IMITECIO
Pose replication using Posenet
Install / Use
/learn @SAtacker/IMITECIOREADME
IMITECIO
<p align="center"> <img src="docs/images/ImitecioLogoFree.png" alt="logo" width="250" height="250"> </p> <!-- TABLE OF CONTENTS -->Table of Contents
- About the Project
- Getting Started
- Usage
- Results and Demo
- Future Work
- Troubleshooting
- Contributors
- Acknowledgements and Resources
- License
About The Project
Pose Estimation (& Replication) Based Game
- Pose Estimation has been for a while in the deep learning industry. Considering the various applications of it, we aimed at creating a simple game at first. Some few things we intend to do further are mentioned at the end. Refer this documentation
Tech Stack
- The Posenet model trained by Google is used.
- For the Posenet Js to Python port this repo is used.
The rest is openCV for webcam input, Unity for NotEndlessRunner game and keyboard for keypresses. Although pynput is used , we prefer pywin32 for windows.
File Structure
IMITECIO
├───docs ## Documents and Images
│ └───images
├───NotEndlessRunner ## Game Files
│ |
│ ├───Assets
│ │ ├───Animation
│ │ ├───Materials
│ │ ├───Prefab
│ │ ├───Raw Mocap Data
│ │ ├───Scenes
│ │ ├───Scripts
│ │ ├───Sprites
│ │ └───TextMesh Pro
│ │ ├───Documentation
│ │ ├───Fonts
│ │ ├───Resources
│ │ └───Sprites
│ ├───Library
| |
│ ├───Logs
│ ├───obj
│ ├───Packages
│ └───ProjectSettings
├───OsX.app ## Game for MacOs
│ └───Contents
│ ├───Frameworks
│ ├───MacOS
│ ├───MonoBleedingEdge
│ └───Resources
└───posenet ## Main Python Files
├───MonoBleedingEdge
│ ├───EmbedRuntime
│
├───NotEndlessRunner_Data
│ ├───Managed
│ └───Resources
├───posenet
│ └───converter
└───models ## You may need to download the models initially.
└───checkpoints
<!-- GETTING STARTED -->
Getting Started
Prerequisites & Installation
- Tested on Windows
git clone https://github.com/SAtacker/IMITECIO.git
cd IMITECIO
In your Virtual Environment
pip install -r "requirements.txt"
python posenet\webcam_demo.py
<!-- RESULTS AND DEMO -->
Results and Demo

- On Manipulating the code according to your requirements, you could use it to control most of the games.


- We have tried playing with SpaceInvaders
Future Work
- [x] Posenet tflite to Python - Single Person detection
- [x] Posenet Based Game
- [ ] Pose Estimation in 3d
- [ ] Socket Code instead of Keyboard Presses
- [ ] C++ Port for faster recognition
Troubleshooting
- You may need to install tensorflow 1.15.0 or tensorflow 1.13 on your own.
- There could be an issue only in the tensorflow installation.
- However one small thing to remember is that multithreading does not guarentee the Game to run first . Meaning that the OpenCV window might appear later and gamethread before. We dont't have a fix for this. Rather press Alt + Tab to overcome this thing.
Contributors
<!-- ACKNOWLEDGEMENTS AND REFERENCES -->Acknowledgements and Resources
- SRA VJTI Eklavya 2020
- Refered this for PoseNet Python
- PoseNet
- OpenPose
- Pytorch 3D pose
- Paper
- Paper
- Paper
- Paper
- Space Invaders
License
Related Skills
node-connect
344.4kDiagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps
claude-opus-4-5-migration
99.2kMigrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5
frontend-design
99.2kCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
model-usage
344.4kUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

