Skip to main content

A Body, Hand, Face tracking utility

Project description

Pose_Estimation

This project contains Full Body estimation, Face Tracking and Hand Estimation all using mediapipe library. These projects were done with help of freeCodeCamp.org video.

Contents

Installation

To use this repo use

git clone https://github.com/REZ3LIET/Pose_Estimations.git

or

pip3 install pose-estimation-mp

Body_Estimations


This contains the module body_estimation_module.py which can be used to track the landmarks on a human body. It is limited to tracking a single person at a time and gives 33 unique landmarks on the body.

Usage

To use body_estimation_module.py in your code simply import one of the following ways:

import Body_Tracking
from Body_Tracking import body_tracking_module as btm
from Body_Tracking.body_tracking_module import BodyPoseDetect

Example

To use the body_estimation_module.py go to Body_Tracking directory in terminal

  • For default execution:
python3 bodytracking_module.py
  • To execute with an image
python3 bodytracking_module.py -p Data/Images/handstand.jpg
  • To execute on a video
python3 bodytracking_module.py -v -p Data/Videos/dance.mp4

Hand_Estimation


This contains the module hand_tracking_module.py which can be used to track the landmarks on hand(s) and also display them. It can track maximum of 2 handas at an instant.

Usage

To use hand_tracking_module.py in your code simply import one of the following ways:

import Hand_Tacking
from Hand_Tacking import hand_tracking_module as htm
from Hand_Tacking.hand_tracking_module import HandPoseDetect

Example

To use the hand_tracking_module.py go to Hand_Tacking directory in terminal

  • For default execution:
python3 hand_tracking_module.py
  • To execute with an image
python3 hand_tracking_module.py -p Data/Images/covered_face.jpg
  • To execute on a video
python3 hand_tracking_module.py -v -p Data/Videos/piano_playing.mp4

Face_Tracking


This contains the module face_tracking_module.py which can be used to detect and track the face by drawing a bounding box around it. To detect faces at farther range set model type to 1.

Usage

To use face_tracking_module.py in your code simply import one of the following ways:

import Face_Tracking
from Face_Tracking import face_tracking_module as ftm
from Face_Tracking.face_tracking_module import FaceTrack

Example

To use the face_tracking_module.py go to Face_Tracking directory in terminal

  • For default execution:
python3 face_tracking_module.py
  • To execute with an image
python3 face_tracking_module.py -p Data/Images/human_3.jpg
  • To execute on a video
python3 face_tracking_module.py -v -p Data/Videos/humans_1.mp4

Face_Mesh_Detection


This contains the module face_mesh_detection_module.py which can be used to detect and track the face by drawing a mesh on it around it. Max 2 faces can be detected.

Usage

To use face_mesh_detection_module.py in your code simply import one of the following ways:

import Face_Tracking
from Face_Tracking import face_mesh_detection_module as ftm
from Face_Tracking.face_mesh_detection_module import FaceDetect

Example

To use the face_mesh_detection_module.py go to Face_Tracking directory in terminal

  • For default execution:
python3 face_mesh_detection_module.py
  • To execute with an image
python3 face_mesh_detection_module.py -p Data/Images/human_2.jpg
  • To execute on a video
python3 face_mesh_detection_module.py -v -p Data/Videos/humans_2.mp4

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pose_estimation_mp-0.1.5-py3-none-any.whl (10.0 kB view details)

Uploaded Python 3

File details

Details for the file pose_estimation_mp-0.1.5-py3-none-any.whl.

File metadata

File hashes

Hashes for pose_estimation_mp-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 b20e2e617964b0d3006cdd2e9c67651e9df129a85b2aac209c2cf640a4ee153e
MD5 58c1c998b0d1215c71ffcfd907bd41a5
BLAKE2b-256 b307fccc8200854c756d8e98f0f209f7e7fc9fc45dbb5c2088e81bf0e4978f68

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page