Back to Maps

Methodology

How the spawn prediction system works

Approach

This system uses behavioral observation—extracting game state from broadcast footage rather than memory reading or code extraction. Everything is derived from what's visible on screen during CDL matches.

The pipeline processes competitive Call of Duty VODs through computer vision to reconstruct game state, then applies machine learning to predict spawn locations from that state.

Data

Training samples109,016 spawn events
Source footage60 competitive VODs
Maps covered9 CDL rotation maps
Events trackedDeaths, spawns, positions, objectives

All data was collected from publicly available tournament broadcasts and creator content under fair use for research purposes.

Technical Stack

The system combines several ML/CV techniques:

  • Object detection and tracking to follow player positions across frames
  • Event detection to identify deaths and spawns from visual state changes
  • Temporal linking to associate each death with its corresponding spawn
  • Feature engineering including spatial, temporal, and objective-relative features
  • Gradient boosted trees for final prediction

The model predicts to 76 discrete spawn points extracted via unsupervised clustering of observed spawn locations.

What's Not Here

This page presents findings, not a tutorial. Key implementation details—minimap extraction regions, clustering parameters, temporal window sizes, feature definitions—are omitted intentionally.

The novel contribution is the findings, not the pipeline. If you want to replicate this, you'll need to solve the same problems we did.

Limitations

Pro play bias
CDL teams play spawn-optimized strategies. Patterns may differ in ranked.
Hardpoint only
Other modes (Control, Search) have different spawn logic.
No live integration
This is analysis, not a real-time tool.
Rotation inference
Active hardpoint is approximated, not detected directly.