← All projects

COMPUTER VISION / GAMING

Dice Vision System.

A computer vision pipeline that detects, tracks, and reads dice rolls in real time, sending verified results straight to a Unity game server.

SECTOR

Gaming

LOCATION

Western Europe

FOCUS

Computer Vision

DELIVERY

Founder’s freelance project

Concept illustration of ivory dice with blue computer vision tracking boxes
Conceptual project illustration. Client interface and data are not shown.

01 / THE CHALLENGE

The problem worth solving.

Real-world dice rolls needed to be read fairly and verified before affecting the game.

What the system needed to do

  • Detect and classify each roll within 3 seconds
  • Hold high accuracy with a minimal training set
  • Keep communication with the Unity server reliable under load

The real-world constraints

  • Only ~101 training images available
  • No generative AI permitted in the decision path
  • Real-time latency budget left little room for error

02 / THE SOLUTION

How it came together.

We built a modular, deterministic CV pipeline and used AI only for non-critical augmentation. Movement detection triggers a YOLO pass, which feeds a tracking layer and a classification stage, with verified results posted to Unity over REST.

Detect movement in the camera feed and start a new roll event.

Explore the architecture. This is an explanatory diagram, not a live production system.

03 / THE OUTCOME

What the work delivered.

Results reported by the project owner. Outcomes vary by workflow.

  • Verified dice recognition in under 3 seconds
  • Stability checks before reporting each roll to Unity
  • No generative AI in the critical decision path

YOUR NEXT CHAPTER

Something great
starts with a conversation.

Bring one repetitive process. We’ll discuss the time it takes, what could be automated, and the next step that fits your business.

30 minutes. One workflow. No obligation.