AI Sports Livestream Director MVP
Budget: €3,000 – €5,000 EUR
We are building an AI-powered livestream production platform that can fully automate the broadcasting of sports competitions, starting with dog agility. The goal is to eliminate the need for camera operators and directors, while still delivering a professional, TV-like livestream using one or multiple cameras.
This is not a theoretical idea – similar systems exist (Pixellot, PlaySight), but none are specialized for agility sports nor integrated with timing systems and live graphics. Our project focuses on rule- based AI direction + computer vision, not generative AI.
MVP Scope
Video & Livestream: - Capture video from 1–2 cameras (USB / IP / phone stream) - Output live RTMP
stream (YouTube / test server) - Automatically switch cameras based on AI decisions
AI Director Logic: - Detect dog + handler using computer vision - Track subjects across frames - Calculate Frame Quality Score (FQS) per camera - Rule-based camera switching (thresholds, cooldowns, fallback camera) - Avoid excessive switching (cooldowns, obstacle locks)
Graphics Overlay: - Show overlays: Category, Handler Name, Dog Name, Country, Time, Faults/Refusals - Competitor data loaded from Excel/CSV - Timing data can be mocked for MVP
Highlights: - Automatically record each run - Generate short highlight clip after run - Play highlight before next competitor
Tech Stack: - Python, OpenCV, YOLOv8 (or similar), FFmpeg / RTMP, Docker (optional)
Deliverables: - Working MVP prototype - Source code (modular, documented) - Demo video or test
livestream - Basic setup instructions
Why This Project is Interesting: - Real-world AI application - Clear commercial potential - No vague AI promises - Opportunity to shape a real product from the start
REQUIREMENTS:
Tech stack (preferred, flexible)
- Python
- OpenCV
- YOLOv8 (or similar)
- FFmpeg / RTMP
- Optional: Docker
- Frontend UI can be minimal or skipped for MVP
Deliverables
- Working MVP prototype
- Source code (modular, documented)
- Demo video or test livestream
- Basic setup instructions
Ideal freelancer profile
- Experience with computer vision
- Experience with video streaming pipelines
- Comfortable with real-time systems
- Able to work independently with clear specs
Bonus:
- Sports video experience
- OBS / broadcast workflows
- Multi-camera systems
This is not a theoretical idea – similar systems exist (Pixellot, PlaySight), but none are specialized for agility sports nor integrated with timing systems and live graphics. Our project focuses on rule- based AI direction + computer vision, not generative AI.
MVP Scope
Video & Livestream: - Capture video from 1–2 cameras (USB / IP / phone stream) - Output live RTMP
stream (YouTube / test server) - Automatically switch cameras based on AI decisions
AI Director Logic: - Detect dog + handler using computer vision - Track subjects across frames - Calculate Frame Quality Score (FQS) per camera - Rule-based camera switching (thresholds, cooldowns, fallback camera) - Avoid excessive switching (cooldowns, obstacle locks)
Graphics Overlay: - Show overlays: Category, Handler Name, Dog Name, Country, Time, Faults/Refusals - Competitor data loaded from Excel/CSV - Timing data can be mocked for MVP
Highlights: - Automatically record each run - Generate short highlight clip after run - Play highlight before next competitor
Tech Stack: - Python, OpenCV, YOLOv8 (or similar), FFmpeg / RTMP, Docker (optional)
Deliverables: - Working MVP prototype - Source code (modular, documented) - Demo video or test
livestream - Basic setup instructions
Why This Project is Interesting: - Real-world AI application - Clear commercial potential - No vague AI promises - Opportunity to shape a real product from the start
REQUIREMENTS:
Tech stack (preferred, flexible)
- Python
- OpenCV
- YOLOv8 (or similar)
- FFmpeg / RTMP
- Optional: Docker
- Frontend UI can be minimal or skipped for MVP
Deliverables
- Working MVP prototype
- Source code (modular, documented)
- Demo video or test livestream
- Basic setup instructions
Ideal freelancer profile
- Experience with computer vision
- Experience with video streaming pipelines
- Comfortable with real-time systems
- Able to work independently with clear specs
Bonus:
- Sports video experience
- OBS / broadcast workflows
- Multi-camera systems
Related categories:
Python
Broadcast Engineering
Video Production
Video Editing
Docker
OpenCV
Computer Vision
Video Streaming