aws-samples/amazon-rekognition-video-analyzer
A working prototype for capturing frames off of a live MJPEG video stream, identifying objects in near real-time using deep learning, and triggering actions based on an objects watch list.
This solution helps security professionals and operations teams monitor live video streams from IP cameras to detect specific objects or events. It takes a live video feed, processes it in real-time to identify predefined objects using deep learning, and then sends out SMS alerts when those objects are detected. The system also stores analyzed video frames with metadata for later review in a web-based interface.
378 stars. No commits in the last 6 months.
Use this if you need a serverless, low-latency system to automatically monitor surveillance camera feeds for specific objects and trigger immediate alerts.
Not ideal if you're not comfortable setting up AWS services and configuring Python environments, as it requires significant technical setup.
Stars
378
Forks
161
Language
JavaScript
License
—
Category
Last pushed
Feb 23, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/aws-samples/amazon-rekognition-video-analyzer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ZoneMinder/zmNinja
High performance, cross platform ionic app for Home/Commerical Security Surveillance using ZoneMinder
hijam-git/Porda-AI
The World's First Realtime onDevice AI Project to maintian Modestey and Religious values. ...
w00000dy/ai-object-detection
A web AI object detection
trekhleb/links-detector
📖 👆🏻 Links Detector makes printed links clickable via your smartphone camera. No need to type a...
memoakten/webcam-pix2pix-tensorflow
Source code and pretrained model for running pix2pix in realtime on a webcam feed.