UCAS-GYX/YouTube-GDD

YouTube-GDD: A challenging gun detection dataset with rich contextual information

46
/ 100
Emerging

This project provides a specialized collection of 5000 images, sourced from 343 high-definition YouTube videos, specifically for improving automated gun detection. It delivers image data along with detailed annotations for both guns and people, capturing the dynamic changes of guns during shooting. Security analysts, surveillance system developers, or researchers working on automated threat detection would use this to build and test more accurate gun detection systems.

Use this if you are developing or evaluating computer vision models to automatically identify guns in video footage, especially in challenging, real-world scenarios with varying contexts.

Not ideal if you need a dataset for general object detection or if your primary focus is static image analysis without dynamic contextual changes.

security-analytics threat-detection surveillance-systems public-safety computer-vision-research
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

38

Forks

8

Language

Python

License

Apache-2.0

Last pushed

Dec 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/UCAS-GYX/YouTube-GDD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.