Skip to content

MteaHubHug/Human_Pose_Detection_InRealTime_PoseNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Human pose detection in real time with : TensorFlow, Keras, PoseNet

We can estimate human pose with PoseNet model. Algorithm takes an image input and calculate 17 points which are representing eyes, nose, ears, knees, elbows, shoulders and etc. Also, it returns probability of how sure model is in the a whole-pose-estimation. Model is using deep neural network for estimation. All about the PoseNet model and my project is written in .pdf document. Upload Jupyter notebook in Google Collab to find about pose matching. Open the link below to play a game with pose detection (Make a JumpingJack pose to make ball jump and avoid obsticles) or to try a "teddy bear" face filter.

https://editor.p5js.org/matealukic/collections/-ztHSoGuc