Mirrors/blakeblackshear.frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2025-01-07 00:06:57 +01:00
Code Issues Projects Releases Wiki Activity
NVR with realtime local object detection for IP cameras
755 Commits 47 Branches 128 Tags 244 MiB
Python 47.8%
TypeScript 47.5%
CSS 1.4%
C++ 1.1%
Dockerfile 0.7%
Other 1.5%
58c0d97b5f
Go to file
Charles Munger 58c0d97b5f Include timestamps for notification examples 
In the homeassistant app, the notification timestamp is generated when the push message is received by the app. Delays caused by servers, device load, or network latency/availability will delay those pushes - so in the following case:

1:00 - A dog is detected in the front
1:02 - It stops moving around or leaves view, last notification push sent
1:05 - The phone connects to the network

The user, seeing the alert at 1:05, will see that the notification occurred "a few seconds ago", since the timestamp the app sends to the OS was at 1:05. By adding the `when` parameter, it will instead correctly show that the event was triggered at 1:00.

This is exacerbated by the fact that the default behavior of android pushes won't wake the device from deep sleep - in order to receive it as a high priority notification, the additional parameters

```
data:
  priority: high
  ttl: 0
```
have to be added.
2021-08-14 07:35:52 -05:00
.github Add paularmstrong to funding.yml 2021-02-24 20:58:44 -06:00
docker unpin numpy 2021-02-20 08:20:17 -06:00
docs Include timestamps for notification examples 2021-08-14 07:35:52 -05:00
frigate use gevent sleep to prevent mjpeg from blocking 2021-02-25 06:34:36 -06:00
migrations add database migrations 2021-01-26 21:40:33 -06:00
nginx simple echo websocket working 2021-02-20 08:20:17 -06:00
web build(deps): bump browserslist from 4.16.1 to 4.16.6 in /web 2021-06-05 07:30:53 -05:00
.dockerignore adding version endpoint 2021-01-26 21:40:33 -06:00
.gitignore test(web): add unit test framework 2021-02-20 08:20:17 -06:00
benchmark.py
labelmap.txt
LICENSE
Makefile version tick 2021-02-25 06:34:36 -06:00
README.md Correct spelling Home Assistant 2021-05-01 06:33:49 -05:00
run.sh fix graceful exits 2021-01-26 21:40:33 -06:00

README.md

logo

Frigate - NVR With Realtime Object Detection for IP Cameras

A complete and local NVR designed for Home Assistant with AI object detection. Uses OpenCV and Tensorflow to perform realtime object detection locally for IP cameras.

Use of a Google Coral Accelerator is optional, but highly recommended. The Coral will outperform even the best CPUs and can process 100+ FPS with very little overhead.

  • Tight integration with Home Assistant via a custom component
  • Designed to minimize resource use and maximize performance by only looking for objects when and where it is necessary
  • Leverages multiprocessing heavily with an emphasis on realtime over processing every frame
  • Uses a very low overhead motion detection to determine where to run object detection
  • Object detection with TensorFlow runs in separate processes for maximum FPS
  • Communicates over MQTT for easy integration into other systems
  • Records video clips of detected objects
  • 24/7 recording
  • Re-streaming via RTMP to reduce the number of connections to your camera

Documentation

View the documentation at https://blakeblackshear.github.io/frigate

Donations

If you would like to make a donation to support development, please use Github Sponsors.

Screenshots

Integration into Home Assistant

Also comes with a builtin UI:

Events