Services Projects Blog How I Work Contact
Back to Projects
Case Study Apr 2025 — Ongoing

1 Minute of Football,
Analyzed in 7 Seconds

Transforming a fragile rule-based sports analysis system into a production ML pipeline that processes 1 minute of 720p drill footage in 7 seconds, with zero monthly training costs.

Analysis Speed
1 min → 7s
720p video on L4 GPU
Training Cost
$2,500 → $0
A100s to free-tier L4s
Licensing
100% Apache 2.0
Zero commercial risk
Accuracy
Near-Perfect
From barely usable
// The Client

AIM — AI-Powered Football Coach

AIM is an AI football coaching platform. The product analyzes football drill footage using computer vision to provide tactical insights, player performance metrics, and coaching feedback in real time.

When I joined, AIM had a rule-based system that was brittle, inaccurate, and expensive to run. The task was clear: replace it with production-grade ML, and make it fast and affordable enough to scale.

// The Problem

What I Inherited

Fragile Rule-Based System

Hand-coded rules broke on edge cases. Outputs were barely usable, requiring constant manual correction. No path to improvement without fundamental redesign.

$2,500/mo Training Costs

Models trained on A100 instances at premium cloud rates. Unsustainable for a startup. Every retraining cycle burned through budget.

Licensing Risk

Models with restrictive licenses (AGPL, non-commercial clauses) created legal exposure for a commercial product.

10 FPS Inference

Processing at 10 FPS on 720p video — far too slow for real-time coaching. Analyzing a full drill took far too long for a responsive tool.

// The Approach

What I Built

I replaced the entire system from scratch. Custom models, optimized inference, efficient training pipelines, and a licensing audit of every dependency.

01

Custom Object Detection

Replaced the rule-based player/ball detection with RF-DETR (Real-Time Detection Transformer). Custom-trained on football-specific data with aggressive augmentation. RF-DETR's architecture gave us better accuracy than YOLO alternatives while maintaining speed.

RF-DETR Custom Training Data Augmentation
02

Pose Estimation Pipeline

Integrated RTMPose for real-time player pose estimation. This feeds into movement analysis, fatigue detection, and tactical formation tracking. Optimized the model for the specific poses and camera angles common in football footage.

RTMPose Pose Estimation Movement Analysis
03

TensorRT Optimization

Converted all models to TensorRT engines with FP16 precision. Custom CUDA memory management to eliminate allocation overhead. Batch processing with optimized memory layouts. Result: 1 minute of 720p video analyzed in 7 seconds on a single L4 GPU.

TensorRT CUDA FP16 Memory Optimization
04

Training Cost Elimination

Designed efficient training pipelines that run on free-tier L4 GPUs instead of expensive A100 instances. Smart data loading, gradient accumulation, and mixed-precision training. Monthly training cost: $0.

Mixed Precision L4 GPU Efficient Pipelines
05

Custom Neural Networks for Drill Analysis

Built custom neural networks for analyzing individual player drill performance. Movement pattern recognition, technique scoring, and spatial analysis of player positioning throughout each drill.

Custom NNs Drill Analysis Movement Patterns
06

Apache 2.0 Migration

Audited every model and dependency for licensing. Replaced all restrictively-licensed components with Apache 2.0 alternatives. Zero licensing risk for commercial deployment.

License Audit Apache 2.0 Compliance
// Tech Stack

What Powers It

Models

  • RF-DETR (Object Detection)
  • RTMPose (Pose Estimation)
  • Custom NNs (Drill Analysis)
  • TabPFN (Tabular Predictions)

Inference

  • TensorRT (FP16)
  • CUDA (Memory Management)
  • ONNX Runtime
  • Triton (Inference Server)

Infrastructure

  • GCP (L4 GPUs)
  • Docker
  • Python / FastAPI
  • Weights & Biases

Data

  • Custom Annotation Suite
  • Roboflow
  • Video Processing Pipeline
  • Synthetic Augmentation
// The Results

What Changed

6 min per minute of video
7 seconds
Per minute of 720p drill footage
$2,500/mo
$0/mo
Training costs via efficient pipelines
Brittle Rules
Custom ML
Near-perfect accuracy with robust models
License Risk
Apache 2.0
Full commercial compliance
// My Role

Beyond the Code

I didn't just write ML code. I drove key strategic decisions that shaped the product's direction:

  • Model selection — chose RF-DETR over YOLO based on accuracy/speed tradeoffs specific to our use case
  • Architecture decisions — designed the full pipeline from data annotation to inference
  • Cost strategy — proved we could train on L4s instead of A100s, saving thousands per month
  • Licensing audit — identified and replaced every restrictively-licensed dependency
  • AI strategy — scoped new features and advised on what's feasible vs. hype
  • Code review — reviewed other engineers' ML contributions for quality and correctness
  • Stakeholder communication — translated technical progress into business language for non-technical stakeholders
In November 2025 I was promoted to AI Lead, overseeing model selection, feature scoping, and technical review across the project.

Need something like this?

I build production ML systems that are fast, affordable, and legally clean. If you have a computer vision or edge deployment challenge, let's talk.