zaigie/stream-infer

Video streaming inference framework, integrating image algorithms and models for real-time/offline video structuring, lightweight NVIDIA DeepStream. 视频流式推理框架,结合图像算法和模型进行实时/离线视频结构化,轻量版 NVIDIA DeepStream

43
/ 100
Emerging

This tool helps operations teams and scientists analyze video streams by integrating various image analysis algorithms. It takes raw video footage, either live feeds or pre-recorded files, and outputs structured analytical results based on object detection, tracking, or other custom image processing tasks. Ideal users are those needing to extract actionable insights from video for monitoring, review, or operational feedback.

No commits in the last 6 months. Available on PyPI.

Use this if you need to apply custom image analysis algorithms to real-time camera feeds or existing video files to get structured data, such as for surveillance, surgical review, or live event analysis.

Not ideal if you're looking for a simple video player or a tool that doesn't require custom algorithm integration for complex video content analysis.

video-analytics real-time-monitoring image-processing operations-intelligence scientific-imaging
Stale 6m
Maintenance 2 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 9 / 25

How are scores calculated?

Stars

28

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Sep 11, 2025

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zaigie/stream-infer"

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