All work
03Computer vision / Edge inferenceCompleted

RoboMaster Enemy Detection

A YOLOv8n pipeline trained on competition footage to detect enemy robots and their pressure plates in real time.

Context

Built for UTA's SCAI RoboMaster team, this project turns tournament recordings into a competition-oriented object-detection dataset. The lightweight nano model was selected to keep the pipeline compatible with real-time inference on robot hardware.

Engineering contributions

  • Extracted representative frames from RoboMaster tournament footage
  • Annotated enemy robots and pressure plates as separate detection classes
  • Trained a YOLOv8n object-detection model
  • Prepared the pipeline for expanded footage and edge-case data

System path

01Match footage
02Frame extraction
03Annotation
04YOLO training
05Edge inference
Next system · 04Real-Time Social Platform