Skip to content
This repository has been archived by the owner on Aug 10, 2022. It is now read-only.

A project that uses optical flow and machine learning to detect aimhacking in video clips.

License

Notifications You must be signed in to change notification settings

waldo-vision/optical.flow.demo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 

waldo-anticheat

A project that aims to use optical flow and machine learning to visually detect cheating or hacking in video clips from fps games. Check out this video discussing the purpose and vision of WALDO.

Notes

  • This project is still under development.

The What

A new market for cheats that are visually indistinguishable to the human eye have led to a rise in "closet hacking" among streamers and professionals. This form of cheating is extremely hard to detect. In some cases it is impossible to detect, even with today's most advanced anti-cheat software.

We will combat this new kind of cheating by creating our own deep learning program to detect this behavior in video clips.

The How

Because of the advanced technology used, the only reliable way to detect this form of cheating is by observing the cheating behavior directly from the end result- gameplay. Our goal is to analyze the video directly using deep learning to detect if a user is receiving machine assistance.

Phase 1 focuses primarily on humanized aim-assist. Upon completion of phase 1, WALDO's main function will be vindication and clarity to many recent "hackusations."

Skills needed:

  1. Machine learning / neural networks / AI
  2. Visualizations and graphics
  3. Data analysis
  4. General Python
  5. Website design / programming
  6. Game graphics / video analysis
  7. Gamers
  8. Current closet hackers you can help ( ͡° ͜ʖ ͡°)