← All systems
P–07 / 07

Case study / Computer vision game

Hand Gesture Puzzle Game

A webcam puzzle controlled through real-time hand tracking, pinch gestures, moving targets, and progressive levels.

CategoryComputer vision gameRoleTeam developerContextAcademic team projectStackPython · OpenCV · MediaPipeLicenseMITSourceGitHub ↗

Vision input laboratory

The controller
is your hand.

A camera frame becomes landmarks, a pinch, and finally a puzzle action.

CAM 01 / LIVEMEDIAPIPE HANDSLEVEL 01
Stage 01 / 05Webcam frame

OpenCV captures the live camera frame.

Overview

What the system is

A webcam-based puzzle game controlled with real-time hand gestures across five levels.

Capabilities

What it does

  • 01Real-time trackingMediaPipe Hands reads webcam landmarks frame by frame.
  • 02Pinch interactionThumb-index distance drives grabbing and dropping.
  • 03Progressive levelsTargets become smaller and move faster across five levels.

Engineering

Decisions on record

Vision
OpenCV capture with MediaPipe Hands.
Structure
Responsibilities are split across game, vision, renderer, and configuration modules.

Credits: Srun Sochettra, Tep Makara & Sar Chanrithy