Firing Range CCTV Scoring System

I have a fixed-angle CCTV camera pointed at a target board on an outdoor firing range. I need a vision workflow that automatically extracts each frame before and after a shot, pinpoints every new bullet hole, and then calculates the shooter’s score according to standard concentric-ring values. Once the session ends, the system should compile everything into a clear, detailed report that can be downloaded.

Scope of work
• Detect the target board in every frame, even if lighting changes or smoke drifts across the lens.
•

Technical preferences
I am comfortable with Python, so OpenCV, YOLO, TensorFlow, or a similar stack will fit well. If you prefer another language or library, just make sure the final solution runs on Windows 10 and can be triggered by a simple command or scheduled task.

Deliverables
1. Well-commented source code and any trained weight files.
2. A small sample dataset for verification.
3. Step-by-step setup guide.
4. Example output report from the sample footage.

Acceptance criteria
• ≥95 % detection accuracy on fresh impacts in the provided test clips.
• Score calculations match manual scoring within ±1 point per 10-shot group.

If you have prior experience with target-board or ballistics imagery, please mention it and share a short demo or link. I look forward to collaborating and refining this into a reliable scoring tool.