yuanmu97/PacketGame

PacketGame: Multi-Stream Packet Gating for Concurrent Video Inference at Scale

27
/ 100
Experimental

This tool is for engineers or researchers working with large-scale video processing and analysis. It acts as an intelligent filter that optimizes how video streams are processed for tasks like object detection or facial recognition. By analyzing incoming video data before it's fully decoded, PacketGame determines which parts are most relevant, significantly reducing the computational load and allowing for more concurrent video streams to be analyzed efficiently.

No commits in the last 6 months.

Use this if you need to run real-time video inference on many concurrent streams and are struggling with high computational costs or system bottlenecks.

Not ideal if you are working with single video streams or offline batch processing where efficiency gains from packet filtering are less critical.

video-analytics real-time-inference edge-computing surveillance computer-vision-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

14

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 01, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yuanmu97/PacketGame"

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