install mediapipe library, then I installed it. Before that it's okay using cv2 to stream my camera, but after installing mediapipe, the cv2 doesn't work here the message…
015_Aris Mahmudi
  • 21
  • 1
  • 4
2
votes
1 answer

mediapipe real time 3D coordinate printing

i would like to print a real time 3D Plot of the mediapipe 3D Landmarks. I am able to get the holistic as shown below in real time from a Video File: Now i would like to plot the real time 3D Plot like this: The code i used to plot the real time…
Daniel
  • 163
  • 12
2
votes
1 answer

I am getting error while executing my code as mediapipe.python.solutions has no attribute selfie_segmentation

self.mpSelfieSegmentation = mp.solutions.selfie_segmentation AttributeError: module 'mediapipe.python.solutions' has no attribute 'selfie_segmentation' Any one has solution for this?
158_Swaraj Devardekar
  • 21
  • 2
2
votes
1 answer

How to use MediaPipe in C#?

I would like to use the Face Mesh application from Media Pipe in a C# project. As the library is not impemented in C#, I looked for solutions. I found that my face mesh model is saved in tflite but I don't know how to use it. Is there a simple way…
Matthieu Planté
  • 53
  • 7
2
votes
1 answer

Different frame rate calculation methods produce very different results

As part of a hand gesture recognition system based on OpenCV and MediaPipe (from Google) I investigated the frame rate possible. The code in approach 1 was used first (partly from a YouTube video and partly from Mediapipe example code) - this uses a…
rlh
  • 23
  • 4
1 2 3
…
38 39